Agent frameworks & infrastructure

Agent memory & context

4,032 agents · most starred first

Agent memory & context, page 19 of 41

Memorie-AI★ 6

Local-first semantic memory engine for AI agents - scores, trusts, and forgets so your agent stops making the same mistake twice.

reasonkit-mem★ 6

High-performance vector database & RAG memory layer - hybrid search, embeddings, RAPTOR trees, BM25 fusion for AI systems.

knowledgeGraph★ 6

MCP server providing long-term memory for AI agents — knowledge graph with Qwen3 embeddings, continuous learning, and knowledge evolution

mindkeeper★ 6

Time machine for your AI's brain — auto-snapshot, diff & rollback for agent context files. OpenClaw plugin + standalone CLI.

memgraph-agent★ 6

🧠 Graph-powered memory for AI agents. NER + co-occurrence graph + Personalized PageRank. Zero LLM cost, CPU-only, 82% faster than vector search. Inspired by SPRIG (arXiv 2602.23372).

llm_growing_agent★ 6

This is a project aimed at creating an agent that perpetually thinks and develops itself. It can add entries into an SQLite database and change the structure of that databaase. It also has the ability to search the web when it needs to. It utilizes OpenAI function calling and the responses API. All that is needed to run it is an OpenAI API key.

langchain-collapse★ 6

Preventive context management for LangChain agents. Collapses consecutive tool-call groups before they fill the context window.

TEMPO★ 6

A temporary/working memory system that assists REMO in handling LLM memories

cognitive-memory-agent★ 6

A production-ready AI agent demonstration showcasing the cognitive-memory package in action. See how agents learn, remember, and get smarter with each interaction.

soleri★ 6

Knowledge engine for AI agents — persistent memory, vault, and brain that learns

rag-user-memories★ 6

🧠 AI Memory Proxy: LLM with persistent user memory using PostgreSQL + pgvector. AI-driven fact extraction, semantic search, single API call optimization.

neo-memory-mcp★ 6

Simple Local GraphDB based Memory, Neo4j / Kuzu

tree-memory★ 6

Experimental hierarchical external memory for AI assistants, designed to reduce context contamination and localize memory updates.

CTX★ 6

Trigger-Driven Dynamic Context Loading for Code-Aware LLM Agents

claude-code-memory★ 6

Claude Code forgets everything when a session ends. This fixes that — persistent memory across sessions, automatic context injection, and cache optimization so you pay less for every turn.

archiledger★ 6

Graph based implementation of the Model Context Protocol Memory Server

archon-memory-core★ 6

The only agent memory that gets better over time. Nightly consolidation, active forgetting, salience scoring. 9.01/10 on AMB benchmark. Local-first, Apache 2.0.

claude-memory-mcp★ 6

Persistent long-term memory for Claude Code via MCP. Auto-captures conversations, semantic search, importance scoring, decay. Just works.

graphstore★ 6

Memory infrastructure for AI agents!! store, recall by meaning or association, ingest documents, and track beliefs in one Python library.

DCGP★ 6

Context governance kernel for LLM agents. Predicts entropy, blocks hallucinations. Pairs with opencode-dcp. llm, llm-agents, opencode, opencode-plugin, context-governance, anti-hallucination, claude-code, cursor, typescript.

penfield-mcp★ 6

🧠 Persistent memory for AI Agents. Free trial → https://portal.penfield.app/sign-up

octopai★ 6

Octopai - The Infinite Evolution Skill Engine for AI Agents. 🐙 Everything Can Be a Skill • Skills Evolve Through Continuous Learning • Elevating AI Agent Cognition!

Mnemon★ 6

Biological nervous systems don't recompute known workflows from scratch. Mnemon gives LLM agents the same primitive — execution memory that caches plans, not responses. 93% token reduction, 2.66ms vs 20s, zero tokens on repeat runs. LangChain, CrewAI, AutoGen.

studiomeyer-memory★ 6

AI memory server with 56 tools. Knowledge Graph, semantic search, session tracking, multi-agent support. Free tier available.

