content large_stringlengths 3 20.5k | url large_stringlengths 53 192 β | branch large_stringclasses 4
values | source large_stringclasses 51
values | embeddings listlengths 384 384 | score float64 -0.21 0.65 |
|---|---|---|---|---|---|
running job's schedule or prompt /cron edit --schedule "every 4h" /cron edit --prompt "Updated task description" # Add or remove skills from an existing job /cron edit --skill arxiv --skill obsidian /cron edit --clear-skills # Remove a job permanently /cron remove ``` --- ## Delivery Targets The `--deliver` flag contro... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/automate-with-cron.md | main | hermes-agent | [
0.0023638284765183926,
-0.04277315363287926,
-0.051336921751499176,
0.05527353286743164,
0.022041847929358482,
-0.039177700877189636,
0.031104298308491707,
-0.03096908889710903,
-0.045592162758111954,
0.02963063307106495,
0.02615421451628208,
-0.05055605247616768,
0.018770338967442513,
0.0... | 0.067934 |
# Operate the Teams Meeting Pipeline Use this guide after you have already enabled the feature from [Teams Meetings](/user-guide/messaging/teams-meetings). This page covers: - operator CLI flows - routine subscription maintenance - failure triage - go-live checks - rollout worksheet ## Core Operator Commands ### Valida... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/operate-teams-meeting-pipeline.md | main | hermes-agent | [
-0.046060655266046524,
-0.023044979199767113,
-0.027054939419031143,
-0.00021656908211298287,
0.018924737349152565,
-0.08277774602174759,
-0.047804996371269226,
-0.07985441386699677,
0.025830864906311035,
0.014318692497909069,
-0.030857475474476814,
-0.03148937597870827,
0.04492248222231865,... | 0.077103 |
teams-pipeline maintain-subscriptions --dry-run` - inspect `hermes teams-pipeline list --status failed` - verify the Teams delivery target is still the correct chat or channel ### Before changing webhook URLs or delivery targets - update the public notification URL or Teams target config - run `hermes teams-pipeline va... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/operate-teams-meeting-pipeline.md | main | hermes-agent | [
-0.07493327558040619,
-0.0016865684883669019,
-0.024797851219773293,
-0.005252863746136427,
0.04780617356300354,
-0.09382588416337967,
-0.09372106194496155,
-0.10299085825681686,
-0.0020485343411564827,
0.05574515461921692,
-0.0015170255210250616,
-0.06726580858230591,
0.0022087045945227146,... | 0.09251 |
| | Are we moving to a new Teams chat or channel? | | | Do subscriptions need to be recreated or renewed? | | | Do we need a fresh end-to-end verification run? | | ## Related Docs - [Teams Meetings setup](/user-guide/messaging/teams-meetings) - [Microsoft Teams bot setup](/user-guide/messaging/teams) | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/operate-teams-meeting-pipeline.md | main | hermes-agent | [
-0.06306418776512146,
-0.11493626236915588,
-0.021559402346611023,
0.004564434289932251,
0.07989812642335892,
-0.051977213472127914,
-0.023411057889461517,
-0.1004316508769989,
0.050106585025787354,
0.012278387323021889,
-0.008288643322885036,
0.060196150094270706,
-0.014314983040094376,
0... | 0.059418 |
# Automation Templates Copy-paste recipes for common automation patterns. Each template uses Hermes's built-in [cron scheduler](/user-guide/features/cron) for time-based triggers and [webhook platform](/user-guide/messaging/webhooks) for event-driven triggers. Every template works with \*\*any model\*\* β not locked to... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/automation-templates.md | main | hermes-agent | [
-0.11674249172210693,
-0.021135175600647926,
-0.05908925086259842,
-0.005540082696825266,
0.032555364072322845,
-0.04297222942113876,
-0.015091078355908394,
0.006689985282719135,
0.010471408255398273,
-0.002349219052121043,
0.035548433661460876,
-0.05881097540259361,
0.03700890392065048,
-... | 0.16537 |
for each code change, check if the corresponding docs page was also updated in the same PR Report any gaps where code changed but docs didn't. If everything is in sync, respond with [SILENT]." \ --name "Docs drift detection" \ --deliver telegram ``` ### Dependency Security Audit Daily scan for known vulnerabilities in ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/automation-templates.md | main | hermes-agent | [
-0.061458420008420944,
0.014679697342216969,
0.0027595346327871084,
-0.017409980297088623,
0.04116533696651459,
-0.09199489653110504,
-0.06514560431241989,
-0.028151005506515503,
0.023053057491779327,
0.07342147827148438,
0.034352175891399384,
-0.0316089503467083,
0.02214164100587368,
-0.0... | 0.052481 |
reports OUTAGE DETECTED, summarize which services are down and suggest likely causes. If NO\_ISSUES, respond with [SILENT]." \ --script ~/.hermes/scripts/check-uptime.py \ --name "Uptime monitor" \ --deliver telegram ``` --- ## Research & Intelligence ### Competitive Repository Scout Monitor competitor repos for intere... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/automation-templates.md | main | hermes-agent | [
-0.05375842750072479,
0.0003162465582136065,
-0.017553338780999184,
-0.011828639544546604,
0.07593046128749847,
-0.10213947296142578,
0.019369006156921387,
0.0017507584998384118,
0.027816304937005043,
0.08943519741296768,
-0.007020227611064911,
-0.00154963752720505,
0.004418674390763044,
0... | 0.170384 |
If conclusion is "success", respond with [SILENT]. deliver: "github\_comment" deliver\_extra: repo: "{repository.full\_name}" pr\_number: "{check\_run.pull\_requests.0.number}" ``` ### Auto-Port Changes Across Repos When a PR merges in one repo, automatically port the equivalent change to another. \*\*Trigger:\*\* GitH... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/automation-templates.md | main | hermes-agent | [
-0.0804833322763443,
-0.013112274929881096,
0.004020791966468096,
-0.027785295620560646,
0.029802240431308746,
-0.09818252921104431,
0.03775070607662201,
-0.027031859382987022,
0.07054449617862701,
0.05099461227655411,
0.062046803534030914,
-0.04092614725232124,
0.01789737306535244,
-0.040... | 0.074451 |
takeaway 4. Save the outline to ~/drafts/blog-$(date +%Y%m%d).md Keep the outline to ~300 words. This is a starting point, not a finished post." \ --name "Blog outline" \ --deliver local ``` --- ## Quick Reference ### Cron Schedule Syntax | Expression | Meaning | |-----------|---------| | `every 30m` | Every 30 minutes... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/automation-templates.md | main | hermes-agent | [
-0.014759127050638199,
0.02615901082754135,
-0.03284382075071335,
0.07326662540435791,
0.02468906156718731,
-0.003387893084436655,
0.037226352840662,
0.0007943000528030097,
-0.05622250214219093,
0.043276090174913406,
-0.016840966418385506,
-0.030131202191114426,
-0.024786923080682755,
0.01... | 0.028648 |
# Using Hermes as a Python Library Hermes isn't just a CLI tool. You can import `AIAgent` directly and use it programmatically in your own Python scripts, web applications, or automation pipelines. This guide shows you how. --- ## Installation Install Hermes directly from the repository: ```bash pip install git+https:/... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/python-library.md | main | hermes-agent | [
-0.04057701304554939,
0.00510550569742918,
-0.07516822963953018,
-0.03139616921544075,
-0.005627401638776064,
-0.09589630365371704,
-0.002738791285082698,
0.022616619244217873,
0.004420681390911341,
0.010591309517621994,
0.016869252547621727,
-0.07113124430179596,
0.06057741492986679,
-0.0... | 0.094811 |
easy to collect datasets from automated runs. --- ## Custom System Prompts Use `ephemeral\_system\_prompt` to set a custom system prompt that guides the agent's behavior but is \*\*not\*\* saved to trajectory files (keeping your training data clean): ```python agent = AIAgent( model="anthropic/claude-sonnet-4", ephemer... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/python-library.md | main | hermes-agent | [
-0.009577074088156223,
-0.0026372112333774567,
-0.09508293122053146,
0.03670215606689453,
-0.05071990191936493,
-0.07303480058908463,
0.051254868507385254,
0.05835805460810661,
-0.08796945214271545,
0.01658221334218979,
0.0029891622252762318,
-0.03826137259602547,
0.08227359503507614,
-0.0... | 0.136856 |
etc.) | --- ## Important Notes :::tip - Set \*\*`skip\_context\_files=True`\*\* if you don't want `AGENTS.md` files from the working directory loaded into the system prompt. - Set \*\*`skip\_memory=True`\*\* to prevent the agent from reading or writing persistent memory β recommended for stateless API endpoints. - The ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/python-library.md | main | hermes-agent | [
-0.025457164272665977,
0.004184163175523281,
-0.07191111147403717,
-0.031446199864149094,
-0.0017165635945275426,
-0.03369836136698723,
0.09906341135501862,
0.03647226467728615,
0.03609678894281387,
0.03898394852876663,
0.009226925671100616,
-0.016718516126275063,
0.02557738684117794,
-0.0... | 0.250574 |
# Set Up a Team Telegram Assistant This tutorial walks you through setting up a Telegram bot powered by Hermes Agent that multiple team members can use. By the end, your team will have a shared AI assistant they can message for help with code, research, system administration, and anything else β secured with per-user a... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/team-telegram-assistant.md | main | hermes-agent | [
-0.08825938403606415,
-0.010534405708312988,
-0.022584406659007072,
-0.036152906715869904,
-0.033888183534145355,
-0.06274684518575668,
0.009795736521482468,
0.023126540705561638,
0.006915253587067127,
0.07006492465734482,
-0.0004898232873529196,
-0.05374070629477501,
0.046436991542577744,
... | 0.205407 |
Copy that number into `TELEGRAM\_ALLOWED\_USERS` :::info Telegram user IDs are permanent numbers like `123456789`. They're different from your `@username`, which can change. Always use the numeric ID for allowlists. ::: --- ## Step 3: Start the Gateway ### Quick Test Run the gateway in the foreground first to make sure... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/team-telegram-assistant.md | main | hermes-agent | [
-0.04559812322258949,
-0.011958811432123184,
-0.02082500047981739,
-0.07052668184041977,
-0.03987869247794151,
-0.05669545754790306,
0.033254485577344894,
0.008575933054089546,
0.02561149373650551,
0.039163753390312195,
-0.015884164720773697,
-0.0021972821559756994,
0.03147605061531067,
0.... | 0.124109 |
randomness - Rate limiting prevents brute-force attacks: 1 request per user per 10 minutes, max 3 pending codes per platform - After 5 failed approval attempts, the platform enters a 1-hour lockout - All pairing data is stored with `chmod 0600` permissions --- ## Step 5: Configure the Bot ### Set a Home Channel A \*\*h... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/team-telegram-assistant.md | main | hermes-agent | [
-0.058813296258449554,
0.001909120474010706,
-0.02175610512495041,
-0.005885921884328127,
0.009033986367285252,
-0.04951992630958557,
0.04635971412062645,
-0.008628720417618752,
0.01776503585278988,
0.07049372792243958,
-0.0028111517895013094,
-0.058525435626506805,
0.05395185574889183,
0.... | 0.114883 |
no memory of prior conversations. Make sure each prompt contains \*\*all\*\* the context the agent needs β file paths, URLs, server addresses, and clear instructions. ::: --- ## Production Tips ### Use Docker for Safety On a shared team bot, use Docker as the terminal backend so agent commands run in a container instea... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/team-telegram-assistant.md | main | hermes-agent | [
0.03967572748661041,
0.03843143954873085,
-0.03127242997288704,
-0.022442592307925224,
0.05413435027003288,
-0.13972574472427368,
-0.07504633814096451,
-0.012335723266005516,
0.04470585659146309,
0.08101566880941391,
-0.04309636726975441,
-0.007987631484866142,
0.04265754669904709,
-0.0337... | 0.052497 |
# Run Hermes Agent with Nous Portal This guide walks you through running Hermes Agent on a [Nous Portal](https://portal.nousresearch.com) subscription end to end β from signing up to verifying that every tool routes correctly. If you just want the overview of what the Portal is and what's in the subscription, see the [... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/run-hermes-with-nous-portal.md | main | hermes-agent | [
0.003247736254706979,
0.019023463129997253,
-0.0906323790550232,
-0.06513489782810211,
0.012557902373373508,
-0.1008288562297821,
-0.06739405542612076,
-0.03653882071375847,
0.03452618420124054,
-0.025528665632009506,
0.025022605434060097,
-0.008919808082282543,
0.02624695934355259,
-0.031... | 0.047982 |
/model ``` Pick a different default permanently: ```bash # in your terminal, outside any session hermes config set model.default anthropic/claude-sonnet-4.6 ``` ### Don't pick Hermes-4 for agent work Hermes-4-70B and Hermes-4-405B are available on the Portal at deep discounts, but they're \*\*chat/reasoning models\*\*,... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/run-hermes-with-nous-portal.md | main | hermes-agent | [
-0.048370636999607086,
-0.04818147420883179,
-0.07846193760633469,
-0.035843625664711,
-0.04825470969080925,
-0.07790743559598923,
-0.004340033512562513,
-0.039334796369075775,
0.03589508682489395,
0.018159426748752594,
-0.005388947669416666,
0.021454816684126854,
0.017028216272592545,
0.0... | 0.114564 |
workarounds. ### "Model: currently openrouter" (or some other provider) instead of "using Nous as inference provider" Your local config drifted. The OAuth worked but `model.provider` is still pointing at a different provider. Fix: ```bash hermes config set model.provider nous ``` Or interactively: ```bash hermes model ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/run-hermes-with-nous-portal.md | main | hermes-agent | [
-0.012476119212806225,
-0.02418924681842327,
-0.03226906433701515,
-0.010992957279086113,
0.018457137048244476,
-0.09772750735282898,
-0.05085274949669838,
-0.029224323108792305,
0.05048485845327377,
0.007663271855562925,
0.015322249382734299,
0.01963186264038086,
0.04610206186771393,
-0.0... | -0.017114 |
# Automated GitHub PR Comments with Webhooks This guide walks you through connecting Hermes Agent to GitHub so it automatically fetches a pull request's diff, analyzes the code changes, and posts a comment β triggered by a webhook event with no manual prompting. When a PR is opened or updated, GitHub sends a webhook PO... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/webhook-github-pr-review.md | main | hermes-agent | [
-0.10026866942644119,
0.025482255965471268,
-0.1032872200012207,
-0.011768271215260029,
0.043222952634096146,
-0.13518932461738586,
-0.04570476710796356,
-0.019472960382699966,
0.03292084112763405,
0.07225654274225235,
0.011987760663032532,
-0.030098842456936836,
0.03525833040475845,
-0.07... | 0.101125 |
the default `hermes-webhook` toolset, so no extra configuration is needed. ::: --- ## Step 2 β Start the gateway ```bash hermes gateway ``` You should see: ``` [webhook] Listening on 0.0.0.0:8644 β routes: github-pr-review ``` Verify it's running: ```bash curl http://localhost:8644/health # {"status": "ok", "platform":... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/webhook-github-pr-review.md | main | hermes-agent | [
-0.03181685879826546,
0.03421332687139511,
-0.10262428224086761,
-0.01763669215142727,
-0.00905236043035984,
-0.08767324686050415,
-0.07944542914628983,
-0.041002560406923294,
0.007923528552055359,
0.05129149556159973,
0.013105230405926704,
-0.035379983484745026,
0.028772545978426933,
-0.0... | 0.019237 |
There is no Jinja2 or conditional template syntax. `{field}` and `{nested.field}` are the only substitutions supported. Anything else is passed verbatim to the agent. --- ## Using a skill for consistent review style Load a [Hermes skill](/user-guide/features/skills) to give the agent a consistent review persona. Add `s... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/webhook-github-pr-review.md | main | hermes-agent | [
-0.09564907103776932,
0.10755528509616852,
-0.02146780677139759,
0.013877498917281628,
0.04815003648400307,
-0.005228772759437561,
-0.01926114410161972,
-0.04543423280119896,
-0.022368697449564934,
0.026110008358955383,
0.02047700248658657,
-0.06308633834123611,
0.024858344346284866,
-0.00... | 0.030458 |
`404 Unknown route` | Route name in the URL doesn't match the key in `routes:` | | `429 Rate limit exceeded` | 30 req/min per route exceeded β common when re-delivering test events from GitHub's UI; wait a minute or raise `extra.rate\_limit` | | No comment posted | `gh` not installed, not on PATH, or not authenticated ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/webhook-github-pr-review.md | main | hermes-agent | [
-0.019100669771432877,
-0.018122605979442596,
-0.050363488495349884,
-0.012946221977472305,
0.018366454169154167,
-0.11047808080911636,
-0.08341755717992783,
-0.04500642046332359,
-0.013409431092441082,
0.03433243930339813,
0.09242017567157745,
-0.011569240130484104,
-0.016986127942800522,
... | 0.03542 |
# OAuth over SSH / Remote Hosts Some Hermes providers β \*\*xAI Grok OAuth\*\*, \*\*Spotify\*\*, and \*\*remote MCP servers\*\* (Linear, Sentry, Atlassian, Asana, Figma, β¦) β use a \*loopback redirect\* OAuth flow. The auth server redirects your browser to `http://127.0.0.1:/callback` so a tiny HTTP listener started by... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/oauth-over-ssh.md | main | hermes-agent | [
0.0167183056473732,
-0.001580184092745185,
0.01184919849038124,
-0.057784516364336014,
0.005211659241467714,
-0.10702726244926453,
-0.015463092364370823,
-0.04108724743127823,
0.04443124681711197,
-0.03668713942170143,
-0.0016975629841908813,
-0.005693595856428146,
0.07415614277124405,
-0.... | -0.021611 |
(Linear, Sentry, Atlassian, Asana, Figma, etc.) use the same loopback redirect flow. Hermes auto-picks a free port per server and prints the authorize URL when the OAuth flow kicks off β either at startup (when a new server appears in `mcp\_servers:`) or when you run `hermes mcp login `. You have two ways to complete i... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/oauth-over-ssh.md | main | hermes-agent | [
-0.003536810167133808,
0.025333015248179436,
0.006680086255073547,
