whereismyai
AI Memory
AI Memory is a persistent memory system for AI coding agents that stores session data in a git-backed markdown wiki for cross-agent and cross-machine access.
AI Memory serves as a persistent storage layer for AI coding agents, allowing knowledge to persist between different tools and sessions. It operates by capturing lifecycle hooks from coding sessions and saving the information as readable markdown files within a git-backed wiki. This approach ensures that data remains accessible regardless of which agent or machine is currently in use. The system functions without requiring LLM calls by default, relying on a derived index for retrieval tasks. It supports multi-user environments with built-in authentication and audit logging for team collaboration. Users retain ownership of their data in a transparent, file-based format that allows for manual editing or external tools.
AI Memory at a glance
Key features
- Git-backed markdown wiki for data storage
- Cross-agent memory sharing for coding sessions
- Lifecycle hook capture for automatic session recording
- Zero-LLM default operational mode
- Multi-user authentication and audit logging
- Automatic handoffs between different coding agents
- Self-contained binary architecture
- Access-weighted retention schedules
Use it for
- Sharing project context across multiple coding agents
- Resuming coding tasks on different machines
- Collaborating on agent-captured project knowledge within teams
- Maintaining persistent architectural records without LLM dependency
Alternatives to AI Memory
- Tigerless Agent Memory — Maintains agent history in portable, greppable Markdown files without API keys.
- Engram — Single Go binary with zero dependencies and built-in full-text search.
- Memorax Code — Carry project architecture and verified engineering decisions across coding sessions.
- claude-mem — It shares persistent, searchable agent memory across sessions and devices.
- Codebase Memory MCP — High-speed indexing and persistent knowledge graphs for AI coding agents.
- Supermemory — Integrates long-term memory into AI coding agents with a single prompt.
- Alook — Connects existing local coding agents to team communication channels.
- AgentMemory — It runs locally with zero external databases and achieves high retrieval recall.
- Dosu — It enables a shared knowledge cache so agents avoid redundant data gathering.
- IHMT MEMORY — It shares one local memory across multiple AI agents without cloud storage or databases.
- memU — It gives every connected agent a shared and inspectable memory layer.
- Turnbook — Saves every chat turn locally with zero model tokens and shares memory across AI apps.
All AI Memory alternatives