Vektor-memory★ 6

Unified Workspace with Multi Agent memory - Slipstream - 5-layer associative graph memory (MAGMA) with autonomous REM cycle, CLI, GUI, DXT-MCP Cloak Tools.

memroos★ 6

Memroos: memory OS and governance layer for AI agents, agent workflows, dispatch, proof, and context continuity.

mistikguard★ 6

Trustworthy memory system for LLM companions. Prevents memory fabrication with provenance tracking, write gates, and grounding audits.

cairn★ 6

Persistent ground truth for Claude Code. Stop AI agents from drifting on your codebase.

context-engine★ 6

This repository contains code and walk-through for creating a local context engine

lunar-vault★ 6

Lunar Vault is a self-contained memory infrastructure for Codex. Features zero-dependency ONNX embeddings, advanced reranking, and secure one-click installation without leaking personal data

transcendence-memory-server★ 6

Self-hosted multimodal RAG cloud memory service — a shared brain for your AI agents. Multi-agent cross-query, LanceDB + LightRAG + RAG-Anything.

cruxible★ 6

Hard, verifiable state layer for AI agents

engram★ 6

Engram - file-system-based memory management system for AI agents that grows with you & your teams, across agents, projects, and devices.

distill★ 6

Your agent wastes context. Distill fixes it.

timps★ 6

The AI memory layer with 17 intelligence tools — catches contradictions, predicts burnout, tracks relationships. Model-agnostic, self-hosted

leaper-agent★ 6

Self-learning AI agent framework with 6-layer memory evolution engine. Build intelligent agents for any business scenario.

agidb★ 6

A cognitive substrate for AI agents — hyperdimensional memory with first-class goals, beliefs, sensory, self-model, and a non-destructive unlearn primitive. Rust top to bottom, embedded-first, no LLM in the read path. One binary, no query language.

dossier★ 6

Keep only the relevant context. AI as a tool.

Mycomind-Daemon-Ollama-Mixture-of-Memory-RAG-Agents★ 6

gradio region:us

wolbarg★ 6

Wolbarg — modular, provider-agnostic semantic memory SDK for AI agents

hco-mcp★ 6

Give your AI agent a memory. And a seatbelt.

SwarmVault★ 6

A shared knowledge vault + full software-engineering workflow for AI coding agents — run Claude Code and Codex in parallel with one memory, one plan.

directed-memory-bank★ 6

Stop re-explaining your project every AI session. Tool-agnostic project context in plain markdown — works with Claude Code, Cursor, Codex, Gemini, any agent that reads files.

aim-antigravity★ 6

A.I.M. – Actual Intelligent Memory: zero-token exoskeleton for long-running Claude/Gemini/Codex CLI agents. External SQLite memory, GitOps guardrails, DataJack cartridges. Alpha, trenches-first.

MemoryStackBench★ 6

an automated benchmark farm for agent memory frameworks.

aiduMEM★ 6

🤔 aiduMEM — Memory & Thought Engine for AI Agents. Built on mem0. Ebbinghaus decay, hybrid recall, relevance gate, federated multi-agent memory.

milepost★ 6

Long-term memory for Claude Code — a milestone-triggered, in-session work diary in plain markdown. No database, no lock-in, fully greppable.

persnally★ 6

A model of you, built from your own AI history, on your machine. Every AI you use reads it. So every AI finally knows you.

