OpenMemory, also called LongMemory, is a local-first persistent memory engine that stores and recalls time-aware, sourced information for language-model applications and agents. It is for developers building agents that need durable project, chat, skills, or code memory, and the catalogue skill supports integrating that memory into agent workflows.
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 skills add CaviraOSS/OpenMemory --skill docsgit clone --depth 1 https://github.com/CaviraOSS/OpenMemoryWrote 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/caviraoss/openmemory/docs)<a href="https://agentmods.dev/skills/caviraoss/openmemory/docs"><img src="https://agentmods.dev/badge/skills/caviraoss/openmemory/docs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/caviraoss/openmemory/docs"><img src="https://agentmods.dev/badge/skills/caviraoss/openmemory/docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 7 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- high Memory Poisoning · line 35 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00096 | $0.01987 |
| Opus 5.5 | $0.00038 | $0.00795 |
| Sonnet 5.5 | $0.00019 | $0.00397 |
| Haiku 4.5 | $0.00010 | $0.00199 |
Grade A, and why
openmemory 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 1mo 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenMemory — OpenMemory MCP Operation Playbook
1. Overview
This skill is the operational playbook for OpenMemory (MCP) — a primary persistent memory system; the file-based fallback is a secondary index only (one-line pointers, no full-text copies). Configure project_id based on your workspace (see §4 Step 2).
2. HARD-GATE
3. Flow Router
| Trigger Signal | Route | When |
|---|---|---|
| User says "remember this", "save to memory", "store this" — or agent forms a stable conclusion worth persisting | SAVE | Post-task, or at user request |
| User says "recall", "what do you remember about", "check memory" — or agent needs historical context before answering | QUERY | Pre-task, or when context is insufficient |
| User says "forget this", "delete memory", "clean up memory" — or agent discovers outdated/wrong/duplicated memory | MAINTAIN | On discovery or user request |
4. SAVE Flow (5 Steps)
Step 1 — Classify sector
| Content Type | Sector | Example |
|---|---|---|
| Events / incidents that happened | episodic |
"2026-05-20 deployment 回滚" |
| Facts / knowledge / decisions / preferences | semantic |
"服务 A 依赖 服务 B 的 API v2" |
| Procedures / methods / rules / constraints | procedural |
"部署前必须运行测试套件" |
| User emotions / reactions / preferences | emotional |
"用户不喜欢冗长的总结" |
| Cross-event patterns / insights | reflective |
"部署失败通常与配置缓存有关" |
Step 2 — Choose scope
| Question | YES | NO |
|---|---|---|
| Is this specific to the current workspace/project? | openmemory_store_project (project_id: "{{PROJECT_ID}}") |
Go to next question |
| Is this general engineering knowledge? | openmemory_store (global) |
Default to project scope |
What ships with it
10 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.
- 1mo ago First seen · 203 lines · 96 tokens per session scan A 08063e0c91a6
openmemory is a skill published in the GitHub repository CaviraOSS/OpenMemory (4,527 stars, last pushed 26d ago), licensed Apache-2.0. It adds 96 tokens to every session and 1,987 once invoked, about $0.0004 per session on Opus 5.5. 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
surface-learnings
Use when the user asks "what have you learned", "what do you remember about me", "show me memory stats", "memory state", "/reflexes", or any variant. Surfaces what the limbic engine has accumulated as patterns, not as a memory dump.
context-recovery
Use at the start of every session, and especially after context compaction or a cold restart. Fires as the first action, before engaging with the user's opening message.
decision-encoding
Use when an architectural choice is made, a library is selected, an approach is committed to, a convention is set, or any "we'll do it this way" moment occurs. Fires the moment the decision stabilizes, not after.
pre-response-recall
Use when the user asks about anything that could have context in prior sessions — names, preferences, decisions, past work, or anything starting with "remember", "what did", "have we", "did we". Fires before generating any substantive response.
salience-filtering
Use when deciding whether to store a memory. Fires as a gate before every remember() call. The default answer is "no" — biological memory is selective, not exhaustive.
ccs-align
Run the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle observations through search → timeline → getobservations, land them in a seat-owned middle cache via atomic grab → append → filter exclude-marks → replace, manage exclude marks, and walk house → project → seat…