README.md

---
title: Thought Anchors
emoji: 🧠
colorFrom: blue
colorTo: red
sdk: docker
app_port: 7860
hf_oauth: true
pinned: false
models:
  - sapientinc/HRM-Text-1B
---

# Thought Anchors

Thought Anchors generates visible reasoning traces from open-weight models and
computes sentence-to-sentence influence with gradient x attention attribution.

Current product shape:

- Hugging Face `Docker Space` first
- Hugging Face OAuth sign-in
- web UI + API
- per-user ephemeral sessions
- JSON / CSV export
- adaptive CPU / MPS / CUDA loading

## Quick Start

Install deps:

```bash
uv sync --extra dev
```

Run API:

```bash
uv run python -m app.cli.run_api
```

Run CLI:

```bash
uv run python -m app.cli.run_prototype "Explain why the derivative of x^2 is 2x"
```

Run tests:

```bash
uv run python -m pytest -q
```

## Main Endpoints

- `GET /healthz`
- `GET /api/me`
- `POST /api/warmup`
- `POST /api/analyze`
- `GET /api/sessions`
- `POST /api/sessions`
- `GET /api/sessions/{id}`
- `GET /api/sessions/{id}/result`
- `GET /api/sessions/{id}/export.json`
- `GET /api/sessions/{id}/export.csv`

## Docs

- [Hugging Face deployment](./docs/deploy-huggingface.md)
- [Runtime and model support](./docs/runtime.md)
- [API and product behavior](./docs/api.md)
- [Notebook usage](./docs/notebook.md)

## Notebook

Colab / Kaggle smoke-test notebook:

- [notebooks/hf_space_demo.ipynb](/Users/vibhorkumar/Desktop/codes/cot-anc/notebooks/hf_space_demo.ipynb)

## Key Constraints

- Attribution needs `attn_implementation="eager"`.
- Model must expose supported decoder layers and attention modules.
- Long traces stay capped because analysis uses full backward pass.
- Space disk is ephemeral; export results you want to keep.