Agent frameworks & infrastructure

Agent memory & context

4,032 agents · most starred first

Agent memory & context, page 9 of 41

ReMemR1★ 46

Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents

how-ai-agents-remember★ 46

源码级逆向工程(Hermes、OpenClaw、nanobot、NullClaw、OpenFang)记忆系统 —— 架构图、数据模型、检索管线、复刻指南。Source-Level Reverse Engineering of Memory Systems (OpenClaw, nanobot, NullClaw, OpenFang) — Architecture, Data Model, Retrieval Pipeline, Replication Guide

memoria-chat★ 46

An open-source AI chat client with structured memory and persona engineering.

palinode★ 46

The memory substrate for AI agents and developer tools. Git-versioned, file-native, MCP-first.

agentmemory★ 46

Memory system for AI agents. #1 on LongMemEval — 96.2% (481/500). Beats every published system including Chronos, Mastra, Supermemory, and Emergence. Built solo in 16 days for $1,000.

CSM★ 46

Persistent memory and operational continuity for AI coding agents — append-only event ledger (AgentBook), rolling summaries, self-model, belief knowledge, and turn-1 frontpage injection for deterministic cold-start.

brain-db★ 46

Memory database for AI agents — stores typed memories (facts, preferences, events, entities, relations) with provenance, confidence, and bi-temporal validity, and answers with fused semantic + lexical + entity-graph + temporal retrieval. One Rust core, one binary wire protocol. Apache-2.0.

persistent-mind-model-v1.0★ 46

Event-sourced runtime for reconstructable AI identity, memory, reflection, commitments, and auditable cognitive continuity.

headroom★ 46

Know when your AI is about to forget — browser extension that monitors context window usage

Adam★ 45

Adam Framework for OpenClaw — 5-layer persistent memory and identity architecture for AI agents. Production-validated over 353+ sessions. First documented case of emergent values in persistent AI, quantum-verified on IBM hardware.

Agentic-Context-Engineering-OpenSource★ 45
goodai-ltm★ 45

A Python library for long-term memory in language models. Improve conversational scenarios and create autonomous learning agents with enhanced context.

context-surgeon★ 45

Give AI agents the ability to edit their own context window

wavescope-mcp★ 45

Wavelet-based multi-resolution context management for LLMs via MCP

sessiongrep★ 45

Local-first memory layer for CLI agents. Indexes Claude Code, Codex CLI, Cursor, Antigravity, and Pi sessions into SQLite + FTS5, searchable from a CLI, TUI, or MCP server.

Refine-Cycle-for-Hermes-Agent★ 45

Self-improvement loop for Hermes Agent: reads its own trajectory, proposes and applies the smallest skill/memory edit (create/patch), journaled with rollback. /refine command, refine_run tool, on_session_end hook.

llm-wiki-workshop★ 45

Learn to design an LLM wiki from first principles. Used as agent memory. Workshop with 3 exercises, open-source code, video, and slides. No coding skills required.

NylonME★ 45

A Memory Engine for AI Agents,Working with Jev can bring higher decision accuracy . Nylon models a memory as a woven body of multiple strands of "threads" (facts/emotions/timing/relationships/beliefs/frequencies), with weighted edges between memory nodes forming a network graph rather than a hierarchical tree.

awesome-letta★ 45

A curated list of awesome Letta projects, tools, tutorials, and resources for building stateful AI agents with persistent memory.

context-editor-agent★ 44

Cursor uses AI to edit code — we use AI to edit AI's context. 🪆 Context map + compression + version control for LLM context windows.

swarms-memory★ 44

A collection of pre-build wrappers over common RAG systems like ChromaDB, Weaviate, Pinecone, and othersz!

mie★ 44

Persistent memory graph for AI agents. Facts, decisions, entities, and relationships that survive across sessions, tools, and providers. MCP server — works with Claude, Cursor, ChatGPT, and any MCP client.

context-harness★ 44

Local-first context ingestion and retrieval for AI tools. SQLite + embeddings + MCP server for Cursor & Claude.

Continuum★ 44

A persistent, multi-agent Model Context Protocol (MCP) server. Continuum gives AI coding agents — Claude Code, OpenCode, Codex, Gemini CLI — a shared, live view of a codebase and a memory that survives across agents and sessions.

ReadMe★ 43

Turn your files into a memory filesystem for AI agents.

dreamer★ 43

Self-evolving context for any coding agent.

ark★ 43

AI Runtime Kernel: a context operating system for AI agents. Eliminates tool bloat, loads only what’s needed, and gives LLMs their reasoning space back.

memclaw★ 43

Persistent project memory for AI coding agents — isolated workspaces per project, web dashboard to review what your agent remembers, team collaboration. Free to use.

ai_lives_on_computer★ 43

An experimental framework for autonomous, self-evolving AI agents living on a server with cross-session state and persistent memory.

superbrain★ 43

Session memory for Claude Code. Auto-captures every session into a plain Obsidian markdown vault. Zero config. MIT. macOS + Linux.

inite-brain-service★ 43

Open-source bitemporal knowledge graph — long-term memory for AI agents. Hybrid retrieval, conflict-aware ingest, GDPR forget. REST + native MCP.

loop-agent★ 43

A Python app that shows how an agent calls tools, saves results, and recalls them after a restart.

agent-knowledge-framework★ 42

Agent team knowledge framework with layered structure for principles, skills, insights, and experience

tovana★ 42

Memory management system to enhance AI agents with personalized, reasoned and context-aware responses

atomic-knowledge★ 42

Markdown-first work-memory protocol for existing agents, with maintained knowledge, candidate notes, evals, and an example KB.

