mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-24 10:52:21 +00:00
Addresses reviewer feedback on #13377: 1. Restore all stripped docstrings (_load_config, _is_breaker_open, sync_turn, register, _get_client, _read_filters, _write_filters, _unwrap_results, save_config) and section dividers 2. Revert api_key to required:true in schema — self-hosted Mem0 also requires auth by default; validation in _get_client() handles the either/or logic separately from the schema 3. Confirm secret:true remains on api_key (already correct) |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| plugin.yaml | ||
| README.md | ||
Mem0 Memory Provider
Server-side LLM fact extraction with semantic search, reranking, and automatic deduplication.
Supports both Mem0 Cloud and self-hosted instances.
Requirements
pip install mem0ai- Mem0 Cloud API key or a self-hosted Mem0 server
Setup
Cloud
hermes memory setup # select "mem0"
Or manually:
hermes config set memory.provider mem0
echo "MEM0_API_KEY=your-key" >> ~/.hermes/.env
Self-Hosted
hermes config set memory.provider mem0
echo "MEM0_HOST=http://your-mem0-server:24220" >> ~/.hermes/.env
echo "MEM0_API_KEY=your-api-key" >> ~/.hermes/.env # if auth is enabled
Config
Config file: $HERMES_HOME/mem0.json
| Key | Default | Description |
|---|---|---|
api_key |
— | API key (required for cloud; optional for self-hosted without auth) |
host |
https://api.mem0.ai |
Self-hosted Mem0 URL. When set, overrides the cloud endpoint. |
user_id |
hermes-user |
User identifier |
agent_id |
hermes |
Agent identifier |
rerank |
true |
Enable reranking for recall |
Tools
| Tool | Description |
|---|---|
mem0_profile |
All stored memories about the user |
mem0_search |
Semantic search with optional reranking |
mem0_conclude |
Store a fact verbatim (no LLM extraction) |