Agent memory

Graph-Native Infrastructure for Context and Accountable AI Systems

14,486 stars+82 this week

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

57,520 stars+526 this week

Memory library for building stateful agents

8,028 stars+122 this week

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

861 stars+12 this week

🍙 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.

2,205 stars+22 this week

一款开源、基于昔涟开发的桌面 AI 智能体/An open-source desktop AI agent based on Cyrene.

792 stars+17 this week

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.

12,331 stars+109 this week

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

2,100 stars+34 this week

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

13,859 stars+76 this week

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.

4,314 stars+18 this week

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

2,489 stars+32 this week

Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.

2,895 stars+53 this week

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

68,669 stars+383 this week

Memory that AI Agents Love!

2,360 stars+7 this week

记忆桥 MemoryBridge — 跨设备、跨平台的 AI 共享记忆层 | Cross-device and cross-platform shared memory for AI (CDSMP implementation)

492 stars+42 this week

The best-benchmarked open-source AI memory system. And it's free.

60,478 stars+114 this week

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.

2,050 stars+47 this week

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

554 stars+7 this week

DeepSeek Harness 长篇角色扮演agent（DSH酒馆插件）：SillyTavern 角色卡导入、行动选项卡、分支对话管理、长篇记忆、关键词与语义混合检索、交互式角色卡创作、世界书、多角色 Agent 集群、文风预设、小说与角色卡导出、一键安装。 / Roleplay Agent 、Tavern plugin for DSH (DeepSeek Harness): branch conversation, long-term memory, hybrid keyword and semantic retrieval, SillyTavern cards, interactive card authoring, card export, one-click installers.

227 stars+9 this week

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

33,157 stars+161 this week

雨落下的地方，记忆会再次开花。可自部署的 AI 长期记忆与聊天网关。Self-hosted AI memory & chat gateway for long-term conversations.

236 stars+13 this week

Local long-term memory for Hermes, Codex, Claude Code, WorkBuddy and dsh agents: one SQLite store, source-backed recall, and tools to inspect, correct or delete what is remembered.

535 stars+13 this week

Audit trail database for AI agents. Tamper-evident, checksum-backed decision logs with session replay and time-travel debugging to support EU AI Act Article 12 record-keeping. Drift detection, MCP, Python & TypeScript SDKs. Self-host or cloud.

160 stars+6 this week

A free, open-source desktop app for getting work done with AI. It shows you what it would remember before it saves anything.

458 stars+44 this week

Trustworthy memory for DeepSeek Harness — 4-state trust machine, evidence chains, audited injections. Zero servers, just Markdown.

125 stars+6 this week

Local-first MCP long-term memory for AI agents with knowledge graphs, provenance, history and stale-fact tracking.

10 starsThis week: Not stated

Committed to building the world’s most cutting-edge, CJK-first memory module for all mainstream agents. Any issues and PRs are welcome.

11 starsThis week: Not stated

Bitemporal AI memory system: six-variable decay, time-graded recall, TTL expiry, dedupe, competitive retrieval (Neo4j + PostgreSQL + Redis)

201 stars+48 this week

A persistent memory native AI agent built for long term continuity and autonomy.

23 stars+23 this week

数字生命卡 · 代号 SYNAPSE-1024 · 给陪伴型 AI 的一张会忘事的脑子

26 stars+16 this week

Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source alternative.

1,811 stars+15 this week

Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swarms.

435 stars+6 this week

This project lets you create your own AI desktop companion with customizable characters and voice conversations that respond in just 1 second. Features include long-term memory, visual recognition, voice cloning and LLM training. Compatible with various Live2D customizations.

1,436 stars+14 this week

Your AI forgets every session. Give it a memory you can audit: local-first, review-gated agent memory — one SQLite vault for DSH, Claude Code, Codex, Cursor, OpenClaw, Hermes and MengBot (any MCP client), with an immutable audit log and a token ledger. Agents propose, humans approve. MIT, self-hosted, no cloud.

156 stars+30 this week

Permanent memory for AI agents. Single binary, zero dependencies, MCP native.

615 stars+4 this week

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.

3,084 stars+2 this week

Opensource Memory for Agents

338 stars0 this week

Community edition of RepoPrompt: a native macOS context engineering app for AI coding agents, with an MCP CLI.

985 stars+7 this week

Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.

257 stars0 this week

🌌 Mebular 忆云 · 智能体共享记忆与任务协作 | One shared memory and task graph for all your AI agents and devices: automatic or on-demand, secure, controllable, and decentralized!

150 stars+58 this week

🦉 Augur — 本地优先的投资研究记忆系统：18 位投资大师独立分析 + 加权共识，证据带时间语义、每次运行可复查，CLI / Dashboard / MCP。A local-first research memory system with 18 investor personas.

684 stars+25 this week

A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.

921 stars+5 this week

A persistent, file-based memory layer for coding agents — give Claude Code, Codex & others a project brain (durable decisions, requirements, constraints) via a zero-dependency CLI.

594 stars+3 this week

RuVector provides High Performance, Real-Time decisions and agent memory , Self-Learning Ai, Vector GNN DB built in Rust.

