# mem0-python-server 🧠

**Version:** v1.0.0

A focused FastAPI wrapper around [mem0](https://github.com/mem0ai/mem0) that provides persistent memory over a REST API for OpenClaw and related pipelines.

## Highlights ✨
- Two dedicated collections: **conversational** and **knowledge**
- Local reranking with graceful fallback when reranker is down
- Clear REST contract for storage, search, and recall
- Docker-first workflow with hot reload

## Quick links 🔗
- **PROJECT.md** — purpose, scope, and operating assumptions
- **API.md** — full endpoint reference (requests + responses)

## Architecture (at a glance) 🧩
- **LLM:** Groq (default: `meta-llama/llama-4-scout-17b-16e-instruct`)
- **Vector store:** Chroma (`192.168.0.200:8001`)
- **Embedder:** Ollama (`nomic-embed-text`)
- **Reranker:** local REST server (`192.168.0.200:5200`)

## Collections 📚
- **Conversational** → Chroma collection: `openclaw_mem` → `/memories`
- **Knowledge** → Chroma collection: `knowledge_mem` → `/knowledge`

## Run it (Docker) 🐳
```bash
docker compose up --build
```

## Config 🔐
Create a `.env` file (never commit it):
```env
GROQ_API_KEY=your_key_here
RERANKER_URL=http://192.168.0.200:5200/rerank
```

## Raw conversational writes 🧪
`POST /memories/raw` lets another project inject already-processed memories straight into the conversational collection (`openclaw_mem`) while preserving any supplied metadata (including `created_at`) without hitting the mem0 extraction LLM.

## Docs
- API reference: **API.md**
- Project overview: **PROJECT.md**

If you want the README expanded again or a different doc split, say the word.