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.
git clone --depth 1 https://github.com/mnemon-dev/mnemon /tmp/mnemon && cp -r /tmp/mnemon/internal/setup/assets/pi ~/.claude/skills/mnemonSKILL.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> ``` ## Import Historical Chats When the user asks to import old chats, notes, or exported context, create a `memory_draft.json` with `schema_version: "1"`, `insights` entries containing `content`, `category`, `importance`, `tags`, `entities`, and optional `created_at`, plus optional `edges` using `source_index`, `target_index`, `edge_type`, `weight`, and `reason`. Run `mnemon import --dry-run <file>`, then run `mnemon import <file>` only after validation passes. After import, verify with `mnemon status` and a focused `mnemon search` or `mnemon recall`. Check the output `errors` field because imports can partially succeed. ## 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.
Analyze Mnemon harness eval reports, classify outcomes, and extract improvement evidence.
Turn stable Mnemon harness eval findings into scoped project, loop, adapter, docs, or eval asset improvements.
Design a scenario-driven Mnemon harness eval with target, hypothesis, HostAgent, loop configuration, evidence, and rubric.
Execute or supervise a planned Mnemon harness eval run in an isolated HostAgent workspace.
Manage project-scoped Mnemon goal state, evidence, verification, completion, blockers, and host goal links.
Recall long-term memory from Mnemon when GUIDE.md indicates that prior memory may help the current task.
Maintain prompt-facing working memory by editing MEMORY.md when GUIDE.md indicates that durable information should be kept.
Draft or revise high-quality SKILL.md content for approved or proposed Mnemon skill changes.