Awesome-AI-Memory★ 42

TMLR | This survey presents a comprehensive and structured synthesis of memory in LLMs and MLLMs, organizing the literature into a cohesive taxonomy comprising implicit, explicit, and agentic memory paradigms.

memory-engine★ 42

Agentic memory built on Postgres

memraw★ 42

An open experiment in memory for AI agents — the whole memory, always in context.

chum-mem★ 42

Better memory for your AI agents. (Karpathy + Graphify + PCKC)

memflywheel★ 42

Agent-native long-term memory that learns after every run. File-native, auditable, and integrated with Pi, Hermes, OpenCode, and OpenClaw.

neuralmind★ 42

Persistent code memory for AI coding agents, kept in your project on your machine. Gives Claude Code, Cursor, Cline, Hermes-Agent and any MCP client the files that matter for each prompt, learns which files you use together, and publishes every benchmark with its misses.

sediment★ 42

Semantic memory for AI agents. Local-first, MCP-native.

memory-trigger★ 42

AI 恋爱 · 人机恋 · AI 伴侣记忆引擎 —— 让你的Ai/Agent 永不失忆

mycelium★ 42

Organize your AI sessions, and carry what they know into the next one.

daidocs★ 42

Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM models work). MCP server + hooks for Claude Code, Claude Desktop, Cursor, Windsurf, Codex. 83% LongMemEval-S (GPT-4o), 92% (Claude Fable 5), 10x fewer tokens.

MnemoBrain★ 42

Two-engine memory stack for AI agents: Mnemosyne (reflex memory) + GBrain (knowledge brain). Installer, launcher, doctor — one command, any host.

mnemo★ 41

Persistent memory for Claude Code. Your AI never starts from scratch again.

Agent-Memory-Playground★ 41

Agent Memory Playground: AI Agent Memory Design & Optimization Techniques

codex-agent-mem★ 41

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflows. SQLite + FTS5 compact context packs, token savings, read-only mode, no external memory server.

WeLoom★ 41

基于本地 RAG 与大模型人格蒸馏的多平台聊天记忆系统。通过 FTS5 检索、语料清洗与长期报告生成,将聊天记录转化为高拟真的数字分身。

source-of-truth★ 41

Give your coding agent a persistent memory. source-of-truth keeps a living docs/ catalog of what exists, why, and what rules apply — so AI stops rebuilding, deleting, and breaking things it never knew were there. Works with Claude, Codex, Cursor, Gemini, Copilot & more.

deep-memory★ 41

A self-evolving knowledge accumulation & hybrid retrieval system for AI coding agents (Claude Code / Codex / etc.)

Kage★ 41

Persistent, verified memory for coding agents — so they stop re-explaining your codebase and never act on stale knowledge. Every memory is checked against your actual code; lives in your repo as plain files, shared via git. No account, no DB. Install: npx -y @kage-core/kage-graph-mcp install

Perenna★ 41

A lightweight, Git-backed permanent memory for AI agents.

agent-context-lab★ 41

A minimal coding-agent harness built to measure what context management actually costs: constraint survival after compaction (8%→83%), default-FAIL verification against false completions, and KV-cache prefix design (21%→90%). Stdlib-only, real deepseek-chat runs

agience-core★ 40

The operating system that AI workflows trust. Structure messy inputs. Establish identity. Track provenance. Build the durable data layer your AI workflows need to be trusted, reusable, and auditable.

context-mesh★ 40

Context Strategy Framework: Intent → Build → Learn workflow. Preserves context in AI-generated code.

prompt-refiner★ 40

🚀 Lightweight Python library for building production LLM applications with smart context management and automatic token optimization. Save 10-20% on API costs while fitting RAG docs, chat history, and prompts into your token budget.

mem7★ 40

Memory layer for AI Agents and OpenClaw powered by Rust

smriti★ 40

Shared memory for AI-powered engineering teams. Captures, indexes, and recalls conversations across Claude Code, Cursor, Codex, and other agents. Share team knowledge through git — no cloud required.

monlite★ 40

The complete backend for AI agents in one SQLite file : Documents, vectors, cache, queue, and cron.

dense-mem★ 40

Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgvector

pi-smart-compact★ 40

Smart Compact — recoverable context cleanup, verified compaction, session navigation and project memory for Pi Coding Agent.

overcr★ 40

Hermes-first operational AI substrate with filesystem-grounded memory, governance, persistent routes, and recoverable agent continuity.

