By anthony-maio
Equip Claude Code and compatible AI agents with biomimetic long-term memory via local MCP server. Recall relevant repo facts, user preferences, prior fixes, and architecture decisions before coding tasks; curate and store high-salience context during workflows; consolidate episodic data into compact semantic memory for persistent continuity across sessions.
Biomimetic memory orchestrator. Retrieve before complex work, store high-salience facts during execution, and consolidate before handoff.
Curate durable Mnemos memory after meaningful work. Use proactively to store stable repo facts, decisions, environment constraints, and recurring bug patterns, then consolidate memory.
Recall the most relevant Mnemos context before substantial work. Use proactively at task start to surface durable repo facts, environment constraints, prior fixes, and stable preferences that matter to the current task.
Use when Codex users or Codex agents need to install, configure, validate, troubleshoot, or operate Mnemos through MCP, or when they mention Codex memory, AGENTS.md memory policy, Codex Automations, or Mnemos in Codex.
Use when users or OpenClaw/ClawHub agents need to install, configure, self-bootstrap, troubleshoot, or operate Mnemos for persistent scoped agent memory, or when they mention Mnemos, agent memory, scoped memory, memory MCP tools, or memory automation.
Matches all tools
Hooks run on every tool call, not just specific ones
Admin access level
Server config contains admin-level keywords
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Local-first memory for coding agents that keeps project, workspace, and global context separate.
Mnemos plugs into Claude Code and other MCP hosts, rewrites stale facts instead of appending forever, and compacts raw agent history into durable memory.
Quick start · MCP setup · Codex · Website
Mnemos is a local-first memory layer for coding agents. The v1 target is straightforward:
This is not a hosted memory platform, team memory system, or remote sync product in v1.
Mnemos is now in broad public beta. The core engine and onboarding control plane are ready for real coding-agent usage, and the intended setup path is:
pip install "mnemos-memory[mcp]"mnemos uiIf you are coming from an env-var or hand-edited MCP config setup, use the UI's Import Existing Setup action first.
Manual env-var setup is still supported for advanced users, but it is no longer the primary onboarding path. This beta is meant for real users and real workflows, but it is still a beta: use it, stress it, and report where setup, retrieval quality, or host behavior breaks down.
pip install "mnemos-memory[mcp]"
mnemos ui
What the control plane gives you:
mnemos.toml.mnemos/mnemos.tomlInspectability entry points:
mnemos inspect <chunk-id> for raw JSON inspection from the CLImnemos inspect <chunk-id> --query "..." --current-scope project --scope-id <repo> to explain why a memory is relevant to a taskmnemos_inspect for MCP-native hostsFeedback review loop:
mnemos-cli feedback helpful|not_helpful|missed_memory --query "..." [--chunk-id <id>]mnemos-cli feedback-list --event-type missed_memory or mnemos-cli feedback-list --event-type not_helpfulmnemos-cli feedback-export --format jsonl --output feedback-events.jsonlFor advanced/manual setup, see docs/MCP_INTEGRATION.md.
Claude Code already has built-in memory. Mnemos is narrower and more explicit:
What curator is supposed to keep:
What curator should skip:
If you want "memory exists somewhere in the background," Claude's built-in path may be enough. If you want scoped, local, inspectable continuity across coding sessions, Mnemos is the point.
See the side-by-side writeup at docs/demos/claude-code-continuity.md.
Most agent memory tools either keep too much raw transcript or append contradictory facts forever. Mnemos uses a different design:
npx claudepluginhub anthony-maio/mnemos --plugin mnemos-memoryRepo analysis for coding agents with slash commands, skills, documentation agents, and a bundled Cartograph MCP server.
Human-Agent Loop Over Bot — give any AI agent a Discord communication channel for human-in-the-loop conversations via threads.
Persistent memory with reinforcement learning for coding agents. Powered by Turso.
memX: local-first semantic memory for coding agents. Native Claude Code lifecycle hooks.
Persistent memory for Claude Code - store decisions, patterns, and context across sessions
MeMesh — Local memory for Claude Code and MCP coding agents. One SQLite file, zero cloud required.
Long-term memory for Claude Code — slash commands, skills, opt-in session hooks, codebase indexing, and a deep-retrieval subagent over the @memsy-io/mcp server.
Persistent memory for Claude Code — remembers across sessions automatically. Install and forget. Scientific retrieval backed by 41 published papers.