Graph-RAG Memory

产品介绍

Graph-RAG memory system using Graphiti temporal knowledge graph + FalkorDB + local Ollama embeddings. Provides persistent, queryable long-term memory for OpenClaw agents via a MoE-style (Mixture-of-Experts) multi-embedding router. Use when: setting up persistent agent memory, querying past conversations or facts, ingesting documents into the memory graph, checking memory system status, or integrating graph-rag memory into an OpenClaw agent. Triggers on: "memory system", "graph rag", "graphiti", "persistent memory", "ingest memory", "query memory", "what do you remember", "memory upgrade".

资源信息

许可证信息摘自官方源，可能过时或缺失。商用前请以原仓库的 LICENSE 文件为准。

安装方式

请选择你的平台

依赖说明

See `references/setup.md` for full installation and environment details.
**Quick check:**
```python
# Verify services (write to a temp script, don't use python3 -c inline)
import falkordb, httpx
r = falkordb.FalkorDB(host='172.18.0.1', port=6379)
print("FalkorDB OK:", r.list_graphs())
# nomic-embed-text must be loaded on NVIDIA Ollama
```
**Python packages** (reinstall after container restart — ephemeral layer):
```bash
export PATH=$PATH:/home/node/.local/bin
curl -sS https://bootstrap.pypa.io/g

适用平台