AGENT SKILL

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.py Config: reads ~/.hermes/config.yaml (override with HERMES_CONFIG_PATH), looking for plugins.entries.hermes-mem0.config.oss. That block is OPTIONAL — if absent, the script falls back to working defaults (ollama nomic-embed-text embedder + gemma2:2b LLM, qdrant 127.0.0.1:6333, collection hermes_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-mem0 plugin oss block) or fallback default nomic-embed-text
  • LLM for extraction: ~/.hermes/config.yaml (hermes-mem0 plugin oss block) or fallback default gemma2:2b

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

jleechanorg
jleechanorg/jleechan-skills

disk-reclaim-playbook

Use Disk Magician to diagnose disk growth or qualify cleanup on macOS or Linux.

★ 6
jleechanorg
jleechanorg/jleechan-skills

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.

★ 6
jleechanorg
jleechanorg/jleechan-skills

pr

Alias for the canonical pr-lifecycle PR workflow skill (/pr-workflow, /prw).

★ 6
jleechanorg
jleechanorg/jleechan-skills

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.

★ 6
jleechanorg
jleechanorg/jleechan-skills

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.

★ 6
jleechanorg
jleechanorg/jleechan-skills

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.

★ 6