whereismyai
Memory Catalog
Memory Catalog is a protocol for organizing an AI assistant's long-term memory into structured Markdown index, backlog, and log files.
Memory Catalog is a protocol for organizing an AI assistant's long-term memory into an index, backlog, log, and considered ideas register. It works by sorting memory into plain Markdown files with chat-level provenance links, allowing you to track work streams, tasks, and history accurately. Built on Claude's memory and Projects, the protocol carries over to any assistant supporting file-based memory. It is designed for users who want to keep their AI assistant's memory structured and useful as it grows. The system includes safety rules and verification tools to prevent data loss during cleanups.
Memory Catalog at a glance
Key features
- Organizes memory into index, backlog, log, and register files
- Links every entry back to the exact chat turn it came from
- Tracks open tasks and work streams in plain Markdown
- Records declined and undiscussed ideas in a considered register
- Provides safety rules and byte-verified backups for cleanups
- Supports project boards for organizing chats
Use it for
- Organize an AI assistant's long-term memory into structured files
- Track open tasks and work streams without status drift
- Review history and chat provenance for AI decisions
- Manage declined ideas so they do not repeat
Alternatives to Memory Catalog
- AI Memory — Shared memory for coding agents that works across machines and team members.
- ReMe — It enables local-first, file-native long-term memory sharing across multiple AI agents.
- Memori — Reduces LLM token usage and spend by over 97% with targeted recall.
- Tigerless Agent Memory — Maintains agent history in portable, greppable Markdown files without API keys.
- Maximem — It delivers fast retrieval and structured memory across frameworks.
- DocuMemory — Turns messy AI chat transcripts into clean, reusable context for future sessions.
- MemOS — It delivers ultra-persistent memory, hybrid-retrieval, and token savings.
- MemMachine — Provides long-term persistent memory for LLM-based agents.
- 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.
- Cognee — Persistent memory for AI agents using graph, vector, and relational retrieval.
- Engram — Single Go binary with zero dependencies and built-in full-text search.
All Memory Catalog alternatives