2origin★ 6

本象协议 Benxiang · 一源万影:保存本象,按需投影。面向 AI 的持久对象表示层——AI 只提交语义事务,确定性编译器校验后才落地,每个字段都能回答「凭什么」。A2 消融实测(2026-08-13,README §5):唯一幸存的分类性主张是结构性的——提示词结构上产不出证据链;A3 全套机制给 15.0%/27.5% 受测字段可溯源证据,所有纯提示词基线均为 0%(A0→A2 +41.3pt 显著 p=3.3e-5,A2→A3 +2.5pt 不显著)。四方言共用核心仅加 4 行;87 条语言无关一致性向量 + 两份实现。

alvyn★ 6

TypeScript event history on PostgreSQL for agent workflows and domain applications: typed aggregates, replay, projections, and transactional outbox - zero extra infrastructure

ai-agent-relay★ 6

Portable context for AI coding agents and agentic harnesses.

dsh-shoucang-memory★ 6

守藏 Shoucang — DeepSeek Harness (DSH) 长期记忆插件:会话蒸馏自动沉淀 × 深度睡眠反思归纳 × 词法+向量混合召回 × 认知环引导 × 主动遗忘,配本地设置面板。一条命令装上,助理即拥有跨会话记忆——数据全在本机,零上传。

ai-raccoon★ 6

Give AI agents a memory that outlives the session: local-first SQLite per project, hybrid search, workspace sandboxes, and optional cloud sync.

Agent-Brain-Hub★ 6

Shared, brain-inspired memory for AI agents: 13 brain regions with awake/sleep loops, a live visualizer, agents connected via REST/SDK/MCP, governance & audit, and business-value metrics. Works with Claude, GPT, Gemini, DeepSeek or local LLMs. SQLite storage. VI/EN/JA.

seamless★ 6

Local-first shared memory and task coordination for AI coding agents. One Go binary, MCP server, markdown files you own. Hooks for Claude Code and Codex CLI (and their desktop apps).

Mesh★ 6

Local-first shared memory and task ledger for AI coding agents. Keeps context across sessions in SQLite via MCP.

aries★ 6

Issue tracker, shared memory and coordination for AI coding agents across sessions and machines. MCP server, Go CLI, Dolt-backed, offline sync. bd/beads alternative.

Mnemai★ 6

A free AI interface with memory, local agents and multitasking. One memory for Claude, ChatGPT, Gemini and local models — on your computer.

continuity-plane★ 6

Continuity Plane|面向长期 AI 辅助开发的 provider-neutral 控制面,解决压缩遗忘、重复工作与多 Session 竞态;reliable recovery, bounded context, evidence gates, checkpoints, and safe collaboration.

open-brain-template★ 5

Open-source AI agent memory dashboard and MCP memory template with Supabase pgvector recall, Mem0, Optimization Kit, and Memory File Sync Kit for Claude, ChatGPT, and Cursor.

BIG-BRAIN-Memory-Bank★ 5

The definitive Memory Bank implementation for AI assistants that never forget

claw-kit★ 5

The safe OpenClaw — persistent AI identity, memory & Telegram chat for Claude Code. No daemons, no session hijacking, fully auditable markdown files.

engram-ai-memory★ 5

🧠 Cognitive memory system for AI coding agents — persistent semantic search, knowledge graph, Ebbinghaus forgetting, zero API cost. Works with Claude, Cursor, Antigravity.

agent-config★ 5

Skills SSOT and proving ground for entwurf — one operator's memory, skills, and 1KB identity carried identically across pi, Claude Code, Codex, Antigravity, Copilot, OMP, and OpenClaw. Semantic memory (Qwen3-Embedding-8B + LanceDB), 43 shared skills, and a version-pinned bench for agent runtimes.

