agentmemory
agentmemory is a MCP server for workflow automation and orchestration, published by rohitg00.
Persistent memory engine for AI coding agents—automatically captures session context, enables semantic search across agent interactions, and injects relevant context into new sessions.
Is it any good?
Effectiveness · benchmark pending
We haven't benchmarked agentmemory yet, so its score is provisional — computed from safety, maintenance, and documentation only, with popularity given no weight. When we benchmark it, we measure whether it produces materially better output than a frontier model alone, and that result leads the score. How we measure.
About agentmemory
Description · AI-summarised from the rohitg00 README
agentmemory is a memory engine built on the iii framework that enables AI coding agents to maintain persistent, searchable context across sessions. It automatically captures agent interactions (through 12+ hooks), stores them in a local SQLite database, and uses hybrid search (BM25 + vector + knowledge graph fusion) to retrieve relevant memories when starting new sessions. Works with any MCP-compatible agent (Claude Code, Cursor, Gemini CLI, Cline, Aider, Windsurf, and 15+ others) through a single shared server. Eliminates the need to re-explain architecture, preferences, and decisions across sessions.
Where it fits
Browse related skills
Install agentmemory
Install
Install via MCP server
{
"mcpServers": {
"rohitg00-agentmemory": {
"command": "npx",
"args": ["-y", "@rohitg00/rohitg00-agentmemory"]
}
}
}Install with your AI
Zero install · paste into ChatGPT, Claude, Cursor…
Install the "agentmemory" skill into my project by following all instructions at https://skillsdirectory.co/s/rohitg00-agentmemory
Your assistant reads /s/rohitg00-agentmemory and follows it — fetching the files from the source, placing them, and confirming before it runs anything. No account needed. How this works.
Frequently asked
FAQ
What does agentmemory do?
Persistent memory engine for AI coding agents—automatically captures session context, enables semantic search across agent interactions, and injects relevant context into new sessions.
How do I install agentmemory?
agentmemory is a MCP server. Primary install path: { "mcpServers": { "rohitg00-agentmemory": { "command": "npx", "args": ["-y", "@rohitg00/rohitg00-agentmemory"] } } }
What is the Skill Score for agentmemory?
agentmemory has a Skill Score of 7.2/10 (Solid). It is currently a provisional score — agentmemory hasn't been benchmarked yet, so it weights safety 75/100 (40%), maintenance 55/100 (30%), and documentation 85/100 (30%). Popularity carries zero weight until effectiveness is measured. See methodology.
Is agentmemory free?
agentmemory is published under the Apache-2.0 license. See the vendor's source repository for any usage limits or paid tiers.
Related skills in Workflow automation and orchestration
Related
LangGraph
Low-level orchestration framework for building, managing, and deploying long-running, stateful agents.
Devin Cursorrules
Transforms Cursor or Windsurf into a Devin-like agent with planner-executor multi-agent flow, web browsing, and self-evolving lessons.
Paperclip
Node.js server and React UI that orchestrates multiple AI agents with org charts, budgeting, governance, and task management to run autonomous businesses.
Embed this score
For maintainers · always-current, links back
Put it in your README — it updates as the score changes.[](https://skillsdirectory.co/skills/rohitg00-agentmemory)
<a href="https://skillsdirectory.co/skills/rohitg00-agentmemory"><img src="https://skillsdirectory.co/badge/rohitg00-agentmemory.svg" alt="Scored by skillsdirectory" height="28" /></a>