Agent frameworks & infrastructure
Agent memory & context
4,032 agents · most starred first
Agent memory & context, page 4 of 41
Local personal memory for LLM agents
A context graph which is based on confidence-aware belief that drives more determinstic reasoning in long-horizon agents.
A context graph which is based on confidence-aware belief that drives more determinstic reasoning in long-horizon agents.
Local-first Memory OS for personal AI assistants with L0-L3 memory, Wiki++ knowledge, skill routing, and TokenLess context compression.
Persistent memory for Claude Code — identity, context, and continuity across sessions
Portable agent setup through one INSTALL.md: minimal project instructions, verified workflows, native memory reuse, and reversible configuration.
IJFW — It Just F*cking Works. Ferrox Labs' local-first infrastructure for AI coding agents: shared memory, smart routing, multi-AI cross-audits, disciplined workflow.
On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.
Drop-in memory harness for AI agents — 3-tier memory, compaction tree, hybrid search. One command to set up. Works with Claude Code and OpenClaw.
ELF provides persistent memory, pattern tracking, and multi-agent coordination for Claude Code sessions without the need for an api key
A menu bar app that keeps a written record of what you worked on.
Local-first memory layer for OpenClaw, Codex App, and Codex CLI: capture, recall, dedupe, and native sync.
[COLM 2025] Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
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。
🧠 Production-grade memory sidecar for AI agents — gbrain + Hindsight + 3-tier recall. Agent-agnostic, battle-tested. | 生产级外挂记忆系统,兼容Hermes/Claude/Cursor等任意AI智能体
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.
Git-native memory for coding agents. Repo memory before the diff.
Carry the context forward
Persistent local memory for AI coding agents. Preserve decisions and project context across sessions, compaction, and tools.
[ICML'26] Scaling Long-Horizon LLM Agent via Context-Folding
Agentic memory infra for AI agents
Local-first AI agent memory — one command, works offline, no account needed. Give your Claude Code, Cursor, Windsurf, OpenClaw agent persistent memory. Markdown storage, hybrid search (FTS5 + embedding), MCP protocol, Web dashboard.
A pure-Python context management layer for LLM systems — retrieval, re-ranking, memory decay, and token-budget enforcement in one pipeline.
Fast, privacy-first desktop & web UI for self-hosted Honcho — browse memories, peers, sessions, conclusions, and chat with memory context.
Context intelligence layer for LLM agents: persistent memory with write-time dedup, sensitivity tagging, conflict detection, and hierarchical decay. ~12ms. No LLM calls. MIT.
🦀 AI Agent Engine with Long-Term Memory and Self-Learning & One-Click OpenClaw Migration
Give git-like & traceable memory to OpenClaw and any coding agents. By https://memov.ai/ aka Entire CLI for every coding agents by MCP. Self-evolution for skills.
Grov automatically captures the context from your private AI sessions and syncs it to a shared team memory. It auto injects relevant memories across developers and future sessions to save tokens and time spent on tasks.
Context Engineering: Build Consistent, Accurate, Predictable AI Systems
Make every AI agent you use smarter. Persistent memory with SQLite FTS5, MCP server, Obsidian sync, and self-learning intelligence pipeline.
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.
OKF (Open Knowledge Format): Durable, structured memory for AI agents. Author, validate, consume, and maintain portable knowledge bundles through an ecosystem of Skills, MCP, an interactive graph, TUI, CLI, Docker, and a Claude Code plugin. 100% local.
面向 AI Agent 的高并发、低延迟上下文治理与 Prompt Cache 守护网关 (Tree-sitter AST / Tool Delta / 50%~80% Token 削减)
Ultimate zero-dependency compound knowledge system for AI agents. Auto-extract, classify, search, and maintain memory in plain Markdown.
真正记得住你、认识你、随你成长的 AI 长效认知记忆引擎 Long-term Cognitive Memory Engine for LLM Agents
LLM agent 的有界自纠错长期记忆层:把连续、含矛盾的项目交互日志蒸馏成有界、可自更新的记忆库。Bounded, self-correcting long-term memory for LLM agents — candidate pool + value dynamics + tension adjudication + causal-replay evals.
How to turn your Second Brain into a living research memory that your agents maintain. Workshop with slides, video and code.
Local-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history, MCP, and a self-hosted WebUI.
The filesystem for AI agents
Built for Claude Code but works in any agent that supports skills, easily recall what you discussed with your favorite coding agents, what decisions you made, and where you left off so you can pick up where you left off as easily as asking "where did we leave off on XYZ..."
A memory framework for Large Language Models and Agents.
Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, and fades stale memories via temporal decay, written in Rust (Apache-2.0) as a library, MCP server, or HTTP cluster.
Persistent cross-session memory for Claude & AI agents. Self-host on Redis/Valkey, or use the managed SaaS at recallmcp.com.
ChatIndex: Tree indexing and retrieval for long conversational memory
Production-grade memory layer for AI agents with durable multi-tenant memory, semantic recall, async distillation, and SDK/Gateway integration.
Source-backed feature comparison of memory systems for AI coding agents. No affiliation, no marketing — just facts from public docs.
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.
PRD-Led Context Engineering — Memory as Infrastructure. An ontology layer for product teams building products that solve real problems — with AI agents that remember. Gated PRD, typed IDs, markdown knowledge graph, Claude Code skills & hooks.
Shared Memory That Never Forgets — persistent memory for AI agents with Space-based sharing across agents and teams. Plugins for OpenCode, Claude Code, OpenClaw, MCP Server.
Persistent Intelligence Infrastructure for AI Agents
Lossless long-term memory for a personal AI: never summarize, keep every line, put a timestamp on everything.
🐾 给AI加长期记忆的轻量网关 / A lightweight gateway that adds long-term memory to any LLM
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.
AKB — Agent Knowledgebase. Organizational memory for AI agents: vault-scoped docs / tables / files unified by URI graph, served over MCP.
Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.
GPT-3 Chatbot with Long and Short Term Memory and advanced logic built in javascript with openai API - short and long memory, KYC, embeddings, openai, database, flexible, gpt-3.5-turbo, react
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.
One install. Shared memory, smart routing, disciplined workflow, multi-AI audits -- across every AI coding agent. No BS.
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.
Auditable, local-first memory for AI agents in one SQLite file. MCP server for Claude Code, Cursor and Codex. npm: mnemosy-ai
A chatbot 🤖 which remembers 🧠 using 🦜 LangChain 🔗 OpenAI | Streamlit | DataButton
Shared Memory Storage for Multi-Agent Systems
Persistent memory plugin for OpenCode. Obsidian-style knowledge base that survives across sessions
For Claude.
A context harness for AI agents: all your scattered context — code, memory, docs, databases, SaaS — in one searchable, browsable, file-like interface.
🧠 LLM-Driven Intelligent Memory & Context Management System (AI记忆管理与智能上下文感知平台) AI记忆管理平台 | 智能上下文感知 | RAG检索增强生成 | 向量检索引擎
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.
A mind built around a local 27B model on one Mac: lasting memory, affect and drives, offline Wikipedia, voice and screen, procedures she writes and keeps, and a receipt for every consequential action. Claims are preregistered and failures stay in the record.
One workspace all your AI agents can read and write. Encrypted client-side, model-agnostic, gone 24h after the last edit.
The local-first intelligence layer that gives AI agents durable continuity, explainable retrieval, portable context, and verified learning across harnesses.
Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local project files.
Query-aware context compression for LLMs and coding agents. Cut ~65% of input tokens.
CTX - Context Runtime Engine for Coding Agents
Harnessing the Memory Power of the Camelids
Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang, vLLM, llama.cpp, OpenClaw, RAG, and Agentic AI.
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.
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.
Zettelkasten-based persistent memory for AI coding agents. Works with Claude Code, Cursor, VS Code Copilot, Codex, Windsurf & any MCP client. No vector DB — just markdown + git sync.
Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.
Git-native context control plane for AI coding agents
A lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.
给 AstrBot 的可落地 AI 记忆与生活层:五类记忆、混合检索、遗忘治理、情绪边界、自主生活循环。不覆盖人格。
Nemp - The memory plugin for Claude Code that remembers everything.
Human memory, for agents. Scalable, private, personal knowledge base for any LLM provider.
Self improving agents through iterations
Memory that remembers the story not just the facts. File System Memory and Three layer sentence graph for AI agents -> Facts, Episodes, raw Sentences. One DB. Zero config.
A portable memory layer that makes AI agents reliable across apps and sessions. Persistent, verifiable, and fully under your control.
A minimalist implementation of Agentic Memory architecture is DSPy
Trustworthy memory for DeepSeek Harness — 4-state trust machine, evidence chains, audited injections. Zero servers, just Markdown.
GateMem: a benchmark and evaluation toolkit for memory governance in multi-principal shared-memory LLM agents.
Budget-aware context compiler for coding agents - scan, grade, spark-test and pour a hard-budget context pack
Your AI brain, externalized. It remembers everything you do, then becomes whatever role you need. Same skeleton can run as your chief of staff, lawyer, PM, or investigator. Plain markdown. Built on Claude Code.
Memory that remembers the story not just the facts. File System Memory and Three layer sentence graph for AI agents -> Facts, Episodes, raw Sentences. One DB. Zero config.
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.
Claude Code 的記憶系統 | A memory system built with hooks + markdown. Zero dependencies.
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.
Your AI never starts over. Lore keeps sessions coherent for days and millions of tokens — no lossy summary that wipes your file paths and decisions — and turns every session into compounding memory across tools, providers, and (soon) your team. No context files. No workflow changes.
🦞 A Digital Life Embryo for your MCP Client. An intelligent micro-kernel with Nociception, Memory Apoptosis, and a Curiosity Drive. Evolve your AI Copilot into a sentient partner for Claude Desktop, Qoderwork, Cursor, and beyond.
Personal Context Manager for Claude Code. Your life in walnuts.
Official implementation of paper "ACON: Optimizing Context Compression for Long-horizon LLM Agents"