A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.

Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

Claude Code 的記憶系統 | A memory system built with hooks + markdown. Zero dependencies.

🚀 Build powerful agents and configurations with the complete collection of Claude Code from an Anthropic hackathon winner, refined over 10+ months.

Private. Free. Local. — Memory engine for personal AI agents. AES-256-GCM encrypted, 73.7% on LoCoMo (beats Mem0), 62µs ingest, cross-device sync via your own cloud. Pure Rust, 3.8MB.

Persistent cross-session memory for Kiro CLI

MCP Context Server — a FastMCP-based server providing persistent multimodal context storage for LLM agents.

Memory that returns

A deterministic, high-performance memory engine. Built in Rust.

Persistent memory for GitHub Copilot — never lose context across chat sessions. Inspired by claude-mem.

OpenClaw plugin for Cortex — automatic long-term memory with knowledge graph retrieval. Auto-recall injects relevant memories before every agent turn, auto-capture extracts facts after responses, and file sync ingests MEMORY.md and daily logs in the background.

An embedded, deterministic, versioned memory engine and state-tracker for long-lived programs.

Team memory sharing for claude-mem — sync AI memories across developers, with Claude Code plugin, github action and knowledge distillation

storage engine for expeditious that uses node.js process memory

Mnemosyne is a research-driven system that models music as a memory artifact rather than as structured metadata. Instead of searching by title, artist, or lyrics, Mnemosyne allows users to recall songs using emotions, vague memories, scenes, and life moments.

Standalone AI agent memory engine — hybrid search (BM25 + vectors), Q-learning scoring, Ebbinghaus decay, tiered storage, knowledge graph. Part of TRW Framework.

AI companion framework with persistent memory, inner life, and continuity. 58 phases of proof that it works on a gaming PC.

SnailDB — A fast, scalable AI-native database built for LLM memory, embeddings, and high-performance knowledge storage.

Starter template for building LangGraph agents with real long-term memory using OpenMemory’s temporal graph.

3-tier AI memory engine with forgetting curves, spaced repetition, permanent memory integrity (Merkle+Hamming+Lyapunov), MnemoCoin economy, and AgentPay bridge. Drop-in memory for any AI agent.