ai-memory
Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
ai-memory is an MCP server that provides persistent, cross-agent memory for AI coding assistants, enabling seamless handoffs between different tools and team members. It captures session observations through lifecycle hooks and consolidates them into a searchable, git-backed markdown wiki that follows you across machines and agents. The server works with 20+ coding agents including Claude Code, Codex, Cursor, Gemini CLI, and OpenCode, storing knowledge per-project while keeping personal handoffs private. It operates with zero required LLM calls by default, using full-text search, entity extraction, and optional embeddings for retrieval.
Key Features
Use Cases
- 01Switching from Claude Code to Codex mid-task and continuing without re-explaining context
- 02Team collaboration where knowledge learned by one developer's agent is available to everyone
- 03Resuming work on a different machine with full access to project history and open questions
- 04Bootstrapping an existing project with months of history into agent memory
- 05Querying past architectural decisions and failed approaches before trying new solutions
- 06Maintaining long-running coding sessions with persistent memory across agent restarts
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
ai-memory — FAQ
What is ai-memory MCP server?+
ai-memory is an MCP server that provides long-term, persistent memory for AI coding agents. It captures session observations and creates a searchable markdown wiki that works across different AI assistants, machines, and team members.
How do I install ai-memory for Claude Code?+
Install via Docker by running the server container, then execute 'ai-memory install-mcp --client claude-code --apply' and 'ai-memory install-hooks --agent claude-code --apply'. Alternatively, use 'ai-memory run claude' which auto-installs hooks and MCP on first launch.
Which AI coding assistants work with ai-memory?+
ai-memory supports 20+ agents including Claude Code, Codex, Cursor, Command Code, Devin CLI, OpenCode, Gemini CLI, Grok Build CLI, Kimi Code, Kiro CLI, OMP, Zed, VS Code Copilot, and more. Full compatibility matrix is in the documentation.
Do I need API keys or LLM providers to use ai-memory?+
No, ai-memory works with zero LLM calls by default using full-text search. Adding providers like Anthropic or OpenAI is optional and enhances session summaries and enables semantic search, but is not required for core functionality.
Is ai-memory free and open source?+
Yes, ai-memory is released under the MIT license and completely free to use. Multi-user authentication, audit logs, and team features are built-in, not paid tiers.
Can I use ai-memory with my team?+
Yes, run the server on a shared host and point all team members at it. Knowledge is shared per project, personal handoffs stay personal, and every write includes attribution and appears in the audit log.
How do I install ai-memory?+
Open the source repository on GitHub and follow its README. ai-memory is a mcp server — MCP Agents Market links you directly to the official repo.
Is ai-memory free?+
ai-memory is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.