4,675 stars+18 this week

The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, and OpenCode. Zero cloud lock-in.

304 stars0 this week

Memory layer for AI agents — SDKs, CLI and MCP server for Membase

126 stars+30 this week

Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness: a ctx.memory capability seam with a zero-dependency SQLite provider, a memory tool, and frozen snapshot injection. Active (unfrozen 2026-10-12); see README for alternatives.

143 stars+1 this week

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

2,609 stars+4 this week

Stop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your AI harness that connects across your different tools (Cursor, Claude Code, Codex). It keeps your proprietary data completely local, and it actually learns over time.

790 stars0 this week

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.

1,425 stars+13 this week

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.

1,137 stars+5 this week

OpenLoomi is an open-source AI coworker. It connects your work tools, understands what you’re working on, and tells you what needs your attention, why it matters, and what to do next. It’s your open-source Attention Agent.

1,041 stars+2 this week

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

4,571 stars+11 this week

PSSA: a non-transformer language model written from scratch in Rust. Recurrent state-space layer, episodic memory, self-modifying weights, CUDA training, and a full terminal dashboard.

120 stars0 this week

Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and serves them over MCP.

145 stars-1 this week

The one place for the skills, keys and memory of every agent you use. Formerly OMNI.

377 stars0 this week

An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.

233 stars+2 this week

Local-first, evidence-aware project memory for AI coding agents.

105 stars+12 this week

Self-hosted AI Agent Memory + Code Intelligence Platform — one MCP endpoint for persistent memory, AST-aware code search, shared knowledge, and quality enforcement across all your AI coding agents.

105 stars0 this week

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。

110 stars0 this week

Recent memories stay detailed. Older ones grow concise. Important ones live on.近期记忆保持详细，旧记忆逐渐精简，重要记忆长期存在。

116 stars+4 this week

Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context across sessions.

827 stars+1 this week

Persistent local memory for AI coding agents. Preserve decisions and project context across sessions, compaction, and tools.

203 stars+6 this week

Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.

792 stars+1 this week

Fast, privacy-first desktop & web UI for self-hosted Honcho — browse memories, peers, sessions, conclusions, and chat with memory context.

194 stars0 this week

A portable memory layer that makes AI agents reliable across apps and sessions. Persistent, verifiable, and fully under your control.

133 stars+2 this week

A collection of enhancements, plugins, and prompts for Open WebUI, developed and curated for personal use to extend functionality and improve experience.

333 stars0 this week

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

106 stars+3 this week

Long-term memory for any AI agent. One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Self-host free or use Uteke Cloud.

284 stars+3 this week

Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns from use, forgets the irrelevant, and strengthens what matters. No cloud, no API keys.

322 stars+4 this week

Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.

232 stars+3 this week

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

1,218 stars+10 this week

Shared memory for AI agents

313 stars+1 this week

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.

282 stars-1 this week

Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, tamper-evident SHA-256 chain with RFC 3161 anchoring, 20 MCP tools.

1,441 stars+4 this week

Finish What You Start — Context engineering for Claude Code. Sessions last 20+ exchanges instead of crashing at 7.

355 stars+2 this week

Agent 通用长期记忆层：Agent 将重要信息按类型记录为多篇可读的 markdown 记忆文档，文档以链接形式列在限长索引中，索引随会话自动注入。DeepSeek Harness（dsh）有专用插件 dsh-engramory。

203 stars+4 this week

TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.

493 stars0 this week

Command line artificial intelligence - Context engineering for terminal powerusers

152 stars+1 this week

Plugin-first long-term memory for agent platforms — reference implementation of AMP (Agent Memory Protocol).

549 stars+1 this week

the agent experience layer · observability + memory for AI coding agents (Claude Code + Codex) · local-first, typed, yours

122 stars0 this week

Persistent memory for AI coding agents

224 stars0 this week

Auditable, local-first memory for AI agents in one SQLite file. MCP server for Claude Code, Cursor and Codex. npm: mnemosy-ai

159 stars+4 this week

Lossless long-term memory for a personal AI: never summarize, keep every line, put a timestamp on everything.

168 stars0 this week

🐾 给AI加长期记忆的轻量网关 / A lightweight gateway that adds long-term memory to any LLM

169 stars+5 this week

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

165 stars0 this week

Mine your Claude Code and Codex logs into a local you.md agent profile.

303 stars+1 this week

a best-effort approximation of a synthetic entity complete with all of the primatives required for long-horizon persistance. batteries included.

483 stars+1 this week

An open-source AI companion that actually remembers you — runs entirely on your own Mac or server. Desktop pet · long-term memory · proactive companionship · multi-device sync.

197 stars+7 this week

Context intelligence layer for LLM agents: persistent memory with write-time dedup, sensitivity tagging, conflict detection, and hierarchical decay. ~12ms. No LLM calls. MIT.

198 stars0 this week

30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.

490 stars+2 this week

Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG. Finds what RAG misses. Zero cloud, zero cost.

162 stars0 this week

Nexus, the shared context plane where every agent and human connect, collaborate, and evolve together.

