garrytan/gbrain

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

What it does

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.

How it helps ATF

Storing facts with sources and allowing corrections and withdrawal is worth comparing with how Harness keeps task memory and how Company Brain connects company records within access scope.

License

MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.

More in this category

• MemPalace/mempalace
  MemPalace stores AI conversation history as verbatim text, without summarizing, and retrieves it with semantic search. Its index organizes people, projects and topics so searches can be scoped, and data stays local unless the user opts in.
• 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.
• rohitg00/agentmemory
  A persistent memory server for coding agents such as Claude Code, Codex CLI, Cursor and Gemini CLI, and for any MCP client. It extends Karpathy's LLM Wiki pattern with confidence scoring, lifecycle, knowledge graphs and hybrid search.
• 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.
• supermemoryai/supermemory
  Supermemory is a memory and context layer for AI that extracts facts from conversations, keeps user profiles, handles updates and contradictions, forgets expired information, and combines memory with document search. It can run fully locally.

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.