-0.01775379106402397,
-0.01831299439072609,
-0.1228802278637886,
-0.08784903585910797,
-0.024296965450048447,
0.029393166303634644,
0.03170086070895195,
-0.030651696026325226,
0.005717620253562927,
0.0529320053756237,
-0.00... | -0.018277 |
`Login successful!`. You can tear down the tunnel (Ctrl+C in the first terminal) once you see the success line. ## Step-by-step: through a jump box If you reach Hermes through a bastion / jump host, use SSH's built-in `-J` (ProxyJump): ```bash ssh -N -L 56121:127.0.0.1:56121 -J jump-user@jump-host user@final-host ``` T... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/oauth-over-ssh.md | main | hermes-agent | [
0.003812213661149144,
0.01624572090804577,
-0.03309938311576843,
-0.03636585548520088,
-0.04284631833434105,
0.0006632019067183137,
-0.05436808988451958,
-0.011971653439104557,
-0.0005825487896800041,
-0.005740161053836346,
0.0299441646784544,
0.04476107656955719,
0.05920669063925743,
0.00... | -0.032854 |
# Tutorial: Build a GitHub PR Review Agent \*\*The problem:\*\* Your team opens PRs faster than you can review them. PRs sit for days waiting for eyeballs. Junior devs merge bugs because nobody had time to check. You spend your mornings catching up on diffs instead of building. \*\*The solution:\*\* An AI agent that wa... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/github-pr-review-agent.md | main | hermes-agent | [
-0.11518792808055878,
-0.04303791746497154,
-0.09839603304862976,
-0.014127448201179504,
0.05823154374957085,
-0.09272512793540955,
0.027913594618439674,
0.02152939885854721,
0.0026626773178577423,
0.11575011163949966,
0.0514954999089241,
-0.041057366877794266,
0.00830808188766241,
-0.0201... | 0.118352 |
/ Suggestion - \*\*What's wrong\*\* β one sentence - \*\*Fix\*\* β how to fix it ## Rules - Be specific. Quote the problematic code. - Don't flag style nitpicks unless they affect readability. - If the PR looks good, say so. Don't invent problems. - End with: APPROVE / REQUEST\_CHANGES / COMMENT ``` Verify it loaded β ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/github-pr-review-agent.md | main | hermes-agent | [
-0.11254304647445679,
0.06798230856657028,
-0.016684014350175858,
0.022216126322746277,
0.013932009227573872,
-0.06640072166919708,
0.03055826760828495,
0.005326560698449612,
-0.11176781356334686,
0.09078005701303482,
-0.00368487904779613,
-0.013938304036855698,
0.0519157312810421,
0.00149... | 0.025221 |
count and oldest PR age 2. PRs merged this week 3. Stale PRs (older than 5 days) 4. PRs with no reviewer assigned Format as a clean summary." \ --name "weekly-dashboard" \ --deliver telegram ``` ### Multi-Repo Monitoring Scale up by adding more repos to the prompt. The agent processes them sequentially β no extra setup... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/github-pr-review-agent.md | main | hermes-agent | [
-0.0512734018266201,
-0.029607489705085754,
-0.09569812566041946,
-0.010065975598990917,
-0.021096324548125267,
-0.05647798627614975,
-0.03797992691397667,
0.024904564023017883,
-0.0324547104537487,
0.09456796944141388,
0.05030494183301926,
-0.017707135528326035,
0.04263770207762718,
-0.03... | 0.041828 |
# Tutorial: Build a Daily Briefing Bot In this tutorial, you'll build a personal briefing bot that wakes up every morning, researches topics you care about, summarizes the findings, and delivers a concise briefing straight to your Telegram or Discord. By the end, you'll have a fully automated workflow combining \*\*web... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/daily-briefing-bot.md | main | hermes-agent | [
-0.08832202851772308,
0.017901061102747917,
-0.0055983662605285645,
-0.0048753125593066216,
-0.007109842728823423,
-0.07407784461975098,
0.004298217128962278,
-0.006041904911398888,
-0.0019434333080425858,
-0.003319515846669674,
-0.030984381213784218,
-0.05507030710577965,
0.0061110309325158... | 0.211732 |
Every morning at 8am, search the web for the latest news about AI agents and open source LLMs. Summarize the top 3 stories in a concise briefing with links. Use a friendly, professional tone. Deliver to telegram. ``` Hermes will create the cron job for you using the unified `cronjob` tool. ### Option B: CLI Slash Comma... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/daily-briefing-bot.md | main | hermes-agent | [
-0.030331425368785858,
-0.01452003512531519,
-0.008255226537585258,
-0.00171137775760144,
0.05614683777093887,
0.005932235158979893,
-0.012476964853703976,
0.04709494486451149,
-0.009809670969843864,
0.02735658548772335,
-0.04269261285662651,
-0.02847561612725258,
-0.012280909344553947,
0.... | 0.183702 |
Don't need briefings on weekends? Use a cron expression that targets MondayβFriday: ``` /cron add "0 8 \* \* 1-5" "Search for the latest AI and tech news..." ``` ### Twice-Daily Briefings Get a morning overview and an evening recap: ``` /cron add "0 8 \* \* \*" "Morning briefing: search for AI news from the past 12 hou... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/daily-briefing-bot.md | main | hermes-agent | [
-0.04002251476049423,
-0.006396229844540358,
-0.0402207188308239,
0.053631700575351715,
0.029085129499435425,
0.03665181249380112,
0.038844507187604904,
0.04964122921228409,
-0.03778694570064545,
-0.04579063877463341,
-0.08227009326219559,
-0.041261978447437286,
-0.06118674576282501,
0.044... | 0.093081 |
# Pipe Script Output to Messaging Platforms `hermes send` is a small, scriptable CLI that pushes a message to any messaging platform Hermes is already configured for. Think of it as a cross-platform `curl` for notifications β you don't need a running gateway, you don't need an LLM, and you don't need to re-paste bot to... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/pipe-script-output.md | main | hermes-agent | [
-0.004468260332942009,
-0.013988516293466091,
-0.024196553975343704,
-0.021763794124126434,
-0.019886041060090065,
-0.10756780207157135,
0.006360742729157209,
0.04532715678215027,
0.020924022421240807,
0.04999784380197525,
0.004818200133740902,
-0.06361439824104309,
0.05865523964166641,
-0... | 0.139832 |
wait for input β you'll get a clear usage error instead. This keeps scripts from hanging if they accidentally omit the body. --- ## Real-World Examples ### Monitoring: Memory / Disk Alerts Replace ad-hoc `curl https://api.telegram.org/...` calls in your watchdogs with a single portable line: ```bash #!/usr/bin/env bash... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/pipe-script-output.md | main | hermes-agent | [
0.020715629681944847,
0.05345273017883301,
-0.036697857081890106,
0.039778027683496475,
0.011341467499732971,
-0.09421247988939285,
0.035679012537002563,
0.02612975984811783,
0.07986869663000107,
0.060521360486745834,
-0.0032016730401664972,
0.004748388193547726,
0.07701216638088226,
-0.03... | 0.130906 |
| β
| No (bot-token) | Everything below | | Raw `curl` to each platform | Each scripted separately | Manual | No | Critical watchdogs | | `cron` job with `--deliver` | β
| β
| No | Scheduled agent tasks | | `send\_message` agent tool | β
| β
| No | Inside an agent loop | `hermes send` is intentionally the simplest poss... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/pipe-script-output.md | main | hermes-agent | [
-0.04533570632338524,
-0.022644154727458954,
-0.05048678070306778,
-0.008134029805660248,
-0.04270245134830475,
-0.0778222605586052,
-0.024330152198672295,
0.03051353432238102,
0.017925940454006195,
0.009170337580144405,
-0.007315852213650942,
-0.07363805919885635,
0.06356203556060791,
-0.... | 0.109316 |
# Use SOUL.md with Hermes `SOUL.md` is the \*\*primary identity\*\* for your Hermes instance. It's the first thing in the system prompt β it defines who the agent is, how it speaks, and what it avoids. If you want Hermes to feel like the same assistant every time you talk to it β or if you want to replace the Hermes pe... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/use-soul-with-hermes.md | main | hermes-agent | [
-0.045841194689273834,
0.0381089486181736,
-0.06762148439884186,
-0.11194004118442535,
-0.04661291465163231,
-0.06257735192775726,
0.0716496929526329,
-0.04255078732967377,
0.020109858363866806,
0.024302713572978973,
-0.014643294736742973,
-0.0018240041099488735,
0.06236899644136429,
-0.02... | 0.119243 |
3. Teacher / explainer ```markdown You are a patient technical teacher. You care about understanding, not performance. ## Style - Explain clearly - Use examples when they help - Do not assume prior knowledge unless the user signals it - Build from intuition to details ``` ### 4. Tough reviewer ```markdown You are a rig... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/use-soul-with-hermes.md | main | hermes-agent | [
-0.06328687816858292,
0.08832675218582153,
0.04756477475166321,
-0.00742114195600152,
0.003687983611598611,
0.004161922261118889,
0.02687678672373295,
0.01589248888194561,
-0.05684935674071312,
0.04538755118846893,
-0.06890314817428589,
0.00991001259535551,
-0.001355811720713973,
-0.014901... | 0.061229 |
