thedotmack/claude-mem

This page introduces an external open-source repository. It is not an HDATF product.

What it does

Claude-mem captures what an agent does during sessions, compresses it into semantic summaries with AI, and injects relevant context into later sessions. It works with Claude Code, Codex, Gemini, OpenCode and other agents.

How it helps ATF

Worth comparing with how Harness keeps state and memory during a task. Turning tool usage into summaries that later sessions can search could also be a reference.

License

Apache-2.0 Permissive, with a patent grant. Commercial use is allowed; keep the notices and state your changes.

More in this category

• NevaMind-AI/memU
  memU is an agent-driven memory system that keeps a personal LLM wiki shared across sessions, agents and devices. It captures session knowledge in scheduled background tasks, retrieves it into later tasks, and distills reusable skills from agent history.
• memvid/memvid
  Memvid packs data, embeddings, search structure and metadata into a single file that AI agents can search without a database server. Memory is written as append-only frames with timestamps and checksums, so past memory states can be queried.
• volcengine/OpenViking
  OpenViking is a context database for AI agents that stores documents, user memories and skills as a virtual filesystem agents browse with commands such as ls, read and write. Layered summaries let agents load full content only when needed.
• gastownhall/beads
  Beads (bd) is a CLI issue tracker for coding agents that stores work as a dependency-aware graph in Dolt. Agents find ready work, claim it and close it, and the graph can be shared with other machines and agents.
• garrytan/gbrain
  GBrain gives AI agents a memory that several agents can share. It stores explicit facts with their sources, supports corrections and withdrawal, and starts with keyword retrieval, adding semantic search and background enrichment when needed.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.