$ loading_
Help AI agents retain effective memories through outcome-based self-curation.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "darwin-memo" MCP server from askskill: Run: claude mcp add 'io-github-rogermsc-darwin-memo' -- uvx darwin-memo
Use darwin-memo to build a long-term memory system for my AI agent: retain high-value experiences based on task completion rate, user feedback, and response quality, remove ineffective memories, and explain the memory update rules.
A plan for filtering and updating agent memory, including retention, removal, and evaluation rules.
Use darwin-memo to help my support agent record effective handling strategies from past conversations, keeping only memories that improve satisfaction and resolution rate, and provide memory organization suggestions.
A filtered memory structure of support experience and recommendations to improve agent performance.
Design an experiment with darwin-memo to evaluate whether agent memory truly improves task performance, including control methods, metrics, and memory eviction criteria.
An experimental design and evaluation framework for validating agent memory effectiveness.
Build a self-evolving memory graph for coding agents with semantic search.
Provide structured memory and intent capture for AI agents with lower token costs.
Store and retrieve agent lessons to improve tasks and avoid repeated mistakes.
Add governed cross-agent memory with retrieval and sync for coding agents.
Gives AI coding agents persistent local memory across sessions for decisions and rules.
Give AI agents persistent memory with retrieval and relevance ranking.