MemSearch is a cross-platform semantic memory layer for AI coding agents that stores human-readable Markdown memories and indexes them with Milvus for searchable retrieval. It is used by agent users who want persistent context and by developers building memory features into agents across tools such as Claude Code, Codex, DeepSeek Harness, OpenClaw, and OpenCode. Catalogue add-ons provide the hooks, skills, and plugin workflows that capture, retrieve, and maintain this memory.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/zilliztech/memsearch/memory-to-skillnpx skills add zilliztech/memsearch --skill memory-to-skillgit clone --depth 1 https://github.com/zilliztech/memsearchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zilliztech/memsearch/memory-to-skill)<a href="https://agentmods.dev/skills/zilliztech/memsearch/memory-to-skill"><img src="https://agentmods.dev/badge/skills/zilliztech/memsearch/memory-to-skill.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00082 | $0.01816 |
| Opus 5 | $0.00041 | $0.00908 |
| Sonnet 5 | $0.00016 | $0.00363 |
| Haiku 4.5 | $0.00008 | $0.00182 |
Grade A, and why
memory-to-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You manage MemSearch's procedural memory: skills distilled from the work you repeat — a third layer beside the daily journals (episodic) and PROJECT.md / USER.md (semantic). State once that this is MemSearch skill distillation, not the host agent's built-in skills system.
Stages: 0 memory journals → 1 candidate (.memsearch/skill-candidates/,
a git-tracked store that keeps evolving) → 2 installed (an agent skill dir).
Candidates are never installed automatically; installing is always a human step.
User requests may stop at candidate creation/review, or continue to installation
in the same turn after explicit approval; match the requested stage.
The plugins.<platform>.memory_to_skill.* config key prefix and the install-path
notes are platform-specific — see your platform reference file:
- Claude Code →
references/claude-code.md - Codex →
references/codex.md - OpenClaw →
references/openclaw.md - OpenCode →
references/opencode.md - DeepSeek Harness →
references/dsh.md
Intent routing
- "make/turn this into a skill", "from what we just did" → A. Capture now.
- "what skills / review candidates / install X" → B. Review & install.
- "mine my history / find recurring workflows" → C. Distill from history.
- "enable / configure / how eager" → D. Configure.
- Unclear or empty → run B's
list; if empty, offer A or C.
A. Capture what you just did (0→1→2)
You already have the context, so draft the skill yourself — do not call the background distiller for this. Write a SKILL.md body (markdown, no frontmatter): imperative numbered steps for the recurring task, concrete commands and paths, no secrets, self-contained.
Be exact — do not guess. You have the live session for what you just did, so use the real commands, paths, and output, not approximations. If a detail is uncertain, verify it (re-read the relevant files or the transcript) or keep that step general — a wrong command is worse than a vague one. Then persist it as a candidate:
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 139 lines · 82 tokens per session scan A 62b251b7e5a7
memory-to-skill is a skill published in the GitHub repository zilliztech/memsearch (2,568 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 1,816 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
openclaw-plugin
This plugin is a thin adapter between OpenClaw and LycheeMem. It does not replace memory-core, does not claim plugins.slots.memory, and does not duplicate LycheeMem algorithms.
lycheemem
Forceful operating rules for using LycheeMem as the primary structured long-term memory path inside OpenClaw.
memory
Use LycheeMem as Claude Code's structured long-term memory for prior conversations, user preferences, project decisions, timelines, and durable facts.
pre-pr
Prepare a Honcho change for a pull request to plastic-labs/honcho. Invoke before opening a PR, when drafting a PR body, when asked if a branch is PR-ready, or when filling the pull request template. Checks the linked issue, required tests and docs, then writes Description / Proofs / Fixes.
learn
Must be used near the end of any non-trivial turn that produced potentially reusable tools, guidance, errors, workarounds, or workflows, so those lessons are saved for future turns.
evolve-lite:retention
Apply data-retention rules to the local evolve store — flag or delete stale and unused memories and expired sessions (dry-run by default).