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

claude-mem★ 118,538

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

headroom★ 80,193

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.

mem0★ 69,274

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

hindsight★ 62,148

Hindsight: Agent Memory That Learns

OpenViking★ 42,516

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

cognee★ 33,431

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free

gbrain★ 33,328

Garry's Opinionated OpenClaw/Hermes Agent Brain

graphiti★ 32,959

Build Real-Time Knowledge Graphs for AI Agents

TencentDB-Agent-Memory★ 31,070

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.

agentmemory★ 30,495

#1 Persistent memory for AI coding agents based on real-world benchmarks

beads★ 28,862

Beads - A memory upgrade for your coding agent

letta★ 25,502

Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

Agent-Skills-for-Context-Engineering★ 18,384

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★ 17,601

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.

memvid★ 17,435

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.

ai-memory★ 16,175

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

memU★ 14,630

Personal memory across agents

EverOS★ 13,947

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

MemOS★ 12,463

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.

autoharness★ 11,199

Building the self-learning layer next-gen agents will ship with, learning skills from real work.

engram★ 8,244

Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.

GPTCache★ 8,233

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

honcho★ 8,207

Memory library for building stateful agents

MineContext★ 5,553

MineContext is your proactive context-aware AI partner(Context-Engineering+ChatGPT Pulse)

obsidian-mind★ 5,552

A self-organizing Obsidian vault that gives AI coding agents persistent memory.

obsidian-second-brain★ 5,392

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★ 5,010

Zep | Examples, Integrations, & More

byterover-cli★ 4,945

ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)

OB1★ 4,769

Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat channel — any AI plugs in. No middleware, no SaaS.

LongMemory★ 4,585

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

OpenMemory★ 4,475

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

memory-lancedb-pro★ 4,447

Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI

agent-memory★ 4,323

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★ 4,262

TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.

lean-ctx★ 3,955

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.

SimpleMem★ 3,884

[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

letta-code★ 3,882

Agents that self-improve with experience

ReMe★ 3,827

ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

obsidian-wiki★ 3,789

Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents

Acontext★ 3,697

Agent Skills as a Memory Layer

PromptX★ 3,688

PromptX · 领先的AI 智能体上下文平台 | PromptX · Leading AI Agent Context Platform

agent-beacon★ 3,578

The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu

agentfs★ 3,509

The filesystem for agents.

vault-ai★ 3,385

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★ 3,281

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.

MemMachine★ 3,089

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.

memobase★ 2,962

User Profile-Based Long-Term Memory for AI Chatbot Applications.

trustgraph★ 2,955

The open-source ontology runtime for AI agents.

memsearch★ 2,913

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

Memary★ 2,662

The Open Source Memory Layer For Autonomous Agents

agentic-context-engine★ 2,608

🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai

magic-context★ 2,542

Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.

Agent-Memory-Paper-List★ 2,481

The paper list of "Memory in the Age of AI Agents: A Survey"

OptMem★ 2,452

Permanent memory for AI agents. A 426-token prompt, a script, plug and play.

openwolf★ 2,401

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.

memanto★ 2,387

Memory that AI Agents Love!

agentic-stack★ 2,315

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.

kernel-memory★ 2,233

Research project. A Memory solution for users, teams, and applications.

kernel-memory★ 2,232

Research project. A Memory solution for users, teams, and applications.

memmy-agent★ 2,227

🍙 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.

memorax-code★ 2,168

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.

mcp-memory-service★ 2,138

Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.

headroom★ 2,038

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

claw-compactor★ 2,005

14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.

hermes-hudui★ 1,863

Web UI consciousness monitor for Hermes — the AI agent with persistent memory

iwe★ 1,829

Markdown knowledge graph — LSP for your editor, CLI + MCP memory for your AI agents

mex★ 1,797

Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.

powercontext★ 1,756

Agent memory: long-term memory & agent memory handoff. Claude Code & Codex.

hivemind★ 1,657

Hivemind turns your traces into reusable skills across agents

puppyone★ 1,644

The (local & cloud) folder built for your agents.

deja-vu★ 1,633

Claude Code, Codex & Cursor memory — local MCP memory, session history search & coding agent handoff.

MemoryOS★ 1,627

[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.

omnibox★ 1,563

Anywhere, anything to memory, memory to anything.

nocturne_memory★ 1,436

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.

mnemosyne★ 1,428

The Zero-Dependency, Sub-Millisecond AI Memory System for Hermes Agents and Everyone Else!

memory-os★ 1,398

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.

PrismerCloud★ 1,365

Prismer Cloud

hermes-jev-skills★ 1,354

Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)

PaperGuru-Benchmark★ 1,328

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

claude-memory-compiler★ 1,324

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★ 1,317

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。

autocontext★ 1,300

a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task

OpenContext★ 1,292

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.

cq★ 1,279

An open standard for shared agent learning. Agents persist, share, and query collective knowledge so they stop rediscovering the same failures independently.

nautilus-compass★ 1,259

Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform

LightMem★ 1,228

[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation

agent-file★ 1,218

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★ 1,217

A-MEM: Agentic Memory for LLM Agents

Agent_Memory_Techniques★ 1,146

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.

MemAgent★ 1,118

A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.

Memslides★ 1,100

A hierarchical memory framework for personalized presentation agents. Try it at memslides.com.

Orbital★ 1,049

Context is yours. Agents are replaceable.

zhigeng★ 1,041

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.

A-mem★ 1,020

The code for NeurIPS 2025 paper "A-Mem: Agentic Memory for LLM Agents"

kody★ 980

🐨 The cloud for your team's agents. Save your agent memory, credentials, code, and automations, portable across every agent with Kody.

imcodes★ 965

The IM for agents. Shared Agent Context & Memory, supervised execution, and cross-agent audit across AI providers.

obelisk★ 957

Every past session, subagent, and workflow -- queryable by your agent, browsable by you

memorix★ 943

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.

MindMemOS★ 935
busabase★ 929

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.

More in Agent frameworks & infrastructure