pos★ 40

Give Claude Code a persistent memory — it remembers you, your projects, and your decisions as plain Markdown files you own. Fully local. Just say `start`.

keep★ 40

Reflective memory for agents

cost-of-remembering★ 40

The Cost of Remembering: filesystem memory matches long-context accuracy on LongMemEval while reading 97% fewer tokens and costing 95% less. Harness, run data, 129 agent-built memories, and paper source.

dsh-memoir★ 40

DeepSeek Harness (DSH) local-first cross-session project memory: zero bundled runtime deps, bounded cache-friendly Hot Memory, BM25 recall/cache, provenance, lifecycle and bilingual Web GUI; no embeddings or external service. / DSH 本地项目记忆插件。

hive★ 40

CPU-side action routing, context compression, and causal memory for AI agents — matches an LLM-everything agent at 58% fewer LLM calls and ~45% lower cost. Glues busyBee-cpu, honey-comb, and rust-brain.

dsh-session-sync★ 40

Cross-device DeepSeek Harness session sync: a dedicated git mirror with append-only keep-both conflict resolution (fork files, never silently overwritten), /sync command and sync_* tools

project-wiki★ 40

Durable, traceable project memory for AI coding agents. An evolution of Karpathy's LLM Wiki pattern built for codebases.

mnemosyne★ 40

Local-first MCP memory server for AI agents. Zero dependencies, SQLite on your own disk, 52 MCP tools with Mem0-compatible names. MIT.

MuscleMemory★ 40

Open-source procedural memory for AI agents. Learns from what worked and what failed.

Open-Memory-Protocol★ 40

Open Memory Protocol (OMP): an open protocol for moving and sharing AI-agent memory. Hosted at the AI Disclosures Project, co-convened with IBM and Mozilla.

Deepseekagents-DSA-Context-Engine★ 39

Cost saving Cognitive Architecture for AI Agents. Infinite Context. Perfect Recall. Zero Hallucinations.

zettelforge★ 39

Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents

openclaw-memory-management★ 39

AI Agent 记忆管理系统:P0/P1/P2 优先级 + 自动归档,Token 降 78%

braindump★ 39

An ergonomic, opinionated memory interface for AI agents

openclaw-membase★ 39

OpenClaw plugin for persistent AI memory

private-machine★ 39

You look lonely. I can fix that.

convx★ 39

Git-commit your AI conversations before they disappear.

claude-recap★ 39

Topic-based automatic memory for Claude Code — never lose context across sessions or compactions.

mempalace-rs★ 39

A high-performance, local, offline-first AI memory system built in Rust

engram-memory★ 39

The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.

personal-brain-builder★ 39

Local-first agent workflow for building private cross-project memory with explicit consent, validation, and crash-safe history.

dsh-agent-team★ 39

dsh-agent-team gives DeepSeek Harness agents that don't reset: durable Members with their own memory, notes, and skills across sessions, rollovers, and restarts. You set the direction; agents coordinate through Channels and Tasks.

DSH-KRouter★ 39

Second brain for coding agents. Seal the day, distill into Obsidian, hit that page tomorrow. Cursor, Codex, Claude Code, DeepSeek Harness.

jev-recall★ 39

Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev

borhan★ 39

Save conversations, search by idea, read the surrounding context. Memory for AI agents.

intent-continuity★ 39

A pure-Python system that automatically discovers, verifies, and applies relevant historical requirements for coding agents — no embeddings, no vector database, no LLM calls. Companion code for the Towards Data Science article on intent continuity.

AgentMemory★ 39

Self-hosted memory service for AI agents that work in teams, written in Rust: layered L0→L3 memory, async LLM distillation, hybrid BM25 + vector recall, and department/team/member isolation. SQLite or Postgres, any OpenAI-compatible LLM.

TeamAgentMemory★ 39

Self-hosted memory service for AI agents that work in teams, written in Rust: layered L0→L3 memory, async LLM distillation, hybrid BM25 + vector recall, and department/team/member isolation. SQLite or Postgres, any OpenAI-compatible LLM.

gcp-redis-llm-stack★ 38

Reference architecture for LLM-based applications on Google Cloud Platform with Redis Enterprise as a high-performance data layer.

digital-twin-proxy★ 38

A forward proxy to turn network traffic into personal memory for AI agents

getprofile★ 38

User profile and long-term memory for your AI agent. Drop-in LLM proxy that gives AI model persistent memory and structured user understanding.

tocket★ 38

Tocket: a file based project notebook that many AI agents read and write together

neotoma★ 38

The system of record for AI agents

cortex★ 38

Memory for AI agents that never leaves your device. Local-first, end-to-end-encrypted, zero-telemetry memory engine (Rust, MCP) — gives Claude & any MCP client persistent cross-session memory.

neuralyzer★ 38

AI agent harness tool allowing it to wipe its own session context and re-run the first message

brain★ 38

Give your AI a hippocampus. A unified, local-first memory operating system written in pure Rust

More in Agent frameworks & infrastructure