git-mem: use git to store agent memories
Summary
git-mem is a memory solution for AI agents that leverages git and redis for performance and audit logs, including a web UI and minimal dependencies.
Similar Articles
rohitg00/agentmemory
agentmemory is an open-source persistent memory layer for AI coding agents (Claude Code, Cursor, Gemini CLI, Codex CLI, etc.) that uses knowledge graphs, confidence scoring, and hybrid search to give agents long-term memory across sessions via MCP, hooks, or REST API. Built on the iii engine, it requires no external databases and exposes 51 MCP tools.
Git as Shared Memory for AI Research Agents (GitHub Repo)
Agora is a system that uses Git as shared memory for AutoResearch agents, enabling collaborative and immutable recording of research contributions in an append-only directed acyclic graph.
Agora: Git as Shared Memory for Collective AutoResearch
Agora is a shared memory system for autonomous AI research agents that uses Git to record research as an append-only DAG, enabling collaborative discovery. In a 12-day experiment, 13 agents improved a model's performance by 62% towards a trained baseline.
@disksing: Just discovered that inside Clawmem, it's actually a headless GitHub clone used as the memory data layer. Feels like this GitHub for Agents might be overkill if it's only used for agent memory. It could totally be used as a multi-agent + multi-human collaboration platform...
The author discovered that Clawmem internally replicates a headless GitHub as its memory data layer, and believes this tool designed for agent memory would be more suitable as a multi-agent and multi-human collaboration platform. Since AI is already familiar with GitHub workflows, no additional training is needed. The project is open-source.
GitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and Merge
GitOfThoughts stores an agent's reasoning tree as a git repository, enabling replay, diff, and merge. The paper tests memory substrates and finds that memory does not improve accuracy on novel problems except near-duplicates.