Skill391 repo starsupdated yesterday

mnemon

Mnemon is a persistent memory CLI tool that enables Claude agents to store, link, and retrieve facts across sessions using a structured knowledge graph. Use it to maintain continuity by remembering user preferences, past decisions, and contextual insights, while deliberately excluding secrets and operational noise. The tool supports intelligent deduplication, semantic and causal linking between memories, and batch import from historical chats or exported contexts.

View source Repository: mnemon

Install in Claude Code

Copy

git clone --depth 1 https://github.com/mnemon-dev/mnemon /tmp/mnemon && cp -r /tmp/mnemon/internal/setup/assets/workbuddy ~/.claude/skills/mnemon

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

# mnemon

## Workflow

1. **Remember**: `mnemon remember "<fact>" --cat <cat> --imp <1-5> --entities "e1,e2" --source agent`
   - Diff is built in: duplicates are skipped, conflicts are auto-replaced.
   - Output includes `action` (added/updated/skipped), `semantic_candidates`, and `causal_candidates`.
2. **Link** (evaluate candidates from step 1 using judgment):
   - Review `causal_candidates`: link only when the memories are genuinely causally related.
   - Review `semantic_candidates`: high `similarity` alone is not enough; skip unrelated keyword matches.
   - Syntax: `mnemon link <id> <candidate> --type <causal|semantic> --weight <0-1> [--meta '<json>']`
3. **Recall**: `mnemon recall "<query>" --limit 10`

## Commands

```bash
mnemon remember "<fact>" --cat <cat> --imp <1-5> --entities "e1,e2" --source agent
mnemon link <id1> <id2> --type <type> --weight <0-1> [--meta '<json>']
mnemon recall "<query>" --limit 10
mnemon search "<query>" --limit 10
mnemon import --dry-run <file>
mnemon import <file>
mnemon forget <id>
mnemon related <id> --edge causal
mnemon gc --threshold 0.4
mnemon gc --keep <id>
mnemon status
mnemon log
mnemon store list
mnemon store create <name>
mnemon store set <name>
mnemon store remove <name>
```

## Guardrails

- Use memory only when it can materially improve continuity or task quality.
- Do not store secrets, passwords, tokens, private keys, or short-lived operational noise.
- Categories: `preference`, `decision`, `insight`, `fact`, `context`
- Edge types: `temporal`, `semantic`, `causal`, `entity`
- Max 8,000 chars per insight.