| --- |
| title: loosecanvas |
| emoji: 🕸️ |
| colorFrom: indigo |
| colorTo: purple |
| sdk: docker |
| app_port: 7860 |
| pinned: false |
| license: mit |
| short_description: Local AI that turns talk into a trust-tagged map |
| models: |
| - unsloth/gemma-4-26B-A4B-it-qat-GGUF |
| suggested_hardware: l4x1 |
| startup_duration_timeout: 2h |
| tags: |
| - build-small-hackathon |
| - track:wood |
| - achievement:offgrid |
| - achievement:llama |
| - achievement:offbrand |
| - achievement:fieldnotes |
| - gradio |
| - knowledge-graph |
| - local-llm |
| - llama.cpp |
| - gemma |
| - cytoscape |
| - off-the-grid |
| --- |
| |
| <!-- |
| THIS IS THE HF SPACE README — its YAML frontmatter is the Space config. |
| To deploy, this content must live in the README.md at the ROOT of the Space |
| repo (alongside the Dockerfile). It is kept here so it does not overwrite the |
| project's own README.md. |
|
|
| Grounded against HF docs (2026-06-14): |
| - sdk: docker + app_port are required; HF proxies HTTPS to the one public port. |
| - suggested_hardware is ADVISORY only (hints duplicators) — you must still |
| pick "Nvidia L4" in Space Settings; that is when GPU billing starts. |
| - startup_duration_timeout default is 30m; "2h" covers the runtime download |
| (~13.6 GB) + cold-GPU load of the default (BAKE_MODEL=0) build. If you bake |
| the model (BAKE_MODEL=1), "1h" is sufficient. |
| - models: is discovery metadata; confirm the exact Unsloth repo id/filename. |
| --> |
| |
| # loosecanvas 🕸️ |
|
|
| **Talk through an idea. Watch it become a map — and decide which connections are real.** |
|
|
| ## The problem |
|
|
| LLMs assert. They hand you fluent text where a hard fact, a hedge, and a |
| confident hallucination all look identical — so you can't tell what to trust, and |
| the "knowledge" you build with them quietly rots. A knowledge graph an AI fills in |
| on its own is just a prettier version of the same problem. |
|
|
| ## The value prop: an AI that proposes, but never decides |
|
|
| loosecanvas is a local, co-created understanding map. You chat; a small local |
| model proposes concepts and connections; **you accept, reject, or edit every |
| single proposal.** Each claim carries four independent trust fields that never |
| collapse into one — `origin` (frozen at birth), `claim_type`, `support_state`, |
| `review_state` — so a model's guess is permanently marked a guess until you say |
| otherwise. Export drops unreviewed model-inferred claims, so the map you take with |
| you is one you actually vouched for. Messy thinking in; a trustworthy, co-owned |
| map out. |
|
|
| ## TL;DR for judges |
|
|
| - **Track:** 🌲 Thousand Token Wood — a small local model is the whole point. |
| - **Off the grid:** zero cloud API calls. 100% local inference via **llama.cpp**. |
| `base_url` is hardcoded to localhost; the API key is a dummy `not-needed`. |
| - **Small model, load-bearing:** Gemma 4 26B-A4B (~25B active params, GGUF, QAT) — |
| no fine-tune, stock Unsloth weights. The small-model constraint _forces_ the |
| good UX: the human is in the loop because the model shouldn't be trusted blind. |
| - **Off-brand UI:** a real custom **Svelte 5 + TypeScript Cytoscape.js** Gradio |
| component, not a chatbot with a decorative graph beside it. |
| - **Field notes:** a genuine build write-up ships with the submission (see links). |
|
|
| ## Features |
|
|
| - **Magic build from a paragraph.** Paste or write messy thoughts, press Send, and |
| watch the graph assemble live as the model streams concepts and edges. |
| - **Trust-tagged everything.** Model proposals land with an amber "awaiting review" |