# Run Local LLMs on Mac This guide walks you through running a local LLM server on macOS with an OpenAI-compatible API. You get full privacy, zero API costs, and surprisingly good performance on Apple Silicon. We cover two backends: | Backend | Install | Best at | Format | |---------|---------|---------|--------| | \*\... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/local-llm-on-mac.md | main | hermes-agent | [
-0.0233910009264946,
-0.010088099166750908,
0.017451010644435883,
-0.035349126905202866,
0.007472360506653786,
-0.09767861664295197,
-0.06553858518600464,
-0.029844066128134727,
0.03834071010351181,
0.06442055106163025,
-0.012124953791499138,
-0.025358671322464943,
-0.01669440045952797,
0.... | 0.106705 |
when you see: ``` main: server is listening on http://0.0.0.0:8080 srv update\_slots: all slots are idle ``` ### Memory optimization for constrained systems The `--cache-type-k q4\_0 --cache-type-v q4\_0` flags are the most important optimization for systems with limited memory. Here's the impact at 128K context: | KV ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/local-llm-on-mac.md | main | hermes-agent | [
0.0730150043964386,
0.05308207497000694,
-0.04987797513604164,
-0.0047933198511600494,
-0.01816922426223755,
-0.054819148033857346,
-0.03362428769469261,
0.033043522387742996,
0.0016989640425890684,
-0.002868055133149028,
0.04106656834483147,
0.024730609729886055,
-0.047325413674116135,
-0... | 0.082115 |
MLX finishes sooner. - Both backends are \*\*extremely consistent\*\* β variance across runs was negligible. You can rely on these numbers. ### Which one should you pick? | Use case | Recommendation | |----------|---------------| | Interactive chat, low-latency tools | llama.cpp | | Long-form generation, bulk processin... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/local-llm-on-mac.md | main | hermes-agent | [
-0.0005428802105598152,
-0.06824027001857758,
0.026467030867934227,
-0.04441625252366066,
-0.02906102128326893,
-0.076253242790699,
-0.15219639241695404,
0.0038510228041559458,
0.012360945343971252,
-0.028878074139356613,
-0.010512975975871086,
0.004979144316166639,
0.009780618362128735,
-... | 0.037773 |
# Script-Only Cron Jobs Sometimes you already know exactly what message you want to send. You don't need an agent to reason about it β you just need a script to run on a timer, and its output (if any) to land in Telegram / Discord / Slack / Signal. Hermes calls this \*\*no-agent mode\*\*. It's the cron system minus the... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/cron-script-only.md | main | hermes-agent | [
-0.02016713283956051,
-0.02488391473889351,
-0.044782668352127075,
0.02473163791000843,
0.016405174508690834,
-0.0699327141046524,
0.05182145908474922,
0.02373225800693035,
0.05414906516671181,
0.017380056902766228,
0.003430177690461278,
-0.06971153616905212,
0.020410800352692604,
0.030952... | 0.171799 |
`no\_agent=True` whenever the message content is fully determined by the script. It falls back to the normal LLM-driven path when the request needs reasoning (\*"summarize the new issues"\*, \*"pick the most interesting headlines"\*, \*"draft a friendly reminder"\*). You don't have to specify `--no-agent` yourself. Jus... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/cron-script-only.md | main | hermes-agent | [
-0.06041296198964119,
0.011073793284595013,
-0.016143055632710457,
0.04283151775598526,
0.03736129403114319,
0.0021051252260804176,
0.03492286056280136,
-0.04696736857295036,
0.04720050469040871,
-0.014070543460547924,
-0.017968013882637024,
-0.01445835642516613,
0.015951748937368393,
0.02... | 0.087986 |
# specific chat --deliver telegram:-1001234567890:17585 # specific Telegram forum topic --deliver discord:#ops --deliver slack:#engineering --deliver signal:+15551234567 --deliver local # just save to ~/.hermes/cron/output/ ``` No running gateway is required at script-run time for bot-token platforms (Telegram, Discord... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/cron-script-only.md | main | hermes-agent | [
-0.05024129897356033,
-0.049400027841329575,
-0.02457553893327713,
-0.031105589121580124,
-0.01502666063606739,
-0.04798639938235283,
-0.03551643714308739,
-0.007207291200757027,
0.03883196786046028,
0.04753744974732399,
0.019360659644007683,
-0.02468698099255562,
0.017506122589111328,
-0.... | 0.10944 |
# Build a Hermes Plugin This guide walks through building a complete Hermes plugin from scratch. By the end you'll have a working plugin with multiple tools, lifecycle hooks, shipped data files, and a bundled skill β everything the plugin system supports. :::info Not sure which guide you need? Hermes has several distin... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/build-a-hermes-plugin.md | main | hermes-agent | [
-0.10196266323328018,
-0.057411953806877136,
-0.04249199107289314,
-0.006215638015419245,
-0.06213679164648056,
-0.06445648521184921,
-0.015099108219146729,
0.03193242847919464,
-0.044462427496910095,
0.060845110565423965,
0.03810704126954079,
-0.041129786521196365,
0.038958869874477386,
0... | 0.131675 |
-, \*, /, \*\*), functions (sqrt, sin, cos, " "log, abs, round, floor, ceil), and constants (pi, e). " "Use this for any math the user asks about." ), "parameters": { "type": "object", "properties": { "expression": { "type": "string", "description": "Math expression to evaluate (e.g., '2\*\*10', 'sqrt(144)')", }, }, "r... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/build-a-hermes-plugin.md | main | hermes-agent | [
-0.07995999604463577,
0.09519939124584198,
-0.06985525786876678,
0.05473075807094574,
-0.10143322497606277,
-0.03633391857147217,
0.003268119180575013,
0.09618353098630905,
-0.037679992616176605,
0.01978950761258602,
-0.04378775507211685,
-0.1474798172712326,
0.04583832249045372,
0.0148416... | 0.090153 |
lc[to\_unit.lower()] return json.dumps({"input": f"{value} {from\_unit}", "result": round(result, 6), "output": f"{round(result, 6)} {to\_unit}"}) return json.dumps({"error": f"Cannot convert {from\_unit} β {to\_unit}"}) except Exception as e: return json.dumps({"error": f"Conversion failed: {e}"}) ``` \*\*Key rules fo... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/build-a-hermes-plugin.md | main | hermes-agent | [
-0.08729804307222366,
0.09342208504676819,
0.008361085318028927,
0.009328053332865238,
-0.07615432888269424,
-0.07065825909376144,
-0.009916989132761955,
0.027309326454997063,
-0.025591587647795677,
-0.057799551635980606,
0.012058611959218979,
-0.04456072300672531,
0.052809543907642365,
0.... | -0.007591 |
etc.) - on `register()` failure: a full traceback pointing at the line in your `\_\_init\_\_.py` that raised The same logs are always written to `~/.hermes/logs/agent.log` at WARNING level (failures only) and DEBUG level (everything) when the env var is set. So if you can't run with the env var (e.g. from inside the ga... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/build-a-hermes-plugin.md | main | hermes-agent | [
-0.013004424050450325,
-0.05973254516720772,
-0.04470907896757126,
-0.02348247915506363,
0.008497640490531921,
-0.0435713455080986,
-0.05554678663611412,
0.017657464370131493,
-0.023820368573069572,
0.019104216247797012,
0.044677846133708954,
-0.007191269192844629,
0.019299186766147614,
0.... | 0.024248 |
For a better install experience, use the rich format with descriptions and signup URLs: ```yaml # plugin.yaml β rich format requires\_env: - name: WEATHER\_API\_KEY description: "API key for OpenWeather" url: "https://openweathermap.org/api" secret: true ``` | Field | Required | Description | |-------|----------|------... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/build-a-hermes-plugin.md | main | hermes-agent | [
-0.026611948385834694,
0.02782907895743847,
0.0103473961353302,
-0.002392587484791875,
0.018978334963321686,
-0.07157409936189651,
-0.03342282027006149,
0.01654273457825184,
-0.00787645485252142,
-0.009137560613453388,
0.01734337955713272,
-0.08025545626878738,
0.04782845824956894,
0.01153... | -0.015363 |
Before any tool executes | `tool\_name: str, args: dict, task\_id: str` | ignored | | [`post\_tool\_call`](/user-guide/features/hooks#post\_tool\_call) | After any tool returns | `tool\_name: str, args: dict, result: str, task\_id: str, duration\_ms: int` | ignored | | [`pre\_llm\_call`](/user-guide/features/hooks#pre\... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/build-a-hermes-plugin.md | main | hermes-agent | [
-0.04079035669565201,
0.043328091502189636,
-0.040422216057777405,
0.03620137274265289,
-0.07165691256523132,
-0.1016760990023613,
0.07719177007675171,
0.02153979428112507,
0.06188436597585678,
-0.04251033067703247,
0.02512124553322792,
0.00011139573325635865,
-0.013783365488052368,
-0.014... | 0.058122 |
sessions:\n" text += "\n".join(f"- {m['text']}" for m in memories) return {"context": text} except Exception: return None # fail silently, don't break the agent def register(ctx): ctx.register\_hook("pre\_llm\_call", recall\_context) ``` #### Example: Guardrails plugin ```python """Guardrails plugin β enforces content ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/build-a-hermes-plugin.md | main | hermes-agent | [
-0.056784410029649734,
0.052195314317941666,
-0.09338203817605972,
0.05014420300722122,
-0.05476807802915573,
-0.011696930974721909,