194 stars0 this week

Open-source cognitive coprocessor with active memory for AI agents — persistent recall, semantic search, overnight dreaming, verified facts, encrypted USB sync. MCP server; works with Claude, ChatGPT, and any local LLM. Built by one maker and his agents.

159 stars0 this week

Persistent memory plugin for OpenCode. Obsidian-style knowledge base that survives across sessions

159 stars0 this week

Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.

207 stars+1 this week

Long-term memory for your AI companion, on your own Cloudflare account. Captures instantly, extracts every 4 hours, consolidates nightly, with six memory layers and a visual curation panel. QQ group: 1091783659

145 stars+4 this week

Open-source tools for AI on Memgraph: persistent agent memory, knowledge graphs, GraphRAG, and integrations for LangChain, LightRAG, and MCP.

119 stars+1 this week

Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.

139 stars+3 this week

Open-source infrastructure for agents that learn from experience. Capture production traces and turn lessons into reusable knowledge and skills.

342 stars0 this week

Context engineering for coding agents - CLAUDE.md templates, mechanical enforcement, and a field guide to 20+ best practices. Bootstrap with one command.

126 stars0 this week

Local-first semantic memory for AI assistants — one store your preferences, decisions and gotchas follow you into, across Claude Code, Codex, Cursor and Zed.

111 stars0 this week

Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more. / 深入解析 Claude Code 源码：架构、Agent 循环、上下文工程、工具系统等

3,816 stars+17 this week

A local-first, long-term memory for anything you'd otherwise forget.

271 stars+2 this week

Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex.

156 stars0 this week

OriginTrail Decentralized Knowledge Graph (DKG) — Shared memory for AI agents. Give Hermes, OpenClaw, Claude Code, Codex, and Cursor a local knowledge-graph memory that several agents can share, with provenance, and verify on-chain when it matters. Open source, Apache-2.0.

135 stars-2 this week

Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.

335 stars0 this week

Context Engineering: Build Consistent, Accurate, Predictable AI Systems

185 stars+4 this week

Turn your workday into structured workflows agents can execute. 100% local, served over MCP.

530 stars0 this week

Open-source Rust TemporalStore for LLM context management, temporal features, and risk control

212 stars0 this week

Self-hosted AI agent memory — MCP memory server with durable recall for agents

107 stars0 this week

Claude Code / Codex 共用的长期记忆 MCP：本地 Markdown/Obsidian 存储，跨工具记住你的项目与偏好｜Local-first shared memory MCP for Claude Code & Codex

103 stars+3 this week

Living Memory Coordinate-5: five-axis memory architecture for long-running LLM agents. Minimal SQLite + production PostgreSQL/pgvector reference impls, multi-channel recall pipeline, LLM-proposed hippocampus, persona policies, VPS 7×24 deployment shape. Not another vector DB.

159 stars+2 this week

Turn your Win, Mac or DGX Spark into an AI hotspot. Nightshift races hundreds of attempts overnight and keeps what passes. Plus the open context engines it runs on.

258 stars0 this week

Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini wrote on your machine, then carries the durable parts to every agent. It is local-first and under MIT license.

133 stars0 this week

Frozen — cross-agent persistent memory for coding assistants. Still works; the compressed-memory core now ships inside JuliusBrussee/caveman.

676 stars0 this week

Nemp - The memory plugin for Claude Code that remembers everything.

140 stars+1 this week

A memory layer for Claude Code that learns as you work. Persistent, per-context memory as plain markdown in your own git repo. No server, no telemetry.

118 stars0 this week

Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance.

905 stars+3 this week

Durable, file-based long-term memory for AI agents. Five-package plugin family: SDK, CLI, MCP server, Hermes adapter, and a LangGraph BaseStore. No vector database, no embeddings.

174 stars+1 this week

Infinite Long-Term Memory for AI Agents (MCP Server)

159 stars0 this week

Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats (Claude, ChatGPT, DeepSeek) straight to your local IDE agents (Cursor, Claude Code, Windsurf) powered by a local SQLite knowledge graph.

246 stars0 this week

Evidence-first local memory for AI agents with temporal versions, admission policies, citations, explainable recall, MCP, and audit tooling.

692 stars0 this week

A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

4,509 stars+1 this week

Stash — persistent memory layer for AI agents. Episodes, facts, and working context stored in Postgres. MCP server included. Self-hosted, single binary, no cloud required.

772 stars0 this week

Make every AI agent you use smarter. Persistent memory with SQLite FTS5, MCP server, Obsidian sync, and self-learning intelligence pipeline.

190 stars0 this week

A filesystem designed for agents, with SOTA retrieval, automatic memory profiles, sync engine. Drop any file type (pdf, images, videos), and grep through them.

492 stars0 this week

Deterministic memory layer for your agents

114 stars0 this week

Local-first persistent memory for OpenAI Codex: governed recall, progressive disclosure, no hosted vector database.

103 stars0 this week

Halofy is the open access and governance layer for AI agents across your organization. Identity, policy, provenance, audit, and signed erasure.

319 stars0 this week