Awesome AI Memory | LLM Memory | A curated knowledge base on AI memory for LLMs and agents, covering long-term memory, reasoning, retrieval, and memory-native system design. Awesome-AI-Memory 是一个 集中式、持续更新的 AI 记忆知识库，系统性整理了与 大模型记忆（LLM Memory）与智能体记忆（Agent Memory） 相关的前沿研究、工程框架、系统设计、评测基准与真实应用实践。

Lightweight Long-Term Memory for LLM Agents.

Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discovery defines what to build, Delivery executes autonomously until criteria pass. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and more. No SDK. No package. Markdown + YAML + bash.

Automatic memory for OpenCode agents: persistent workspace memory, hot session context, and compaction-based memory extraction — with zero extra API calls.

A guide to building persistent AI memory using Obsidian, so your AI assistant knows you without re-explaining yourself every session

AI memory system combining vector search with temporal knowledge graph. Built-in cognitive engine for agents. Supports memory decay, contradiction detection, and MCP integration.

Lightweight, local-first memory for AI agents. Hybrid vector + BM25 search, LLM-powered fact extraction, zero infrastructure — just pip install.

POC visual search with smart glasses and Qdrant Edge.

A lightweight persistent-memory companion for OpenCode & Claude

Recallium is a local, self-hosted universal AI memory system providing a persistent knowledge layer for developer tools (Copilot, Cursor, Claude Desktop). It eliminates "AI amnesia" by automatically capturing, clustering, and surfacing decisions and patterns across all projects. It uses the MCP for universal compatibility and ensures privacy

Repo-local continuity runtime for AI coding agents. Preserves work state, decisions, failures, validation evidence and repo context across sessions, helping agents behave less like cold-start rookies.

Helix-AGI is an 'Agentic' LLM wrapper that uses a spatial-graph-based-memory retrieval system instead of a conventional RAG based system. The agent's focus center is mapped within the spatial mind graph with each turn allowing the importance of each memory to be determined by numerous additional metrics beyond cosine similarity alone.

Mimir's Memory Hub - multi-agent AI chat with persistent memory and SillyTavern compatibility

The World's #1 Memory Architecture for AI • Memory that thinks, learns, and dreams • Synthetic cognition infrastructure for Agentic Ai.

Persistent context for any AI agent with rules that hold themselves.

Context and memory management for agents to learn over time. Private and lightweight.

Local-first agent memory in one SQLite file: sqlite-vec/QJL two-pass vector + FTS5 search, knowledge graph (optional auto capture,) Ed25519-signed entries, and MCP server. No cloud dependencies.

A local MCP server that provides a vector file store to give AI agents a long-term memory.

A self-organizing memory for any AI agent. Brain dump tasks, decisions, ideas, and context — the agent captures, organizes, and helps you stay on top of whatever you're working on. Works with any use case: work, personal productivity, writing, training, research, or anything else.