| badge. Accept, reject, or edit — origin is never silently upgraded. |
| - **Color the clusters.** Community detection groups related ideas at a glance. |
| - **Find a hidden connection.** Ask the model to surface a surprising cross-domain |
| link, articulated in plain language — then judge it. |
| - **Trust-gated export.** Unreviewed guesses are dropped on the way out. |
|
|
| ## Demo |
|
|
| - **Live Space:** https://huggingface.co/spaces/build-small-hackathon/loosecanvas |
| (goes live when transferred to the org and made public) |
| - **Demo video:** _TODO_ |
|
|
| ## Architecture / system flow |
|
|
| A turn is a negotiation, not autocomplete: |
|
|
| ``` |
| You chat ─▶ LangChain create_agent (local llama.cpp endpoint, streams tokens + tool calls) |
| ─▶ agent tools accumulate proposed actions |
| ─▶ validator + reducer DECIDE (pure: actions → GraphPatch + ScenePatch) |
| ─▶ graph repository + renderer adapter ─▶ RendererPatch ─▶ Cytoscape.js canvas |
| ``` |
|
|
| The LLM **proposes**; the validator and reducer **decide**. Rejected actions return |
| a reason string the model can self-correct from. Three layers stay separate: the |
| portable product artifact (graph + claims), the runtime/control plane, and the |
| frontend (which owns positions and pan/zoom). The trust model is enforced in code, |
| not by prompting. |
|
|
| ## Tech stack |
|
|
| | Layer | Choice | |
| | ---------- | ------------------------------------------------------------------ | |
| | Model | Gemma 4 26B-A4B-it-qat (GGUF, ~25B active params) — stock Unsloth | |
| | Inference | llama.cpp OpenAI-compatible server, 100% local (127.0.0.1:8080) | |
| | Agent loop | LangChain `create_agent`, streaming tools | |
| | Backend | Python 3.13, FastAPI + Gradio, uvicorn (0.0.0.0:7860) | |
| | Frontend | Svelte 5 + TypeScript, Cytoscape.js — custom Gradio component | |
| | Deploy | Single self-contained Docker Space (llama-server + app, one image) | |
|
|
| ## Hackathon badges |
|
|
| | Tag | Why it's earned | |
| | ------------------------ | --------------------------------------------------------------------- | |
| | `track:wood` | A small local model (Gemma 4 26B-A4B) is the core of the product. | |
| | `achievement:offgrid` | Zero cloud API calls; all inference is local llama.cpp. | |
| | `achievement:llama` | llama.cpp is the inference runtime. | |
| | `achievement:offbrand` | Real custom Svelte 5 + Cytoscape.js component, not default Gradio UI. | |
| | `achievement:fieldnotes` | A genuine published build write-up ships with the submission. | |
|
|
| ## Submission links |
|
|
| | Item | Link | |
| | ----------- | ----------------------------------------------------------------------------- | |
| | Live Space | https://huggingface.co/spaces/build-small-hackathon/loosecanvas (on transfer) | |
| | Demo video | _TODO_ | |
| | Social post | _TODO_ | |
| | Field notes | `submission/FIELD_NOTES.md` (in source repo) | |
| | Source | GitHub — Joshua Sundance Bailey | |
| | Team | @joshuasundance | |
|
|
| ## Run it / deploy |
|
|
| This Space runs a single self-contained Docker image: llama-server loads the GGUF |
| in-container on `127.0.0.1:8080`, and uvicorn serves the app on `0.0.0.0:7860`. The |
| model repo (`unsloth/gemma-4-26B-A4B-it-qat-GGUF`) is public — no token needed. |
|
|
| `suggested_hardware: l4x1` is advisory; pick **Nvidia L4** in Space Settings to run |
| on GPU. `startup_duration_timeout: 2h` covers the runtime model download (~13.6 GB) |
| plus cold-GPU load. To run locally instead, see the source repo's `README.md`. |
|
|
| Built for the **Build Small Hackathon** — Thousand Token Wood track. |
|
|