0.11847976595163345,
0.09042780101299286,
-0.021052422001957893,
-0.019172070547938347,
0.04620624706149101,
-0.0030239736661314964,
0.0439574271440506,
0.03... | 0.086876 |
receives | Raw args string | argparse `Namespace` | | Use case | Diagnostics, status, quick actions | Complex subcommand trees, setup wizards | \*\*Conflict protection:\*\* If a plugin tries to register a name that conflicts with a built-in command (`help`, `model`, `new`, etc.), the registration is silently rejected w... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/build-a-hermes-plugin.md | main | hermes-agent | [
-0.07607277482748032,
-0.0875600054860115,
-0.07274151593446732,
0.10487762838602066,
-0.10645102709531784,
-0.07226551324129105,
-0.0000193029463844141,
0.004472686909139156,
-0.020103085786104202,
-0.039408065378665924,
-0.015529725700616837,
-0.029561568051576614,
-0.007858410477638245,
... | 0.057498 |
disconnect(self): ... def check\_requirements(): import os return bool(os.environ.get("MYPLATFORM\_TOKEN")) def \_env\_enablement(): import os tok = os.getenv("MYPLATFORM\_TOKEN", "").strip() if not tok: return None return {"token": tok} def register(ctx): ctx.register\_platform( name="myplatform", label="MyPlatform", ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/build-a-hermes-plugin.md | main | hermes-agent | [
-0.02817855030298233,
-0.009719102643430233,
-0.030263805761933327,
-0.01564580760896206,
-0.019537081941962242,
-0.03445923328399658,
-0.02625495195388794,
0.03844406455755234,
-0.0640631839632988,
-0.05436396226286888,
-0.0053948042914271355,
-0.0903431624174118,
0.04333081468939781,
-0.... | 0.065675 |
-> None: if context.get("duration\_seconds", 0) > 120: # send notification β¦ pass ``` Events include `gateway:startup`, `session:start`, `session:end`, `session:reset`, `agent:start`, `agent:step`, `agent:end`, and wildcard `command:\*`. Errors in hooks are caught and logged β they never block the main pipeline. \*\*Fu... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/build-a-hermes-plugin.md | main | hermes-agent | [
-0.018853232264518738,
-0.00043877417920157313,
-0.05429309606552124,
0.004846999887377024,
0.007008928339928389,
-0.06343335658311844,
0.03535085171461105,
0.021542921662330627,
0.05569184198975563,
-0.004585825838148594,
-0.011183850467205048,
-0.059351563453674316,
-0.003096421714872122,
... | 0.094858 |
as e: return json.dumps({"error": str(e)}) ``` \*\*Schema description too vague:\*\* ```python # Bad β model doesn't know when to use it "description": "Does stuff" # Good β model knows exactly when and how "description": "Evaluate a mathematical expression. Use for arithmetic, trig, logarithms. Supports: +, -, \*, /, ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/build-a-hermes-plugin.md | main | hermes-agent | [
-0.05841352790594101,
0.09415289014577866,
0.01708635874092579,
0.02163597196340561,
-0.06245526298880577,
-0.07807502895593643,
-0.03312139958143234,
0.07858153432607651,
0.017050104215741158,
-0.05593715235590935,
0.006486041005700827,
-0.03636036440730095,
-0.013261505402624607,
0.09852... | 0.111719 |
# Use Voice Mode with Hermes This guide is the practical companion to the [Voice Mode feature reference](/user-guide/features/voice-mode). If the feature page explains what voice mode can do, this guide shows how to actually use it well. :::tip [Nous Portal](/integrations/nous-portal) bundles both the LLM and TTS throu... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/use-voice-mode-with-hermes.md | main | hermes-agent | [
-0.07536137849092484,
-0.045381080359220505,
0.026471365243196487,
-0.0933060422539711,
-0.030471736565232277,
-0.06840777397155762,
0.015426956117153168,
0.015643464401364326,
0.02448219619691372,
-0.016342507675290108,
0.007184256333857775,
-0.015316536650061607,
0.01717941090464592,
-0.... | 0.139652 |
is missing, the wizard tells you NeuTTS needs the Python package `neutts` and the system package `espeak-ng`, offers to install them for you, installs `espeak-ng` with your platform package manager, and then runs: ```bash python -m pip install -U neutts[all] ``` If you skip that install or it fails, the wizard falls ba... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/use-voice-mode-with-hermes.md | main | hermes-agent | [
-0.021419238299131393,
-0.03609561547636986,
-0.02140638791024685,
-0.058604851365089417,
-0.04044179245829582,
-0.026424506679177284,
0.001758837839588523,
0.00380197586491704,
0.009940940886735916,
-0.05167142301797867,
0.04090143367648125,
-0.09802303463220596,
-0.07068948447704315,
0.0... | 0.04643 |
to user speech, transcribes it, runs the normal agent pipeline, and speaks replies back into the channel. ## Required Discord permissions In addition to the normal text-bot setup, make sure the bot has: - Connect - Speak - preferably Use Voice Activity Also enable privileged intents in the Developer Portal: - Presence ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/use-voice-mode-with-hermes.md | main | hermes-agent | [
-0.01989278756082058,
-0.09933054447174072,
-0.022796668112277985,
-0.07031121104955673,
-0.03171381726861,
-0.03890665993094444,
0.040753696113824844,
-0.005400924012064934,
0.02087411843240261,
-0.054344065487384796,
-0.025601226836442947,
-0.03744175285100937,
0.0010618770029395819,
0.0... | 0.185461 |
# Use MCP with Hermes This guide shows how to actually use MCP with Hermes Agent in day-to-day workflows. If the feature page explains what MCP is, this guide is about how to get value from it quickly and safely. ## When should you use MCP? Use MCP when: - a tool already exists in MCP form and you do not want to build ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/use-mcp-with-hermes.md | main | hermes-agent | [
-0.0593053475022316,
-0.0010610711760818958,
-0.0014284794451668859,
-0.007895299233496189,
-0.012635644525289536,
-0.035019055008888245,
-0.007973592728376389,
0.012630537152290344,
-0.020246319472789764,
0.04061710834503174,
-0.005500488914549351,
-0.04224833846092224,
0.07914042472839355,... | 0.124284 |
Windows Chrome session Mental model: ```text Hermes (WSL) -> MCP stdio bridge -> Windows Chrome ``` ### Why this mode is useful - you keep your real Windows browser profile, cookies, and logins - Hermes stays in its supported Unix environment (WSL2) - browser control is exposed as MCP tools instead of relying on Hermes... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/use-mcp-with-hermes.md | main | hermes-agent | [
0.008234879933297634,
-0.004113353323191404,
-0.018884796649217606,
0.06768982112407684,
0.03024611808359623,
-0.048302073031663895,
-0.04635346680879593,
0.059742607176303864,
0.016848577186465263,
-0.0014047493459656835,
-0.010822651907801628,
-0.06663571298122406,
0.0016967832343652844,
... | -0.009896 |
internal\_api: url: "https://mcp.internal.example.com" headers: Authorization: "Bearer \*\*\*" tools: include: [list\_customers, get\_customer, list\_invoices] resources: false prompts: false ``` Good prompts: ```text Look up customer ACME Corp and summarize recent invoice activity. ``` This is the sort of place where ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/use-mcp-with-hermes.md | main | hermes-agent | [
-0.07802148163318634,
0.03729728236794472,
0.03838513046503067,
0.009905539453029633,
0.03623242676258087,
-0.038620926439762115,
0.04946715757250786,
0.03363572433590889,
0.016563622280955315,
0.02898045815527439,
0.046239230781793594,
0.005297086201608181,
0.07265152782201767,
-0.0173498... | 0.18573 |
- one narrow internal API Not-great first servers: - giant business systems with lots of destructive actions and no filtering - anything you do not understand well enough to constrain ## Related docs - [MCP (Model Context Protocol)](/user-guide/features/mcp) - [FAQ](/reference/faq) - [Slash Commands](/reference/slash-c... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/use-mcp-with-hermes.md | main | hermes-agent | [
-0.06030260771512985,
-0.0290579404681921,
0.03570124879479408,
-0.04617667943239212,
0.030426647514104843,
-0.03961535915732384,
-0.024465778842568398,
0.05437229573726654,
-0.024561621248722076,
-0.0031809976790100336,
-0.004516792483627796,
0.0038138350937515497,
0.04617154970765114,
0.... | 0.256195 |
# Run Hermes Locally with Ollama β Zero API Cost ## The Problem Cloud LLM APIs charge per token. A heavy coding session can cost $5β20. For personal projects, learning, or privacy-sensitive work, that adds up β and you're sending every conversation to a third party. ## What This Guide Solves You'll set up Hermes Agent ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/local-ollama-setup.md | main | hermes-agent | [
-0.030987557023763657,
-0.030041277408599854,
-0.012795415706932545,
0.014174159616231918,
-0.02411590702831745,
-0.11218363791704178,
-0.08946027606725693,
0.045078665018081665,
0.0563676618039608,
0.09241552650928497,
0.0015539254527539015,
-0.011397179216146469,
0.03003615513443947,
-0.... | 0.092531 |
