M

memory

AGI Memory

https://github.com/QuixiAI/agi-memory A sophisticated database design for Artificial General Intelligence (AGI) memory management, implementing multiple types of memory storage and retrieval mechanisms inspired by human cognitive architecture.

🔧🔗https://github.com/cognitivecomputations/agi_memory A sophisticated database design for Artificial General Intelligence (AGI) memory management, implementing multiple types of memory storage

go memdb

https://github.com/hashicorp/go-memdb Golang in-memory database built on immutable radix trees

Cipher

🔧🔗https://github.com/campfirein/cipher Cipher is an opensource memory layer specifically designed for coding agents. Compatible with Cursor, Windsurf, Claude Desktop, Claude Code, Gemini CLI, AWS's Kiro, VS Code, Roo Code, Trae, and Warp through MCP. Built by https://byterover.dev/

🔧🔗https://github.com/mem0ai/mem0-chrome-extension Claude Memory: Long-term memory for Claude

axon

🔧🔗https://github.com/nbursa/axon Local memory layer – no LLM API needed. Browser extension with local daemon that remembers your conversations, builds a YAML profile, and injects personalized context before

Ego AI

🔧🔗https://github.com/nbursa/EgoAI Cognitive control module for synthetic reasoning. Coordinates memory, perception, and goals.

🔧🔗https://github.com/nbursa/inception-core-server

A modular, extensible Rust-based server providing short-term, long-term, and latent memory services, a chat endpoint with a BaseAgent + Sentience DSL, and integration with ChromaDB and LLM services.

🔧🔗https://github.com/harishsg993010/HawkinsDB Building smarter LLM applications isn't just about better models - it's about better memory. HawkinsDB is our take on giving AI systems a more human-like way to store and recall information, inspired by how our own brains work. Based on Jeff Hawkins' Thousand Brains Theory, it helps AI models manage complex information in a way that's both powerful and intuitive.

🔧🔗https://github.com/Yuchen20/Memory-Plus 🧠 𝑴𝒆𝒎𝒐𝒓𝒚-𝑷𝒍𝒖𝒔 is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" across sessions—perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who wants their AI to actually remember them.