mem0
Search, write, and inspect the shared Hermes mem0 qdrant memory store.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 6
- Forks
- 0
01 前言 Front Matter
- name
- mem0
- description
- Search, write, and inspect the shared Hermes mem0 qdrant memory store.
03 SKILL.md 正文
mem0 — Hermes Shared Memory
Query and write to the shared mem0 qdrant store (hermes_mem0, 127.0.0.1:6333).
All agents (Claude, Codex, Hermes) share this store under user_id=$USER.
Quick reference
# Search
python3 ~/.hermes/scripts/mem0_shared_client.py search "<query>"
# Add a fact (with LLM extraction)
python3 ~/.hermes/scripts/mem0_shared_client.py add "<text>"
# Add verbatim (no LLM, guaranteed write)
python3 ~/.hermes/scripts/mem0_shared_client.py add "<text>" --no-infer
# Stats
python3 ~/.hermes/scripts/mem0_shared_client.py stats
Script path:
~/.hermes/scripts/mem0_shared_client.pyConfig: reads~/.hermes/config.yaml(override withHERMES_CONFIG_PATH), looking forplugins.entries.hermes-mem0.config.oss. That block is OPTIONAL — if absent, the script falls back to working defaults (ollamanomic-embed-textembedder +gemma2:2bLLM, qdrant127.0.0.1:6333, collectionhermes_mem0). There is NO~/.hermes/hermes.json; do not chase it as a missing file. Also callable from any repo worktree:python3 scripts/mem0_shared_client.py <cmd>
Store status
- Collection:
hermes_mem0 - Host:
127.0.0.1:6333(qdrant docker, Hermes-managed storage) - Embedder:
~/.hermes/config.yaml(hermes-mem0pluginossblock) or fallback defaultnomic-embed-text - LLM for extraction:
~/.hermes/config.yaml(hermes-mem0pluginossblock) or fallback defaultgemma2:2b
Ingestion (backfill)
The extractor at scripts/mem0_extract_facts.py scans three sources:
| Source | Path | Agent ID |
|---|---|---|
| Hermes | ~/.hermes/ |
hermes |
| Claude Code | ~/.claude/projects/ |
claude |
| Codex | ~/.codex/sessions/ |
codex |
Run a backfill (last 1 year = 525960 minutes):
cd ~/.hermes
python3 scripts/mem0_extract_facts.py --since 525960
Run incremental (last 65 min, for cron):
cd ~/.hermes
python3 scripts/mem0_extract_facts.py --since 65
Check state:
cat ~/.hermes/memory/extraction-state.json | python3 -m json.tool | head -20
Current ingestion status
Use python3 ~/.hermes/scripts/mem0_shared_client.py stats for live status.
When to use this skill
Use /mem0 when the user asks to:
- Search memory for past decisions, branch names, bead IDs, preferences
- Add a new fact that should persist across agent sessions
- Check ingestion status or trigger a backfill
- Debug why an agent doesn't remember something
04 同仓库更多 Skills
disk-reclaim-playbook
Use Disk Magician to diagnose disk growth or qualify cleanup on macOS or Linux.
claudea-bench
Compare `claudea` and normal `claude` on a fair split of comparable work by default; use `--strict` for duplicate runs of the exact same task.
pr
Alias for the canonical pr-lifecycle PR workflow skill (/pr-workflow, /prw).
whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
pr-report
This skill should be used when the user asks for a PR report, PR audit, PR delta analysis, /pr-report, or wants per-PR summary with delta files/lines. Generates a structured report for one or more open PRs covering purpose, files changed, +/− line counts, /code-standards + /thermo review findings, /ponytail simplification opportunities, file-overlap combination candidates, and /green status per pr-green-definition. Output: machine-readable JSONL + human-readable markdown. Read-only by default; can apply simplifications if user opts in.