Commit History

fix(chat/demo): remove memory search β€” bubble chat is a public guide bot only, no db access
e356363
Running

RemanenetSpy commited on

fix(agent): loosen memory retrieval threshold to 0.70 and show raw_text for CSV data
1dce94f

RemanenetSpy commited on

fix(chat): lower similarity threshold to 0.70 and use raw_text for CSV-ingested data
75ebf8d

RemanenetSpy commited on

feat: add /chat/demo endpoint to power KaalChat widget with memory
02937b7

RemanenetSpy commited on

feat(ui): populate API key input with saved key from localStorage to reduce user confusion
76fba02

RemanenetSpy commited on

fix: move CREATE INDEX in vector_store after ALTER TABLE migration
781a9f1

RemanenetSpy commited on

fix: move CREATE INDEX statements after ALTER TABLE migration in memory_store schema to prevent UndefinedColumnError on startup
3484a98

RemanenetSpy commited on

chore: add smriti benchmark runner and eval service
64f8bdd

RemanenetSpy commited on

refactor: centralise all magic numbers into config.py driven by env vars
d62efa7

RemanenetSpy commited on

feat: bi-temporal supersession, scope isolation, configurable threshold, benchmark adapter
f03315c

RemanenetSpy commited on

feat: add article 'How to Give Any AI Agent Long-Term Memory in 3 API Calls'
cfe1ad3

RemanenetSpy commited on

docs: clarify dual-deployment architecture (Vercel UI + Hugging Face API)
eabd9fd

RemanenetSpy commited on

feat: add SEO-optimized article 'The End of AI Amnesia'
9742961

RemanenetSpy commited on

chore: update og:url to vercel domain to prevent SEO backlink fragmentation
45511e2

RemanenetSpy commited on

fix: update Keys.tsx apiCall to use JSON body and Turnstile token for key generation
b1c82da

RemanenetSpy commited on

fix: billing body binding (Pydantic model), surface real error in WelcomeScreen
61d7f2a

RemanenetSpy commited on

security: add Turnstile captcha + IP rate limiting + email dedup to key generation
f71cfd2

RemanenetSpy commited on

fix: add security headers to next.config (X-Frame-Options, CSP, CORS)
63fccd0

RemanenetSpy commited on

UX: Collapse onboarding from 5 screens to 3, remove forced chat popup, fix all Kaal copy to Smriti
6745dda

RemanenetSpy commited on

UI: Complete rebrand to Smriti by Kaal the Absolute
b49293b

RemanenetSpy commited on

fix: add missing KaalChat.tsx to git and fix corrupted .gitignore null-byte wav entry
83f66cb

RemanenetSpy commited on

feat: add KaalChat floating AI widget β€” consent gate, TTS toggle, template feature cards, typing indicator, 5-msg rate limit display
a4022a1

RemanenetSpy commited on

feat: store Amber voice as base64 py constant to avoid binary in git, fix speaker_wav references in TTS route
66c50f8

RemanenetSpy commited on

feat: add XTTSv2 TTS endpoint + public demo chat with Amber voice, template-first responses, and Chronos memory consent storage
22aa01d

RemanenetSpy commited on

UI: remove Builder and Scale tiers from dashboard Keys page
47e576a

RemanenetSpy commited on

UI: remove Builder and Scale tiers from dashboard Billing page
4ba8f50

RemanenetSpy commited on

fix: restore missing Hexagon import in Sidebar to fix Vercel build after reset
0b1d9d2

RemanenetSpy commited on

Logo: remove tagline and HourglassIcon import, clean seal + Kaal wordmark only
dfa2afe

RemanenetSpy commited on

Rebrand to Kaal β€” rename from Chronos OS, add Logo component with serif seal design, swap all Hexagon icons for Logo
4303a4c

RemanenetSpy commited on

Update UI and README to reflect new GPT OSS 120B and Llama 3.1 architecture (removed GLM 4.7 references)
3628226

RemanenetSpy commited on

Add connected tools list to the Connect UI so users can see their registered tools
4e033ec

RemanenetSpy commited on

Switch agent to GPT OSS 120B β€” officially recommended Cerebras model for tool-calling agents
e4339d8

RemanenetSpy commited on

Fix Cerebras model ID to llama3.1-70b as 3.3 was deprecated
b8ef250

RemanenetSpy commited on

Switch primary heavy agent model from GLM 4.7 to blazing fast Llama 3.3 70B on Cerebras
3f14fab

RemanenetSpy commited on

Fix router hanging on rate limits by setting max_retries=0 to force instant fallback
67c1839

RemanenetSpy commited on

Fix pre-launch blocking issues and agent multi-turn reasoning_content error
f753516

RemanenetSpy commited on

Replace emoji with Lucide icons in guide; add info tooltips to sidebar nav
74fd69f

RemanenetSpy commited on

Add interactive Getting Started guide to Overview dashboard
fb15192

RemanenetSpy commited on

Hide paid tiers β€” show only free Explorer plan until payment is integrated
b594b92

RemanenetSpy commited on

Update pricing to premium B2B SaaS tiers: /mo Builder and /mo Scale
8facfc7

RemanenetSpy commited on

Fix AgentRunResponse validation error by parsing GLM/DeepSeek reasoning block lists into strings
29be92c

RemanenetSpy commited on

Update heavy pipeline to use zai-glm-4.7 and update dashboard display
8c99f77

RemanenetSpy commited on

Revert to Llama 3.3 70B to fix API crash with DeepSeek V3.2
c05e370

RemanenetSpy commited on

Update AI Engine display on dashboard to DeepSeek V3.2
56e4c60

RemanenetSpy commited on

Update DeepSeek model to use explicit cerebras endpoint string
cbfc42a

RemanenetSpy commited on

Update heavy pipeline to use DeepSeek V3.2 for optimal reasoning and MoE efficiency
32f9d01

RemanenetSpy commited on

Update heavy pipeline to use GPT-OSS 20B for high efficiency and low token burn
df1f400

RemanenetSpy commited on

Revert heavy pipeline to Qwen 3 235B on Cerebras
b0731a6

RemanenetSpy commited on

Prioritize Cerebras API over Groq in LLM router for higher limits and speed
50a673f

RemanenetSpy commited on

Update demo box in Hero section to include 'WHAT'
fd072c6

RemanenetSpy commited on