ERINYS-mem★ 5

Reflexive memory for AI agents — forgets, distills, and dreams. MCP server with 28 tools.

openbrain★ 5

OpenBrain is an open-source machine-readable memory layer for agentic systems. It stores typed, versioned memory objects (claims, decisions, tasks, artifacts, entities, relations, thought summaries), supports structured queries + semantic search, and exposes a standard plug-in protocol via MCP.

checkpoint★ 5

Persistent memory layer for AI coding assistants. Eliminate rediscovery across sessions. Claude Code / Cursor / Copilot / Codex.

statewave-web★ 5

Official website for Statewave — open-source memory runtime for AI agents

open-mem★ 5

Episodic memory for AI coding agents — captures tool calls, edits, and outputs across sessions. The episodic layer of a full agent memory stack (pairs with QMD + probe).

neurox★ 5

Persistent memory for AI coding agents — your agent stops forgetting between sessions. One Go binary, one SQLite file.

mif-spec★ 5

MIF — Memory Interchange Format. A vendor-neutral JSON schema for portable AI agent memories. Convert between mem0, CrewAI, LangChain, and more.

Thronglets★ 5

P2P shared memory substrate for AI agents — stigmergic knowledge network via libp2p

memrok★ 5

Archived: graph-based memory curation for OpenClaw. No longer maintained.

MIF★ 5

Open standard for portable AI memory interchange — JSON-LD + Markdown dual format with W3C PROV provenance, bi-temporal tracking, entity relationships, and Obsidian-native support.

modular-patchbay★ 5

Context engineering IDE for AI agents. Design knowledge pipelines, not just prompts.

agentcache★ 5

Cache-aware orchestration for LLM agents. Fork helpers that share cached prefixes, detect cache breaks, and cut token costs by 38%+.

agentic-memory★ 5

Agentic memory for the masses.

clawdrive★ 5

Google Drive for AI agents. Store any file and search by meaning across modalities.

omakiten★ 5

Your AI agent's checkpoint

Autoreflex★ 5

Servidor local de skills com busca semântica para agentes de IA — reduz 85% do consumo de tokens tornando o conhecimento do agente reutilizável entre sessões.

deja★ 5

Persistent memory for agents. Agents learn from failures. Deja remembers.

memx★ 5

Lightweight and extensible memory layer for LLMs

engram★ 5

A bitemporal, graph-backed memory system for AI coding agents.

ragy★ 5

Temporal memory for your AI agents, financial research, and knowledge workflows.

aid★ 5

Local memory CLI for coding agents and developers working inside Git repositories.

memee★ 5

Cross-model shared memory for AI agents. One canon every model reads. Free OSS via pipx install memee. memee.eu hosts the Team edition with shared scope, SSO, audit log.

context-pressure★ 5

Context Pressure — AI Context Window Monitor for macOS

agentfeeds★ 5

Ready-to-read fresh context for personal agents

obsidian-cli-memory-bank-skill★ 5

Local-first Obsidian memory bank CLI for AI coding agents, with run logging, linked project notes, compaction, and search.

megg★ 5

Git-native memory for AI agents — markdown knowledge in .megg/ folders that travels with your repo. MCP server + CLI for Claude Code.

LLM-memory-LangMem★ 5

Managing Memory in LLMs with LangMem.

nlp_server★ 5

NLP server housing intent and NER models as well as an LLM agent with long term memory vector store for Ditto assistant clients.

react-ai-agent★ 5

React AI Agent with Long-Term Memory and Tool calling

agent-memory★ 5

Production-ready persistent memory for AI agents. Works with LangChain, CrewAI, AutoGen, and raw Anthropic/OpenAI SDKs — in 3 lines of code.

pinecone_sucks★ 5

An alternative to libraries like Pinecone, which are notoriously expensive, so that you can store information for LLM queries in your local machine.

cybermem★ 5

Remote Self-hosted Memory MCP Server

tulbase★ 5

Depth-aware context compression for LLM proxies. Turn-box marker format with epistemic transparency.

Advance_Agent★ 5

Advance chatbot using chainlit added github athentication using auth , sdk openai. This chat bot saves/remember your history

engram★ 5

Persistent memory for Claude Code — 6 MCP tools, SQLite, local embeddings, zero API calls. Your AI remembers across sessions.

supe★ 5

Cognitive memory for AI agents with validation and proof-of-work

More in Agent frameworks & infrastructure