a-mem-mcp vs agentmemory
Persistent memory for coding agents compared
a-mem-mcp and agentmemory help coding agents retain and retrieve project context across sessions. a-mem-mcp centers on an evolving graph of notes, while agentmemory emphasizes automatic session capture and shared memory across agents.
a-mem-mcp: Evolving Memory for Coding Agents
A-MEM MCP brings the A-MEM self-evolving memory approach to coding agents, organizing project knowledge as a connected graph stored in ChromaDB. It is currently tested with Claude Code and suits agents that need to recall and connect past project decisions.
agentmemory: Persistent Memory for AI Coding Agents
agentmemory gives coding agents persistent, searchable memory across sessions and tools. It captures work through agent integrations and exposes shared memory through MCP and REST, with a local-first runtime built on iii-engine.
| a-mem-mcp | agentmemory | |
|---|---|---|
| Language | Python | TypeScript |
| License | MIT | Apache-2.0 |
| Stars | 35 | 29.1k |
| Forks | 3 | 2.5k |
| Last analyzed | Oct 28, 2026 | Oct 3, 2026 |
Key differences
- a-mem-mcp uses LLM-generated note metadata and evolving links; agentmemory captures prompts and tool activity through agent lifecycle hooks, then organizes observations into memory tiers.
- a-mem-mcp combines semantic search with graph traversal; agentmemory uses BM25, with optional vector embeddings and graph-based matching.
- a-mem-mcp provides an MCP server and Python API; agentmemory provides MCP tools, a REST API, a local viewer, and session replay.
- a-mem-mcp is written in Python and licensed under MIT; agentmemory is written in TypeScript and licensed under Apache-2.0.
- a-mem-mcp reports 35 stars and 3 forks; agentmemory reports 29.1k stars and 2.5k forks, alongside 599 open issues.
- a-mem-mcp uses ChromaDB and configurable LLM backends; agentmemory runs locally on iii-engine and supports keyless BM25 search, while semantic embeddings require setup.
Choose a-mem-mcp if you…
- want an MCP server or Python API for adding, searching, and managing connected notes.
- prefer memory built around project-specific notes that can evolve as related knowledge is added.
- want to configure an LLM backend such as OpenAI, Ollama, SGLang, or OpenRouter.
Choose agentmemory if you…
- need automatic capture of prompts and tool activity through agent hooks.
- want to share memory across agents using MCP or REST, with a local viewer and session replay.
- prefer keyword search that can work without an API key, or want integrations for a range of coding agents.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.