Memmy: Open-Source Client for Unified Cross-Agent Memory Management
vista8 · x · 2026-07-30
The open-source project Memmy aims to solve the pain point of managing conversations and memories across different AI agents. It automatically scans and organizes local history from agents like Codex and Claude Code, distilling scattered chats into structured memory.
- Three-tier memory system: Mirrors human memory modes, evolving from factual memory (L1) to procedural memory (L2), then to pattern recognition (L3), ultimately condensing into reusable Skills.
- Seamless switching & CLI integration: Supports Mac and Windows with TUI and CLI. Users can let any agent read preferences and context via CLI without opening the main app.
- Automation: Automatically extracts and creates reusable skills based on chat history, and supports global search across all agent conversations.
Related event: Open Source Memmy Unifies Memory Across Multiple AI Agents(2 posts)→
More from coding & agent
- 'LLM code is sloppy' rebutted with real ffmpeg code: identical if/else branches in a top library — kingslyj · 2026-10-16
- Agent actions need checks outside the model: NVIDIA demos lean on guardrails amid wave of real agent incidents — Creamy-And-Crowded · 2026-10-16
- Vitalik builds "paranoid mode" agent wrapper with Tor, zkAPI and local prompt rewriting — DavideCrapis · 2026-10-16
- Agent fine-tunes Qwen3.5-0.8B with synthetic data: 4.7%→76.3% accuracy, 11.9× faster — ben_burtenshaw · 2026-10-16
- Beam-501B agent demo: solo beats 5-agent team on ProgramBench rebuild task — ben_burtenshaw · 2026-10-16
- Beam agent builds BeamSpeak, a local Parakeet dictation app for macOS — ben_burtenshaw · 2026-10-16