← Back to Skills Marketplace
anthony-maio

Mnemos Memory

by anthony-maio · GitHub ↗ · v0.6.0 · MIT-0
cross-platform ✓ Security Clean
262
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install mnemos-memory
Description
Use when users or OpenClaw/ClawHub agents need to install, configure, self-bootstrap, troubleshoot, or operate Mnemos for persistent scoped agent memory, or...
README (SKILL.md)

Mnemos Memory

Mnemos is a local-first memory layer for coding agents. Use this skill to guide users or OpenClaw agents onto the supported install path, explain the operating loop, and keep compatibility claims accurate.

Default path

  • Prefer pip install "mnemos-memory[mcp]" and mnemos ui.
  • For OpenClaw / ClawHub, teach the agent to self-install mnemos-memory[mcp], run mnemos ui, then wire mnemos-mcp to the canonical MNEMOS_CONFIG_PATH before relying on memory.
  • Recommend SQLite as the supported persistent store.
  • Recommend a real embedding provider (openclaw, openai, openrouter, or ollama) for production retrieval quality.
  • Validate setup with the control-plane smoke check or mnemos-cli doctor.

Claim discipline

  • Safe to claim: local-first scoped memory, MCP tools, SQLite starter profile, Claude Code plugin flow, documented Codex flow.
  • Be explicit that deterministic auto-memory is shipped for Claude Code via hooks.
  • For Codex, Cursor, OpenClaw, and generic MCP hosts, do not imply automatic capture unless the host has its own automation or the user adds one.
  • Do not present removed legacy backends as available runtime options.

Workflow

  1. Identify the host: Claude Code, Cursor, Codex, OpenClaw, or generic MCP.
  2. If the repo is available locally, read README.md, docs/MCP_INTEGRATION.md, and docs/codex.md before answering.
  3. Give the default install path first. Only fall back to manual config snippets if the user cannot use the control plane.
  4. Explain the operating loop:
    • mnemos_retrieve at task start
    • mnemos_store for durable facts only
    • mnemos_consolidate before finishing substantial work
    • mnemos_inspect when a stored fact looks wrong
  5. Read references/hosts.md for host-specific config snippets and caveats, especially the OpenClaw / ClawHub self-install flow when the agent must bootstrap itself.
  6. Read references/operations.md for automation, capture-mode, storage guidance, and troubleshooting.

Avoid

  • Do not tell users to manually type memories as the primary workflow.
  • Do not recommend SimpleEmbeddingProvider for production retrieval quality.
  • Do not suggest external storage backends for Mnemos. Keep users on the SQLite path.
Usage Guidance
This skill is an instructional guide for installing and operating Mnemos and appears coherent with that purpose. Before using it, consider: (1) only allow the agent to self-install if you trust the package source—verify the mnemos-memory package on PyPI/GitHub and the exact version; (2) run installations inside a virtualenv or container to limit system impact; (3) be prepared that MNEMOS_CONFIG_PATH and a SQLite DB will be created/used—check filesystem permissions and back up any important data; (4) embedding providers mentioned require separate API keys—only supply those when you intend production embedding and store them securely; (5) if you do not want an agent to modify your environment autonomously, disable or restrict the skill's model invocation or require explicit user approval before running install commands; (6) after install, run mnemos-cli doctor and inspect installed files to confirm behavior.
Capability Analysis
Type: OpenClaw Skill Name: mnemos-memory Version: 0.6.0 The mnemos-memory skill bundle provides legitimate instructions and configuration for integrating Mnemos, a local-first memory layer, into AI agents. While it encourages the agent to self-bootstrap via 'pip install', this behavior is transparently documented and aligned with the stated purpose of enabling persistent memory. No indicators of data exfiltration, malicious execution, or unauthorized persistence were found across SKILL.md or the reference files.
Capability Assessment
✓ Purpose & Capability
The name/description match the instructions: the skill is an installation/operations guide for Mnemos. It does not request extraneous credentials, binaries, or config paths beyond what is reasonable for a memory/MCP integration.
ℹ Instruction Scope
SKILL.md tells the agent to prefer pip install, run mnemos ui, wire mnemos-mcp to MNEMOS_CONFIG_PATH, and to read repository docs (README.md, docs/MCP_INTEGRATION.md, docs/codex.md) and the included references. These actions are appropriate for an install/ops guide, but they do authorize an agent to perform system actions (install packages, write config files, read repo docs). Users should be aware the agent may run commands that modify the environment when following these instructions.
✓ Install Mechanism
There is no install spec in the registry bundle (instruction-only). The SKILL.md recommends using pip (a standard mechanism). No embedded download URLs or extract/install steps from arbitrary hosts are present in the skill content itself.
ℹ Credentials
The skill itself does not declare required environment variables or credentials. It does reference MNEMOS_CONFIG_PATH (a canonical config environment variable) and recommends using production embedding providers (openclaw, openai, openrouter, ollama) which would require API keys in practice. This is proportionate but means the user/agent will need to supply unrelated provider credentials to achieve production-grade retrieval; those credentials are not requested by the skill directly.
ℹ Persistence & Privilege
always:false (no forced global installation). However, the guidance explicitly instructs agents on self-install and wiring a config path, which will create files (pip packages, config in MNEMOS_CONFIG_PATH, SQLite DB). That behavior is expected for an install/ops skill but is a material system change the user should consent to.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install mnemos-memory
  3. After installation, invoke the skill by name or use /mnemos-memory
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.6.0
Align the skill to the SQLite-only 0.6.0 release and recall-gated plasticity guidance.
v0.3.0
Added the Mnemos 0.3.0 beta onboarding skill for OpenClaw agents, covering install, self-setup, and daily Mnemos use through MCP. This update also reflects the new Codex and Cursor soft-auto workflows, shared Neo4j-backed persistence guidance, and clearer host compatibility positioning so agents know what is automated today and what still depends on host-specific hooks or rules.
Metadata
Slug mnemos-memory
Version 0.6.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Mnemos Memory?

Use when users or OpenClaw/ClawHub agents need to install, configure, self-bootstrap, troubleshoot, or operate Mnemos for persistent scoped agent memory, or... It is an AI Agent Skill for Claude Code / OpenClaw, with 262 downloads so far.

How do I install Mnemos Memory?

Run "/install mnemos-memory" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Mnemos Memory free?

Yes, Mnemos Memory is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Mnemos Memory support?

Mnemos Memory is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Mnemos Memory?

It is built and maintained by anthony-maio (@anthony-maio); the current version is v0.6.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments