Agent frameworks & infrastructure
Agent memory & context
4,032 agents · most starred first
Agent memory & context, page 3 of 41
memX: self-learning, self-maintaining memory plugin for AI agents; native support for claude code, codex, and openclaw
Context management for long-context LLMs, agents, and vibe coding. Instantly build context for an entire repo, selected files, folders, and GitHub issues to generate structured AI-XML context with real-time token counting.
Make your OpenClaw AI agent faster, smarter, and cheaper. Speed optimization, memory architecture, context management, model selection, and one-shot development guide.
Open agent skills by VESTI: vesti-memory and vesti-handoff
Reflexion: an autonomous agent with dynamic memory and self-reflection
Co-manage memory with your coding agent across sessions. A local workbench for Claude Code, Codex, Pi and OpenCode.
Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.
Self-host Honcho memory layer for Hermes Agent — OpenRouter + Venice, no code changes
The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.
Durable Pi playground and agent network: persistent, multi-device durable agents with web and terminal clients
Living memory for AI
The one place for the skills, keys and memory of every agent you use. Formerly OMNI.
A plain-text memory system for AI agents. Clone it, point your agent at it, start remembering.
Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.
Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twice. Nothing deleted, nothing invented.
Official MemOS Cloud plugin for OpenClaw. Enables long-term memory for agents by recalling context before execution and saving conversations after each run.
Deterministic, local-first code and contract intelligence for AI coding agents, with no LLM in the hot path.
A survey of Graph-based Agent Memory | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based agent memory.
Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party calls.
Local-first AI conversation memory hub to capture, search, summarize, and export chats across major AI platforms. 本地优先的 AI 对话记忆与知识中台。
Your AI coding agent never forgets — progressive session recall CLI
High-performance AI memory retrieval for local agent history — a Rust search core (SDK / API / JSON CLI) plus a desktop GUI. Tantivy + Jieba keyword search, optional semantic recall, stable Turn/Run/Session/Project IDs.
MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents. Accepted at ICLR 2026; Best Paper Award at the NeurIPS 2025 MTI-LLM Workshop.
9 Different Ways to Optimize AI Agent Memories
A Datalog engine for LLM agent memory: stratified rules, provenance-tracked facts, incremental derivation, and an MCP server that lets your harness use it as a shared brain.
🥝 Self-hosted memory gateway for AI companions — OpenAI-compatible proxy with vector search, memory heat, Dream consolidation and calendar-level summaries · AI 伴侣记忆网关:向量搜索、记忆热度、Dream 睡眠整合、日历层级摘要,任何客户端都能接
[!NEW!] OpenClaw Plugin for Agents to Become Clever and Token-Efficient!
understory — memory that grows. Self-wiring, plain-markdown memory for AI agents (MCP + local models + a living graph).
Markdown-first shared memory vault for Claude Code and Codex with SQLite, Zvec, Git, closeout, and audit
Official code for "Zero-Mem: Zero-Token Memory Operations for LLM Agents".
Open-source infrastructure for agents that learn from experience. Capture production traces and turn lessons into reusable knowledge and skills.
Opensource Memory for Agents
Persistent, self-improving memory for AI agents. Local-first Rust memory engine with MCP support.
Minimal kernel to make any AI coding agent stateful. Clone, point your agent, go.
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
Fast and flexible memory for agents and AI applications using Redis
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.
Persistent Agent Workspace — AI agents that remember, collaborate, and never start from zero.
Growing Expertise for Coding Agents — structured expertise files that accumulate over time, live in git, work with any agent
Shared memory for AI agents
Run MemGPT-AutoGEN-Local LLM Together
Memory Palace is a long-term memory operating system purpose-built for AI Agents.
ICML 2026 | PALM@NeurIPS2026 Oral | Plug-and-play long-term memory for LLM agents
Sync and store memories, shared identity files (AGENTS.md, CLAUDE.md), session transcripts, institutional knowledge, and secrets between all of your favorite harnesses and models.
Distributed, transactional document database backed by FoundationDB.
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.
AI Coding Agent 工作协议 — 跨会话记忆、多仓库全局视野、结构化上下文管理
Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.
Mine your Claude Code and Codex logs into a local you.md agent profile.
Stop re-explaining yourself to AI. MARM offers persistent memory, cross-agent context sharing, write queues, swarm-ready presets, and compaction for clean recall. Includes a live web dashboard for managing memories, logs, and sessions. MCP connects over HTTP & STDIO and works with major LLMs like Claude, Codex, Grok, Gemini, and other models.
ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engineered designs for agentic system.
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.
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Self-evolving memory palace for AI agents — persistent memory with automatic learning, knowledge graph, and multi-agent support
Shared context, memory, and task coordination across AI coding agents. Single Go binary, local SQLite, hybrid keyword and semantic search.
Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming, search)
Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn checked rules, and reuse.
WikiSkill (arXiv:2608.27454) for Hermes Agent — self-evolving agent skills via a persistent knowledge wiki. Faithful Algorithm 1 implementation with real agent runs, isolated skill gating, and a documented live run log.
Mimir - Fully open and customizable memory bank with semantic vector search capabilities for locally indexed files (Code Intelligence) and stored memories that are shared across sessions and chat contexts allowing worker agent to learn from errors in past runs. Includes Drag and Drop multi-agent orchestration
Persistent local memory for AI agents. MCP server and plugins for Claude Code, Codex, Cursor, VS Code Copilot, Antigravity and more: your agents remember across sessions, on your machine. arXiv:2608.08253
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.
Long-term memory for AI agents (MCP). One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Works with Claude Code, Cursor, Codex. Self-host free or use Uteke Cloud.
A recursive evidence-gated cognitive runtime for memory-native AI agents, combining hybrid retrieval, temporal reasoning, async learning, and plug-and-play tools.
A self-hosted, secure, feature-rich memory system for AI agents and assistants. Provides intelligent fact extraction and deduplication, with an artifact store for detailed content.
AI Agent Memory
Persistent, provider-neutral memory for Codex, Claude Code, OpenCode, Pi, and MCP coding agents.
LangChain abstractions backed by Postgres Backend
Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses
Jev-Mem: System-One Controlled Agentic Memory
Total Recall — Autonomous Agent Memory. The only memory system that watches on its own. Five-layer observational memory for OpenClaw agents. ~$0.10/month.
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
Self-improving agent runtime that learns from experience — test-verify-fix loops, correction detection, cross-project memory, multi-model orchestration.
The Fastest AI Memory Model - Your Second Brain
A local-first, long-term memory for anything you'd otherwise forget.
Official code for the paper "Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity"
[NAACL 2025] KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents
(S)AGE - (Sovereign) Agent Governed Experience
The AI agent memory cloud you’ll wish existed yesterday. Manage agent memory like a GitHub repo: switch devices, switch agents, switch sessions, and your AI still remembers who you are, what it has learned, the rules you taught it, where the project left off, and what to do next.
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.
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.
Summon it with a keystroke, throw in anything you want to remember or ask your own memory. A local LLM agent that restructures your knowledge into a vectorized DB. fully private, zero cloud.
Multi-agent demo platform for Titans (arXiv:2501.00663) — neural networks that learn to memorize at test time. 7 AI agents, native desktop UI.
The memory & storage database engine for AI agents. Multi-model, edge-to-cloud, PostgreSQL-compatible. Supports graph, vector, array, timeseries.
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.
🏆 AI Hackathon 2026 @ UC Berkeley Intelligent context management for developers
Redis checkpointer and store for memory management in LangGraph
The memory that dreams — long-term memory for AI agents. Readable files on your own machine, consolidated between sessions. Runs as a DeepSeek Harness plugin or over MCP.
Meteor extracts structured context from across your systems and delivers it to power your organization's context graph and AI agents.
Carry context across coding agents/editors/IDEs - Cursor/Windsurf/Claude Code/Antigravity
A persistent local memory for AI, LLMs, or Copilot in VS Code.
Open-source control plane and runtime for organisational agents: shared company context & brain
Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.
Xmem is a India's First open source multi-modal, multi-agentic long‑term memory layer for AI agents.
[EMNLP '26] Dependency-Aware Structural Retrieval for Massive Agent Skills
A curated collection of resources, papers, tools, and best practices for Context Engineering in AI agents and Large Language Models (LLMs).
Persistent memory for AI coding agents
Persistent memory extension for pi with daily logs, scratchpad, and optional qmd‑powered semantic search.
独立、可自托管的 AI 动态心智状态引擎:驱动力、念头池、疲惫、睡眠与意图。
A minimalist MVP demonstrating a simple yet profound insight: aligning AI memory with human episodic memory granularity. Shows how this single principle enables simple methods to rival complex memory frameworks for conversational tasks.