Agent frameworks & infrastructure

Agent memory & context

4,032 agents · most starred first

Agent memory & context, page 5 of 41

MemPrivacy★ 131

MemPrivacy is a privacy-preserving personalized memory management framework for edge-cloud agents.

sqlite-memory★ 131

Markdown based AI agent memory with semantic search, hybrid retrieval, and offline-first sync between agents.

markdown-agent-memory★ 131

Markdown-only hierarchical memory for long-running AI agents. Zero dependencies, 7 months in production. Copy-paste install prompt for any agent.

llm-wiki-memory★ 130

Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over a local LLM wiki with on-device embeddings and an MCP server.

aikito★ 130

Your durable workspace across AI agents.

deepagents-backends★ 129

S3, PostgreSQL, Azure Blob, GCS, MongoDB, and Redis remote backends for LangChain Deep Agents

trackinizer★ 129

Epistemological database for agent and human efforts, beliefs, and findings.

iai-mcp★ 128

The best-benchmarked open-source memory system for AI coding assistants

OpenKL★ 128

(WIP) Open Knowledge Layer(OpenKL): The Advance Knowledge and Memory for Personal Agents.

remindb★ 128

An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.

dreamgraph★ 128

DreamGraph is a graph-governed conceptual development environment (CDE) that turns plans, architecture decisions, and project knowledge into auditable execution through a persistent cognitive graph.

MistakeNotebookLearning★ 127

🎉 Congratulations! This work has been accepted for publication as a Findings paper at ACL 2026! Mistake Notebook Learning (MNL) is a novel, training-free memory framework that enables Large Language Model (LLM) agents to systematically learn from their mistakes

ai-collaboration-notebook★ 127

让 AI 主动记错题、自我迭代的协作机制 · A framework that makes your AI reflect on its own mistakes and stop repeating them

madre★ 127

MADRE · Codex, Claude Code, Gemini CLI and OpenCode in one local chat on your machine, with one memory every agent shares. Home for all your projects and a Coordinator above them. Read-only by default; you unlock more per message. In Spanish and English. Public beta.

Linope★ 127

Inspired by traditional kernels — a lightweight, flexible, general-purpose kernel for Agent OS.

roampal★ 126

Memory that learns what works.

REMO-langflow★ 125

A chat interface that uses the REMO memory system with LangFlow

openstinger★ 125

Portable Memory Harness for Agents. Grounding the Autonomous Era

mentedb★ 125

A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.

mnem★ 124

Git for AI Agent Knowledge. A persistent, versioned memory layer for AI systems. Hybrid GraphRAG retrieval. Runs entirely offline.

xMemory★ 124

[NeurIPS 2026] xMemory: Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation

ax★ 124

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

memorybot★ 123

A Node.js AI chatbot with unlimited context and chat history.

agentkeeper★ 123

Own your AI memory — import ChatGPT, Claude and Gemini exports, see what each AI knows about you. Checkpoint/restore and cross-model continuity for agents.

chatmemory★ 121

The simple yet powerful long-term memory manager between AI and you💕

agent-brain★ 121

Local-first RAG memory for AI agents: hybrid + GraphRAG search, MCP server with OAuth 2.1, plugin for Claude Code / OpenCode / Codex.

goodboy★ 119

Agentic development environment for your coding agents, built in public

StrataGate-AgentMemory★ 119

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。

honeycomb★ 118

AI coding agents forget. They forget across sessions, and they forget across tools. A decision you reached in Claude Code at midnight is invisible to Cursor the next morning. Honeycomb fixes that. Learn something once; recall it everywhere,

grandma★ 118

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.

AutoGen_EnhancedAgents★ 117

This repository holds enhanced Agents, built for the Microsoft AutoGen Framework. Debuting with a MemoryEnabledAgent with improvements in context/token control, portability, and PnP functionality.

MemEngine★ 116

A Comprehensive Library for Memory of LLM-based Agents.

AgenticSTS★ 115

Bounded, typed, ablatable memory contract for long-horizon LLM agents — Slay the Spire 2 testbed

AMA★ 115

ACL 2026 Code and Skills for “AMA: Adaptive Memory via Multi-Agent Collaboration”.

deepmem★ 114

Drop-in AI memory layer with 2x faster retrieval and 10x lower cost. Fully compatible with Mem0 API. Migrate in 5 minutes without any code changes. Self-host for free.

awesome-context-engineering★ 113

A curated list of awesome open-source libraries for context engineering (Long-term memory, MCP: Model Context Protocol, Prompt/RAG Compression, Multi-Agent)

open-index★ 113

Deterministic memory layer for your agents

dsh-sieve★ 113

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。

mallard-app★ 113

Flexible storage solutions for agent sessions.

skardi★ 111

Skardi is a self-improving context framework for ai agents

SR-Agents★ 111

SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.

causal-memory★ 110

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

flow★ 109

Turn isolated Claude sessions into a continuous working relationship

speechless★ 109

LLM based agents with proactive interactions, long-term memory, external tool integration, and local deployment capabilities.

agentbrain★ 108

🧠 Brain-inspired cognitive architecture plugin for AI agents — persistent memory, evolving personality, neurochemistry-driven mood, learning from mistakes. Fully local on OpenClaw.

agentdb★ 108

Vector memory that gets smarter every time your agent uses it.

Autonomous-Long-Term-Memory-System★ 108

具备自主经验涌现与上下文治理能力的 Agent 长期记忆系统

llm-wiki★ 107

Agent-native persistent knowledge management — compile knowledge once, query forever.

metronix-memory★ 107

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

lore★ 107

Local archive of your Claude Code and Codex sessions, plus reviewed long-term memory for coding agents and a doctor for their skill folders. Runs offline; no accounts.

async-cache★ 106

A caching solution for asyncio

cognitive-workspace★ 105

🧠 Active memory management system enabling functional infinite context for LLMs through cognitive workspace architecture

VelesDB★ 105

The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.

ai-memory-gateway★ 105

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

Awesome-Agent-Context-Compression★ 105

Context Compression in Long-Horizon LLM-based Agents

openclaw-graphiti-memory★ 104

Hybrid memory system for OpenClaw using Graphiti temporal knowledge graph

codex-memories★ 104

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

mem-forge★ 104

Give every agent your team's brain on day one. The memory layer for AI agents. Everything your team knows. Cited, and always up to date.

memonto★ 102

Augment AI agents with long-term memory through knowledge graph 🧠

dna-memory★ 102

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

sugar★ 102

Mission control for your agent fleet. One local-first board for Claude Code, Codex, Goose, Cursor and any MCP harness: durable tasks, live activity, cost attribution and audit exports.

mnemosyne★ 102

Mnemosyne is a agentic memory and orchestration system designed to provide Claude Code with persistent semantic memory across sessions.

RogueMap★ 102

High-performance embedded off-heap storage engine for Java, built on memory-mapped files. Map/List/Set/Queue beyond the JVM heap, plus an AI memory layer with hybrid vector + BM25 search.

hoist-the-elephant★ 102

Re-anchor long conversations that drift through repeated local corrections.

loci★ 102

Shared memory for AI coding tools: hybrid search, cited Q&A, harness memory discovery and a built-in Web console. Local index, MCP + HTTP.

pensyve★ 101

Universal memory runtime for AI agents

OmniMem★ 101

Self-hosted semantic memory for AI agents, served over MCP. Persistent sessions, experience scoring, a graveyard for dead ends and skills compiled from what worked, plus knowledge from the RSS feeds you read. One Rust binary on SQLite: a tray app for macOS, Windows and Linux, or a server.

letta-chatbot-example★ 100

An example chatbot application built on the Letta API, which makes each chatbot a stateful agent (agent with memory) under the hood.

MUSE★ 100

(ACL 2026 Findings) Learning on the Job: An Experience-Driven, Self-Evolving Agent for Long-Horizon Tasks

Mem-Gallery★ 100

The source code of Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents (ACL2026 Main).

WorldMM★ 100

[CVPR 2026 Highlight] WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning

letta-agent-sdk★ 100

The Letta Agent SDK is the SDK for stateful agents. Each agent has its own identity and long-term memory, and keeps both across conversations, models, and the computers it runs on.

ReflectWorld★ 100

ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Stream

billion-context★ 100

基本可用 Universal context-compression proxy for AI coding agents

zhigui-openclaw-ui-second-brain-skill★ 100

An advanced, UI-powered AI second brain Agent Skill for OpenClaw, Hermes Agent, WorkBuddy, TRAE, and QClaw. ZhiGui uses long-term memory to help you make better decisions, automatically plan tomorrow, resolve conflicting notes, and deliver each day's plan through your existing agent channels.

shared-memory-vault★ 100

A memory governance engine for multi-agent cloud knowledge bases — one knowledge base shared by every agent and every device, with consistency guaranteed. Pure Markdown, nine governance automations, zero dependencies.

threadport★ 100

Portable, verifiable work state for coding agents

MemRec★ 100

Collaborative Memory-Augmented Agentic Recommender System

membase★ 100

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

cortex★ 99

Cortex: Advanced Memory System for AI Agents

sivtr★ 99

A unified agent memory workspace for human and agent

MemoHarness★ 99

MemoHarness: Agent Harnesses That Learn from Experience

lerim★ 99

Compiles AI agent traces and truns them into reusable context.

dsh-block-ptc★ 99

Model-controlled context blocks for DeepSeek Harness PTC mode

memora★ 98

Memora is an agent that aims to replicate the human memory for AI assistants / agents.

hermes-dreaming★ 98

Staged self-improvement engine for Hermes-style memory, skill, and fact updates with explicit review and apply/discard gates.

mem-agent★ 98

transformers safetensors qwen3 text-generation conversational arxiv:2507.18071

AKV★ 98

Official implementation of paper "Cache Engineering for Agents"

membrane★ 97

A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.

contextual-engineering-guide★ 97

Implementation of contextual engineering pipeline with LangChain and LangGraph Agents

yantrikdb-hermes-plugin★ 97

YantrikDB memory provider for NousResearch/hermes-agent — self-maintaining memory with benchmarked recall, self-tuning ranking, contradiction tracking, proactive hygiene, and explainable recall.

lerim★ 97

Compiles AI agent traces and truns them into reusable context.

atlas-memory-demo★ 97

Atlas — Agent Memory on Elasticsearch. Three indices, hybrid recall with a reranker, supersession, decay, and per-user DLS isolation.

capn-hook★ 97

Navigational memory for coding agents: chart discoveries as you explore, cache-bust when files change

architext★ 96

The Context Engineering framework for building smarter, more reliable AI Agents.

lerim★ 96

Compiles AI agent traces and truns them into reusable context.

daemonkey-agent★ 96

Local-first AI companion daemon — an agent harness with its own long-term memory. Remembers you, grows with you, extends and repairs itself. 跑在你自己电脑上的 AI 搭档守护进程:会记住你、随你成长、能自加技能、能自我修复。

fieldtheory★ 96

Mac app to create context for agents: writing, reading, voice, terminal, bookmarks, and clipboard.

CogniMem★ 96

Zero-LLM cognitive memory architecture for AI agents

PersonalMemoryBot★ 95

Memory 🧠 to your Personal ChatBot 🤖| LangChainAI and Databutton

More in Agent frameworks & infrastructure