Mnemon
Apps & AutomationmnemonMnemon is an Agent Skill for apps & automation published in the mnemon-dev/mnemon repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Persistent memory CLI for Kimi Code. Store facts, recall past knowledge, link related memories, manage lifecycle.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/mnemon-dev/mnemon/blob/HEAD/internal/setup/assets/kimi/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/mnemon, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
mnemon
Workflow
- 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, andcausal_candidates.
- Link (evaluate candidates from step 1 using judgment):
- Review
causal_candidates: link only when the memories are genuinely causally related. - Review
semantic_candidates: highsimilarityalone is not enough; skip unrelated keyword matches. - Syntax:
mnemon link <id> <candidate> --type <causal|semantic> --weight <0-1> [--meta '<json>']
- Review
- Recall:
mnemon recall "<query>" --limit 10
Commands
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.