3: Configure Hermes Run the Hermes setup wizard: ```bash hermes setup ``` When prompted for a provider, select \*\*Custom Endpoint\*\* and enter: - \*\*Base URL:\*\* `http://localhost:11434/v1` - \*\*API Key:\*\* Leave empty or type `no-key` (Ollama doesn't need one) - \*\*Model:\*\* `gemma4:31b` (or whichever model yo... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/local-ollama-setup.md | main | hermes-agent | [
0.005308432038873434,
0.029634686186909676,
-0.016408240422606468,
-0.020674550905823708,
-0.03024601936340332,
-0.11344058066606522,
-0.055318135768175125,
-0.03287498280405998,
0.029509572312235832,
0.019338458776474,
0.01894186995923519,
-0.022791458293795586,
0.043614987283945084,
-0.0... | 0.045765 |
8: Set Up Fallbacks (Optional) Local models can struggle with complex tasks. Set up a cloud fallback that only activates when the local model fails: ```yaml model: default: "gemma4:31b" provider: "custom" base\_url: "http://localhost:11434/v1" fallback\_providers: - provider: openrouter model: anthropic/claude-sonnet-4... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/local-ollama-setup.md | main | hermes-agent | [
-0.0124698206782341,
-0.0016300104325637221,
-0.012089641764760017,
0.07755906879901886,
-0.005868260748684406,
-0.09796950221061707,
-0.08391895145177841,
0.01460940483957529,
-0.026610421016812325,
-0.0014827953418716788,
0.008315631188452244,
0.007598698604851961,
-0.06872475892305374,
... | 0.03492 |
# Register a Microsoft Graph Application The Teams meeting pipeline reads meeting transcripts, recordings, and related artifacts from Microsoft Graph using \*\*app-only\*\* (daemon) authentication β no user sign-in, no interactive consent per meeting. That requires an Azure AD application registration with admin-consen... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/microsoft-graph-app-registration.md | main | hermes-agent | [
-0.042300280183553696,
0.01207524910569191,
-0.09929680824279785,
-0.033420007675886154,
-0.000014594278582080733,
-0.009076331742107868,
-0.015335342846810818,
-0.03471873328089714,
0.029167363420128822,
0.09859728068113327,
-0.023998849093914032,
-0.05694560706615448,
0.01910865120589733,
... | 0.071385 |
channels on behalf of the app. | | `Chat.ReadWrite.All` | Post messages into 1:1 and group chats (only if you set `chat\_id` as the delivery target). | ### Not recommended - `OnlineMeetings.ReadWrite.All` / `Chat.ReadWrite` without `.All` β broader than the pipeline needs. - Delegated permissions β the pipeline uses ap... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/microsoft-graph-app-registration.md | main | hermes-agent | [
0.05244171619415283,
-0.024313071742653847,
-0.04365599900484085,
-0.033184826374053955,
-0.07736667990684509,
-0.06613489240407944,
0.05397653952240944,
-0.002897252794355154,
0.009966992773115635,
0.058889247477054596,
-0.05152960866689682,
-0.008061344735324383,
-0.03658938780426979,
0.... | 0.012585 |
`msgraph\_webhook` gateway platform that receives Graph change notifications. - \*\*Pipeline configuration\*\* β configure the Teams meeting pipeline runtime and operator CLI. - \*\*Outbound delivery\*\* β wire summaries back into a Teams channel or chat. Those pages land alongside the PRs that add the corresponding ru... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/guides/microsoft-graph-app-registration.md | main | hermes-agent | [
-0.1252909153699875,
0.00814148411154747,
-0.0763431042432785,
-0.01732522062957287,
0.0040547531098127365,
-0.05676079913973808,
-0.008993743918836117,
-0.007833143696188927,
-0.004693430382758379,
0.042714253067970276,
-0.036405693739652634,
-0.05004897713661194,
0.016140399500727654,
0.... | 0.143676 |
# Plugin LLM Access `ctx.llm` is the supported way for a plugin to make an LLM call. Chat completion, structured extraction, sync, async, with or without images β same surface, same trust gate, same host-owned credentials. Plugins reach for this when they need to do something that involves the model but isn't part of t... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/plugin-llm-access.md | main | hermes-agent | [
-0.08134713768959045,
-0.0009465541807003319,
-0.004134447779506445,
0.04587062448263168,
-0.05433123931288719,
-0.12431399524211884,
0.021375350654125214,
0.0011135917156934738,
0.03139431029558182,
-0.03654784709215164,
-0.04416602477431297,
-0.0017655957490205765,
0.012877834029495716,
... | 0.110833 |
return "Usage: /tldr " result = ctx.llm.complete( messages=[ {"role": "system", "content": "Summarise the user's text in one tight paragraph. No preamble."}, {"role": "user", "content": text}, ], max\_tokens=256, temperature=0.3, purpose="tldr", ) return result.text ``` `result.text` is the model's response; `result.us... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/plugin-llm-access.md | main | hermes-agent | [
-0.044498004019260406,
0.03268083930015564,
0.023893998935818672,
0.0758432000875473,
-0.019710995256900787,
-0.05289279296994209,
0.049584776163101196,
0.0664699375629425,
0.04768587276339531,
-0.02355126291513443,
0.0172480009496212,
-0.09098544716835022,
0.041574425995349884,
0.01916485... | 0.077463 |
# usage, parsed, content\_type, audit) ``` Inputs are typed text or image blocks (raw bytes get base64 encoded as a `data:` URL automatically). When `json\_schema` or `json\_mode=True` is supplied, the host requests JSON output via `response\_format`, parses it locally as a fallback, and validates against your schema i... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/plugin-llm-access.md | main | hermes-agent | [
0.004672292619943619,
0.017216531559824944,
-0.044158462435007095,
0.06038018688559532,
0.03147372975945473,
-0.06606452167034149,
-0.0860050693154335,
0.027438290417194366,
0.00847509317100048,
-0.03563181310892105,
-0.026723653078079224,
-0.042439430952072144,
0.02706693485379219,
0.0559... | 0.078446 |
trusted to pick a model is still pinned to the user's active provider unless it gets the provider gate as well. ### What the gate does NOT need to enforce \* Request-shaping arguments β `temperature`, `max\_tokens`, `timeout`, `system\_prompt`, `purpose`, `messages`, `instructions`, `input`, `json\_schema`, `schema\_na... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/plugin-llm-access.md | main | hermes-agent | [
-0.09187401831150055,
-0.02548389509320259,
-0.027650222182273865,
0.06995837390422821,
-0.03468756005167961,
-0.04283737763762474,
0.03478124365210533,
0.02458679862320423,
-0.035722531378269196,
0.0304254237562418,
0.03929777443408966,
0.007693820167332888,
0.058083754032850266,
0.019006... | 0.087986 |
[`plugin-llm-async-example`](https://github.com/NousResearch/hermes-example-plugins/tree/main/plugin-llm-async-example) β async with `asyncio.gather()` \* Auxiliary client (the engine under the hood): see [Provider Runtime](/developer-guide/provider-runtime). | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/plugin-llm-access.md | main | hermes-agent | [
-0.11690300703048706,
-0.05091334506869316,
-0.11084350943565369,
0.06905367970466614,
-0.03733965754508972,
-0.06288401782512665,
-0.12054663896560669,
-0.018731648102402687,
-0.00263464474119246,
-0.08508005738258362,
0.04678353667259216,
-0.006316169630736113,
-0.03376391530036926,
-0.0... | 0.099201 |
# Architecture This page is the top-level map of Hermes Agent internals. Use it to orient yourself in the codebase, then dive into subsystem-specific docs for implementation details. ## System Overview ```text βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ β Entry Points β β β β CLI (cli.py) Ga... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/architecture.md | main | hermes-agent | [
-0.036678969860076904,
-0.01566149853169918,
-0.06007155403494835,
-0.02262238971889019,
-0.028093047440052032,
-0.08146673440933228,
-0.0696287676692009,
0.06283056735992432,
-0.07597429305315018,
0.036087989807128906,
0.015715070068836212,
-0.02081807516515255,
0.035050272941589355,
-0.0... | 0.15489 |
implementations (one file per tool) β βββ registry.py # Central tool registry β βββ approval.py # Dangerous command detection β βββ terminal\_tool.py # Terminal orchestration β βββ process\_registry.py # Background process management β βββ file\_tools.py # read\_file, write\_file, patch, search\_files β βββ web\_tools.... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/architecture.md | main | hermes-agent | [
-0.04873396083712578,
-0.013883473351597786,
-0.0627598986029625,
-0.03165052458643913,
0.0028319258708506823,
-0.036763522773981094,
0.00006270578160183504,
0.08903612941503525,
-0.042094916105270386,
0.04926971346139908,
0.03584052622318268,
-0.005957948975265026,
0.06198577955365181,
0.... | 0.078489 |
β `volatile`): identity/tool guidance/skills, context files, then memory/profile/timestamp blocks - \*\*`prompt\_caching.py`\*\* β Applies Anthropic cache breakpoints for prefix caching - \*\*`context\_compressor.py`\*\* β Summarizes middle conversation turns when context exceeds thresholds β [Prompt Assembly](./prompt... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/architecture.md | main | hermes-agent | [
-0.07142609357833862,
0.02312442660331726,
-0.06383959949016571,
-0.0017976955277845263,
-0.021297939121723175,
-0.12984846532344818,
0.042810119688510895,
0.05887091904878616,
0.033559516072273254,
0.0033002120908349752,
