---
name: Mnemon
slug: mnemon-10
category: AI Engineering
description: Mnemon provides persistent graph-based memory for Claude Code agents. Use it to recall context before responding and store durable insights after responses, with private per-group memory and read-only global memory.
github: "https://github.com/mnemon-dev/mnemon/tree/master/internal/memory/setup/assets/nanoclaw/container-skill.md"
language: Go
stars: 523
forks: 65
install: "npx degit https://github.com/mnemon-dev/mnemon/tree/master/internal/memory/setup/assets/nanoclaw ~/.claude/skills/nanoclaw"
installs_to: ~/.claude/skills/nanoclaw
source_path: internal/memory/setup/assets/nanoclaw/container-skill.md
collection_size: 16
category_size: 2451
collection_url: "https://dirskills.com/collections/mnemon-dev/mnemon"
added: 2026-08-26T05:12:10.852Z
last_synced: 2026-08-26T05:12:10.852Z
canonical_url: "https://dirskills.com/skills/mnemon-10"
---

# Mnemon

Mnemon provides persistent graph-based memory for Claude Code agents. Use it to recall context before responding and store durable insights after responses, with private per-group memory and read-only global memory.

**Install:**

```bash
npx degit https://github.com/mnemon-dev/mnemon/tree/master/internal/memory/setup/assets/nanoclaw ~/.claude/skills/nanoclaw
```

## README

# mnemon — Persistent Memory

## Memory Stores

- **Private** (default): Per-group, read-write. All writes go here.
- **Global**: Shared across all groups, read-only. Use `--store global --readonly` to query.

## Recall — before responding

**Default: recall on every new user message**, unless ALL of these apply:
- Direct follow-up within a topic already fully in context
- No reference to past sessions, decisions, or preferences
- No knowledge dependency beyond the current conversation

To recall:
```bash
mnemon recall "<query>" --limit 5
# Also check shared knowledge:
mnemon recall "<query>" --store global --readonly --limit 5
```

Craft a focused, keyword-rich query — do not pass the raw user prompt.

## Remember — after responding

Run this decision tree after every substantive response:

**Step 1 — Does this exchange contain any of these?**
  a) User directive — preference, decision, correction, explicit "remember this"
  b) Reasoning conclusion — non-trivial judgment from multi-source synthesis
  c) Durable observed state — system fact, environment detail, architectural finding
  → No to all → STOP.

**Step 2 — Does a highly overlapping memory already exist?**
  → Yes, incremental new info → UPDATE (merge into existing)
  → Yes, but contradicts/supersedes → REPLACE
  → No significant overlap → CREATE

**Step 3 — Is it worth storing?**
  Rebuilding from scratch costs more than storing + recalling?
  - Single-query public facts → No
  - Multi-source synthesis with non-obvious conclusions → Yes
  - User-specific context no search engine can recover → Yes
  → No → STOP.

**What to store**: conclusions and user-specific context, not raw facts.

## Workflow

1. **Remember**: `mnemon remember "<fact>" --cat <cat> --imp <1-5> --entities "e1,e2" --source agent`
   - Diff is built-in: duplicates skipped, conflicts auto-replaced.
   - Output includes `action` (added/updated/skipped), `semantic_candidates`, `causal_candidates`.
2. **Link** (evaluate candidates from step 1 — use judgment, not mechanical rules):
   - Review `causal_candidates`: does a genuine cause-effect relationship exist? `causal_signal` is regex-based and prone to false positives — only link if the memories are truly causally related.
   - Review `semantic_candidates`: are these memories meaningfully related? High `similarity` alone is not sufficient — skip candidates that share keywords but discuss unrelated topics.
   - 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 recall "<query>" --store global --readonly --limit 10
mnemon search "<query>" --limit 10
mnemon forget <id>
mnemon related <id> --edge causal
mnemon gc --threshold 0.4
mnemon gc --keep <id>
mnemon status
mnemon log
```

## Guardrails

- Do not store secrets, passwords, or tokens.
- Never write to the global store — it is mounted read-only.
- Categories: `preference` · `decision` · `insight` · `fact` · `context`
- Edge types: `temporal` · `semantic` · `causal` · `entity`
- Max 8,000 chars per insight.