Tree of Thoughts Inference Server — no weights, no GPU, no network required.
Response will appear here...
| Endpoint | Method | Description |
|---|---|---|
/api/generate | POST | Ollama-compatible text generation |
/api/chat | POST | Ollama chat + history + tool support |
/api/tags | GET | List available models |
/api/show | POST | Model details |
/api/pull | POST | No-op (compatibility) |
/api/summarize | POST | Extractive document summarization |
/api/agent | POST | Plan-execute-synthesise agent loop |
/api/agent/tools | GET | List registered tools |
/api/agent/tool | POST | Run a single tool by name |
/api/agent/learn | POST | Write to Hermes Learning Journal |
/api/quit | POST/GET | Graceful shutdown |
/v1/chat/completions | POST | OpenAI-compatible (Hermes drop-in) |
/v1/models | GET | OpenAI model list |
pip install tinytot
tinytot
# → server running on http://localhost:11434
curl http://localhost:11434/api/generate \
-d '{"model":"tinytot","prompt":"What is the square root of 144?","stream":false}'