-0.031464096158742905,
0.030319392681121826,
0.02780117653310299,
-0... | 0.111798 |
# Provider Runtime Resolution Hermes has a shared provider runtime resolver used across: - CLI - gateway - cron jobs - ACP - auxiliary model calls Primary implementation: - `hermes\_cli/runtime\_provider.py` β credential resolution, `\_resolve\_custom\_runtime()` - `hermes\_cli/auth.py` β provider registry, `resolve\_p... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/provider-runtime.md | main | hermes-agent | [
-0.09494826942682266,
-0.051117587834596634,
-0.05933555215597153,
0.006295969244092703,
-0.09797050803899765,
-0.04171203076839447,
-0.020954348146915436,
0.08217418193817139,
-0.03144644573330879,
-0.02210560254752636,
0.01417650654911995,
0.005373518913984299,
0.022822927683591843,
0.01... | 0.055042 |
when `OPENAI\_BASE\_URL` is not exported in the current shell ## Native Anthropic path Anthropic is not just "via OpenRouter" anymore. When provider resolution selects `anthropic`, Hermes uses: - `api\_mode = anthropic\_messages` - the native Anthropic Messages API - `agent/anthropic\_adapter.py` for translation Creden... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/provider-runtime.md | main | hermes-agent | [
-0.04010986164212227,
0.010467316024005413,
-0.06217300146818161,
-0.03563088923692703,
0.015590389259159565,
-0.10187669843435287,
-0.04062909632921219,
0.007667084690183401,
0.05181135982275009,
0.023934220895171165,
-0.0043778615072369576,
-0.002104709856212139,
0.019898362457752228,
0.... | 0.016959 |
between primary and fallback - `tests/hermes\_cli/test\_fallback\_cmd.py` β the `/fallback` CLI command - `tests/gateway/test\_fallback\_eviction.py` β gateway eviction of failed providers ## Related docs - [Agent Loop Internals](./agent-loop.md) - [ACP Internals](./acp-internals.md) - [Context Compression & Prompt Cac... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/provider-runtime.md | main | hermes-agent | [
-0.0644427090883255,
-0.0005868318839929998,
-0.06457086652517319,
0.0048872921615839005,
0.031630970537662506,
-0.09747663140296936,
-0.03873232752084732,
0.043052442371845245,
0.004753104876726866,
-0.03564031794667244,
0.0781044214963913,
0.05598976090550423,
0.02592482417821884,
-0.014... | 0.067898 |
# Cron Internals The cron subsystem provides scheduled task execution β from simple one-shot delays to recurring cron-expression jobs with skill injection and cross-platform delivery. ## Key Files | File | Purpose | |------|---------| | `cron/jobs.py` | Job model, storage, atomic read/write to `jobs.json` | | `cron/sch... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/cron-internals.md | main | hermes-agent | [
-0.13683997094631195,
-0.00473473547026515,
-0.056118886917829514,
0.002478109672665596,
-0.02277999557554722,
-0.04975453391671181,
-0.06231793388724327,
0.00361408619210124,
-0.03668775036931038,
-0.027348428964614868,
-0.014737761579453945,
0.006557686720043421,
0.021961873397231102,
0.... | 0.115456 |
must be self-contained β cron jobs cannot ask clarifying questions - The `cronjob` toolset is disabled (recursion guard) ## Skill-Backed Jobs A cron job can attach one or more skills via the `skills` field. At execution time: 1. Skills are loaded in the specified order 2. Each skill's SKILL.md content is injected as co... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/cron-internals.md | main | hermes-agent | [
-0.05205704644322395,
0.016065992414951324,
-0.10265954583883286,
0.0352480486035347,
0.01250566728413105,
-0.02141443081200123,
0.03865284472703934,
-0.0162928719073534,
-0.07644762843847275,
-0.01437426172196865,
0.02630738355219364,
-0.01949313096702099,
0.0577903613448143,
0.0333303995... | 0.112618 |
footer noting the agent cannot see the delivered message in conversation The `[SILENT]` prefix in a cron response suppresses delivery entirely β useful for jobs that only need to write to files or perform side effects. ### Session Isolation Cron deliveries are NOT mirrored into gateway session conversation history. The... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/cron-internals.md | main | hermes-agent | [
-0.11208884418010712,
-0.003136475570499897,
-0.01820613443851471,
-0.0006400244310498238,
0.02255878783762455,
-0.060111381113529205,
0.043901339173316956,
-0.05113286152482033,
0.06583940237760544,
-0.0026801936328411102,
0.007880893535912037,
-0.02114957757294178,
-0.014423869550228119,
... | 0.115496 |
# Tools Runtime Hermes tools are self-registering functions grouped into toolsets and executed through a central registry/dispatch system. Primary files: - `tools/registry.py` - `model\_tools.py` - `toolsets.py` - `tools/terminal\_tool.py` - `tools/environments/\*` ## Tool registration model Each tool module calls `reg... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/tools-runtime.md | main | hermes-agent | [
-0.048693541437387466,
-0.08208998292684555,
-0.11147984117269516,
0.035291917622089386,
-0.028773954138159752,
-0.09081725031137466,
-0.02902291528880596,
0.048990797251462936,
0.018281828612089157,
-0.03128857910633087,
0.03779129311442375,
-0.03383534401655197,
0.03064698912203312,
0.01... | 0.098486 |
entry point is `model\_tools.get\_tool\_definitions(enabled\_toolsets, disabled\_toolsets, quiet\_mode)`: 1. \*\*If `enabled\_toolsets` is provided\*\* β only tools from those toolsets are included. Each toolset name is resolved via `resolve\_toolset()` which expands composite toolsets into individual tool names. 2. \*... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/tools-runtime.md | main | hermes-agent | [
-0.0034903932828456163,
-0.04531625658273697,
-0.06761395186185837,
0.06819532811641693,
0.028109153732657433,
-0.047205474227666855,
-0.0027166870422661304,
-0.0240875706076622,
-0.02698550932109356,
-0.04393536224961281,
0.0259273461997509,
-0.0749305933713913,
0.013715395703911781,
-0.0... | 0.084721 |
callback sends the request to the messaging platform - \*\*Smart approval\*\* β optionally, an auxiliary LLM can auto-approve low-risk commands that match patterns (e.g., `rm -rf node\_modules/` is safe but matches "recursive delete") 4. \*\*Session state\*\* β approvals are tracked per-session. Once you approve "recur... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/tools-runtime.md | main | hermes-agent | [
-0.03398403525352478,
-0.011300379410386086,
-0.01709945686161518,
-0.014688149094581604,
0.08580087870359421,
-0.05031083896756172,
0.03308722376823425,
-0.06171640381217003,
0.03963511809706688,
0.03175191581249237,
0.03162727877497673,
0.05894728749990463,
0.001412114012055099,
0.018045... | 0.11615 |
# Adding Providers Hermes can already talk to any OpenAI-compatible endpoint through the custom provider path. Do not add a built-in provider unless you want first-class UX for that service: - provider-specific auth or token refresh - a curated model catalog - setup / `hermes model` menu entries - provider aliases for ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/adding-providers.md | main | hermes-agent | [
-0.04271981492638588,
-0.06057954579591751,
-0.04297838360071182,
0.008178814314305782,
-0.020084962248802185,
-0.09828502684831619,
-0.02208404242992401,
0.023554908111691475,
-0.00736057385802269,
-0.024925939738750458,
0.012092015706002712,
-0.04069415479898453,
0.08280061185359955,
0.0... | 0.085645 |
CLI flag accepts the provider id 7. `hermes model` menu includes the provider 8. `hermes setup` wizard delegates to `main.py` automatically 9. `provider:model` alias syntax works 10. Runtime resolver returns the correct `base\_url` and `api\_key` 11. `--provider ` CLI flag accepts the provider id 12. Fallback model act... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/adding-providers.md | main | hermes-agent | [
-0.10681416094303131,
-0.03197476267814636,
0.012961044907569885,
-0.04562518373131752,
-0.030715923756361008,
-0.05590508505702019,
-0.023693272843956947,
0.04234922677278519,
-0.019654659554362297,
-0.02603725902736187,
0.024441728368401527,
0.009865877218544483,
0.06239374727010727,
0.0... | 0.003816 |
"env|portal|auth-store|explicit", "requested\_provider": requested\_provider, } ``` If the provider is OpenAI-compatible, `api\_mode` should usually stay `chat\_completions`. Be careful with API-key precedence. Hermes already contains logic to avoid leaking an OpenRouter key to unrelated endpoints. A new provider shoul... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/adding-providers.md | main | hermes-agent | [
-0.019701704382896423,
0.007459907326847315,
-0.012395177036523819,
0.0030608566012233496,
0.013454310595989227,
-0.0873054787516594,
0.020240141078829765,
-0.043609075248241425,
0.05344691872596741,
-0.01390338409692049,
0.00020582068827934563,
-0.019141221418976784,
0.021038219332695007,
... | 0.031125 |
to cover: - auth resolution - CLI menu / provider selection - runtime provider resolution - agent execution path - provider:model parsing - any adapter-specific message conversion Run tests with xdist disabled: ```bash source venv/bin/activate python -m pytest tests/hermes\_cli/test\_runtime\_provider\_resolution.py te... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/adding-providers.md | main | hermes-agent | [
