Agent frameworks & infrastructure
Agent memory & context
Agent memory and context projects manage what an AI agent remembers and what context it sees. Some capture session activity and compress it for later reuse, as claude-mem does, while others shrink bulky tool outputs and logs before they reach the model, which is headroom's focus. Others provide drop-in memory layers or knowledge graphs that persist across runs.
4,032 agents · most starred first
Top 100 of 4,032
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Hindsight: Agent Memory That Learns
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
Garry's Opinionated OpenClaw/Hermes Agent Brain
Build Real-Time Knowledge Graphs for AI Agents
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.
#1 Persistent memory for AI coding agents based on real-world benchmarks
Beads - A memory upgrade for your coding agent
Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Personal memory across agents
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
Building the self-learning layer next-gen agents will ship with, learning skills from real work.
Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
Memory library for building stateful agents
MineContext is your proactive context-aware AI partner(Context-Engineering+ChatGPT Pulse)
A self-organizing Obsidian vault that gives AI coding agents persistent memory.
Persistent memory for Claude Code, Codex and 6 other AI agents, stored as plain markdown in your Obsidian vault. New: Crew, one shared logbook so Claude Code, Codex, Cursor and Grok Bot know what each other did. 48 commands: semantic search, self-rewriting notes, key-less research, scheduled agents.
Zep | Examples, Integrations, & More
ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)
Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat channel — any AI plugs in. No middleware, no SaaS.
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI
Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.
TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.
LeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence. Open-source Engine: CLI, MCP, hooks and supported proxy paths.
[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
Agents that self-improve with experience
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents
Agent Skills as a Memory Layer
PromptX · 领先的AI 智能体上下文平台 | PromptX · Leading AI Agent Context Platform
The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu
The filesystem for agents.
OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, epub, etc) using a simple React frontend.
Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.
User Profile-Based Long-Term Memory for AI Chatbot Applications.
The open-source ontology runtime for AI agents.
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
The Open Source Memory Layer For Autonomous Agents
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.
The paper list of "Memory in the Age of AI Agents: A Survey"
Permanent memory for AI agents. A 426-token prompt, a script, plug and play.
Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.
Memory that AI Agents Love!
One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when you switch.
Research project. A Memory solution for users, teams, and applications.
Research project. A Memory solution for users, teams, and applications.
🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc.
A memory plugin for AI coding that turns engineering experience, repository knowledge, and your way of working into memory that remains useful in future tasks.
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
Web UI consciousness monitor for Hermes — the AI agent with persistent memory
Markdown knowledge graph — LSP for your editor, CLI + MCP memory for your AI agents
Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.
Agent memory: long-term memory & agent memory handoff. Claude Code & Codex.
Hivemind turns your traces into reusable skills across agents
The (local & cloud) folder built for your agents.
Claude Code, Codex & Cursor memory — local MCP memory, session history search & coding agent handoff.
[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.
Anywhere, anything to memory, memory to anything.
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.
The Zero-Dependency, Sub-Millisecond AI Memory System for Hermes Agents and Everyone Else!
A 7-layer memory operating system for Hermes Agent — persistent memory with Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context injection. Runs locally, any LLM provider.
Prismer Cloud
Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
Lifecycle-Aware Memory for long-horizon LLM agents — 66.05% on PaperBench, 94.66% on SurveyBench, 10 peer-reviewed acceptances at FSE/ICML/TOSEM/AEI/ICoGB
Give Claude Code a memory that evolves with your codebase. Hooks automatically capture sessions, the Claude Agent SDK extracts key decisions and lessons, and an LLM compiler organizes everything into structured, cross-referenced knowledge articles - inspired by Karpathy's LLM Knowledge Base architecture.
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。
a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenCode) with built‑in Skills/tools and a desktop GUI to capture, search, and reuse project knowledge across agents and repos.
An open standard for shared agent learning. Agents persist, share, and query collective knowledge so they stop rediscovering the same failures independently.
Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
Agent File (.af): An open file format for serializing stateful AI agents with persistent memory and behavior. Share, checkpoint, and version control agents across compatible frameworks.
A-MEM: Agentic Memory for LLM Agents
Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.
A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.
A hierarchical memory framework for personalized presentation agents. Try it at memslides.com.
Context is yours. Agents are replaceable.
知更 — 本地 AI 的上下文与记忆层。Mac 上用语音输入、情境代回并调度 Codex / Claude Code;iOS 正在成为随身记忆终端和本地 Agent 遥控器。Local-first · BYOK.
The code for NeurIPS 2025 paper "A-Mem: Agentic Memory for LLM Agents"
🐨 The cloud for your team's agents. Save your agent memory, credentials, code, and automations, portable across every agent with Kody.
The IM for agents. Shared Agent Context & Memory, supervised execution, and cross-agent audit across AI providers.
Every past session, subagent, and workflow -- queryable by your agent, browsable by you
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro, OpenCode, and Trae.
Open-source database & workspace for AI agents — structured data, durable knowledge, reusable skills, runnable apps, and human review on the writes that matter. Local-first and self-hostable.