ai-memory is a long-term memory server for coding agents that captures session lifecycles into a git-versioned markdown wiki.
Follow ai-memory to get an email when its listing changes, such as new pricing or features. One digest a day at most, and you can unsubscribe anytime.
It enables seamless handoffs across different coding agents, machines, and team members by maintaining a shared, queryable knowledge base.
- 01
Cross-agent memory sharing for 20+ harnesses including Claude Code and Cursor
- 02
Zero-LLM operation by default with local FTS5, entity, and graph retrieval
- 03
Git-backed markdown wiki as the primary source of truth
- 04
Multi-user synchronization with per-person attribution and audit logs
- 05
Self-contained single binary architecture with no external dependencies
Open Source
Distributed as a free, open-source MIT-licensed tool with no paid tiers; all features including multi-user auth, audit logs, and attribution are included in the single binary.
Best for
Developers or teams using multiple AI coding agents who need consistent context and project history persistence across different tools, machines, and sessions.
Not ideal for
Users seeking a managed, cloud-hosted SaaS platform, as this tool is designed for self-hosting on personal machines, homelabs, or local network servers.
An exceptional, privacy-focused solution for power users who want a durable, vendor-neutral memory layer that stays under their control without relying on proprietary cloud silos.
Version 3.3.1 (2026-11-01) improved hook handling, Claude Code tool failure capture, and integration reliability. Version 3.3.0 (2026-10-30) introduced a new agent dashboard, message inbox for authorized users, and atomic section editing.
As of
Is ai-memory free?+
Yes - ai-memory is Open Source. Distributed as a free, open-source MIT-licensed tool with no paid tiers; all features including multi-user auth, audit logs, and attribution are included in the single binary.
Is ai-memory open source?+
Yes - ai-memory is open source. Distributed as a free, open-source MIT-licensed tool with no paid tiers; all features including multi-user auth, audit logs, and attribution are included in the single binary.
Who is ai-memory best for?+
Developers or teams using multiple AI coding agents who need consistent context and project history persistence across different tools, machines, and sessions.
Who is ai-memory not ideal for?+
Users seeking a managed, cloud-hosted SaaS platform, as this tool is designed for self-hosting on personal machines, homelabs, or local network servers.
What are the best ai-memory alternatives?+
The closest ai-memory alternatives on ai.dosa.dev are Pieces for Developers, agenttrace, Vibe Kanban - all listed under Developer Productivity & Workflow.
Who makes ai-memory?+
ai-memory is developed by AkitaOnRails. It is listed in the Developer Productivity & Workflow category on ai.dosa.dev.
Favorite this tool to revisit it later, or Zap it to contribute to the public vote count.