0.0030696741305291653,
-0.021375998854637146,
-0.03858557343482971,
-0.02887246571481228,
-0.02839725650846958,
-0.11883079260587692,
-0.012296424247324467,
0.0691065639257431,
-0.03670410066843033,
0.006956432480365038,
0.047446586191654205,
-0.03800278156995773,
0.057891663163900375,
0.0... | -0.031381 |
# Browser CDP Supervisor The CDP supervisor closes two long-standing gaps in Hermes' browser tooling: 1. \*\*Native JS dialogs\*\* (`alert`/`confirm`/`prompt`/`beforeunload`) block the page's JS thread. Without supervision, the agent has no way to know a dialog is open β subsequent tool calls hang or throw opaque error... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/browser-supervisor.md | main | hermes-agent | [
-0.023878922685980797,
-0.009071746841073036,
-0.013318617828190327,
0.02539674937725067,
0.12142911553382874,
-0.1143529936671257,
-0.014456038363277912,
-0.022076042369008064,
0.021494276821613312,
-0.04208434000611305,
0.005400722846388817,
-0.006712418980896473,
-0.09096289426088333,
0... | 0.122991 |
workflow wants to navigate away cleanly). Policy is per-task; no per-dialog overrides. ## Agent surface ### `browser\_dialog` tool ``` browser\_dialog(action, prompt\_text=None, dialog\_id=None) ``` - `action="accept"` / `"dismiss"` β responds to the specified or sole pending dialog (required) - `prompt\_text=...` β te... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/browser-supervisor.md | main | hermes-agent | [
-0.02441532537341118,
0.007494963705539703,
0.04400145635008812,
-0.0009447936899960041,
0.02714402601122856,
-0.09298698604106903,
0.03295869007706642,
-0.05807526037096977,
0.06166229769587517,
-0.03533937782049179,
-0.025417611002922058,
-0.051739536225795746,
-0.020670104771852493,
0.0... | 0.031604 |
dismiss, frame attach/detach, child target attach, session teardown. Real-backend E2E (Browserbase + local Chromium-family browser) is manual β exercise via `/browser connect` to a live Chromium-family browser and run the dialog/frame test cases described above. | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/browser-supervisor.md | main | hermes-agent | [
-0.017048437148332596,
-0.0008764959056861699,
0.04279857873916626,
-0.0034931711852550507,
0.07575840502977371,
-0.05747869610786438,
-0.027833817526698112,
0.07800248265266418,
-0.04345466196537018,
-0.06915710866451263,
0.01981821097433567,
-0.013821065425872803,
-0.08043400943279266,
0... | 0.074482 |
# Building a Model Provider Plugin Model provider plugins declare an inference backend β an OpenAI-compatible endpoint, an Anthropic Messages server, a Codex-style Responses API, or a Bedrock-native surface β that Hermes can route `AIAgent` calls through. Every built-in provider (OpenRouter, Anthropic, GMI, DeepSeek, N... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/model-provider-plugin.md | main | hermes-agent | [
-0.10324396193027496,
-0.06992314010858536,
-0.05403219908475876,
0.03993219509720802,
0.04622407630085945,
-0.04572885110974312,
0.017122726887464523,
0.04539019986987114,
0.044083960354328156,
0.026261266320943832,
0.0809408500790596,
-0.019135139882564545,
-0.002095258329063654,
0.02827... | 0.198997 |
str | Picker subtitle | | `signup\_url` | str | Shown during first-run setup ("get an API key here") | | `env\_vars` | `tuple[str, ...]` | API-key env vars in priority order; a final `\*\_BASE\_URL` entry is used as the user base-URL override | | `base\_url` | str | Default inference endpoint | | `models\_url` | str | ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/model-provider-plugin.md | main | hermes-agent | [
-0.07366479933261871,
-0.0402611643075943,
-0.04703251272439957,
0.013703737407922745,
0.042707327753305435,
-0.04618150368332863,
-0.03432583063840866,
0.045733630657196045,
0.01497732289135456,
-0.027035444974899292,
0.05013909563422203,
-0.064698226749897,
0.04076925665140152,
-0.031201... | 0.03768 |
default your provider ships β it acts as a hint. User URL overrides still win. ## Auth types | `auth\_type` | Meaning | Who uses it | |---|---|---| | `api\_key` | Single env var carries a static API key | Most providers | | `oauth\_device\_code` | Device-code OAuth flow | β | | `oauth\_external` | User signs in elsewhe... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/model-provider-plugin.md | main | hermes-agent | [
-0.07104272395372391,
-0.021182319149374962,
-0.048864398151636124,
-0.01611238531768322,
0.005057287402451038,
-0.0556810200214386,
0.051271554082632065,
0.0427229180932045,
0.01039536576718092,
0.01720014028251171,
0.012728231959044933,
0.006053371354937553,
0.010642223991453648,
-0.0253... | 0.058951 |
# Programmatic Integration Hermes ships three protocols for driving the agent from external programs β IDE plugins, custom UIs, CI pipelines, embedded sub-agents. Pick the one that matches your transport and consumer. | Protocol | Transport | Best for | Defined by | |----------|-----------|----------|------------| | \*... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/programmatic-integration.md | main | hermes-agent | [
-0.07160266488790512,
0.02792241796851158,
-0.10848403722047806,
-0.03782081604003906,
-0.06573314219713211,
-0.0692732110619545,
0.03214298561215401,
0.08793099224567413,
-0.018066637217998505,
0.027449175715446472,
-0.016747569665312767,
-0.03785352036356926,
0.02662227861583233,
0.02729... | 0.215813 |
GET /v1/capabilities Machine-readable feature flags GET /v1/models Lists hermes-agent GET /health, /health/detailed ``` Setup, headers (`X-Hermes-Session-Id`, `X-Hermes-Session-Key`), and frontend wiring: [API Server](../user-guide/features/api-server). --- ## Which one should I use? - \*\*You're writing an IDE plugin ... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/programmatic-integration.md | main | hermes-agent | [
-0.07027625292539597,
0.05238122120499611,
-0.08106201887130737,
0.0016336556291207671,
0.0015755401691421866,
-0.09968635439872742,
-0.003150562522932887,
0.07212148606777191,
-0.05011261999607086,
-0.01656307838857174,
-0.012964108027517796,
-0.06451117992401123,
0.039692532271146774,
-0... | 0.167425 |
# Building a Video Generation Provider Plugin Video-gen provider plugins register a backend that services every `video\_generate` tool call. Built-in providers (xAI, FAL) ship as plugins. Add a new one, or override a bundled one, by dropping a directory into `plugins/video\_gen//`. :::tip Video-gen mirrors [Image Gener... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/video-gen-provider-plugin.md | main | hermes-agent | [
-0.09328877180814743,
-0.09978780150413513,
-0.03718032315373421,
-0.01983465626835823,
0.054048314690589905,
-0.03558984026312828,
-0.048475220799446106,
0.06810303777456284,
0.02461610920727253,
-0.07873282581567764,
0.06595083326101303,
-0.043863508850336075,
-0.006491143722087145,
0.02... | 0.089639 |
"My video generation backend" author: Your Name kind: backend requires\_env: - MY\_API\_KEY ``` ## The `video\_generate` schema The tool exposes one schema across every backend. Providers ignore parameters they don't support. | Parameter | What it does | |---|---| | `prompt` | Text instruction (required) | | `image\_ur... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/video-gen-provider-plugin.md | main | hermes-agent | [
0.025199633091688156,
-0.08594486117362976,
-0.04132766276597977,
-0.03659268468618393,
0.014865774661302567,
-0.003090397920459509,
-0.03729797527194023,
0.02756018377840519,
0.006409629248082638,
-0.0076998015865683556,
0.015226767398416996,
-0.12171485275030136,
0.07567581534385681,
-0.... | -0.019628 |
# Session Storage Hermes Agent uses a SQLite database (`~/.hermes/state.db`) to persist session metadata, full message history, and model configuration across CLI and gateway sessions. This replaces the earlier per-session JSONL file approach. Source file: `hermes\_state.py` ## Architecture Overview ``` ~/.hermes/state... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/session-storage.md | main | hermes-agent | [
-0.052203767001628876,
0.03779873251914978,
-0.08512026816606522,
-0.02021382376551628,
-0.036670949310064316,
-0.06770766526460648,
0.017507916316390038,
0.022578824311494827,
0.041654374450445175,
0.04714169353246689,
0.0024242117069661617,
0.00840840581804514,
0.021932246163487434,
-0.0... | 0.144431 |
index/FTS changes that can't be expressed declaratively: | Version | Change | |---------|--------| | 1 | Initial schema (sessions, messages, FTS5) | | 2 | Add `finish\_reason` column to messages | | 3 | Add `title` column to sessions | | 4 | Add unique index on `title` (NULLs allowed, non-NULL must be unique) | | 5 | A... | https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/session-storage.md | main | hermes-agent | [
0.023988818749785423,
-0.0034485303331166506,
-0.07176169008016586,
0.08607029169797897,
0.015005432069301605,
-0.038083866238594055,
0.025258535519242287,
0.07442343235015869,
0.013434479013085365,
0.1063084676861763,
-0.015120268799364567,
-0.06508219242095947,
0.009653388522565365,
-0.0... | 0.131272 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.