Agent Memory
Persistent memory that lets agents remember across sessions. As of 2026-11-21, 804 indexed products offer it (316 with full profiles), in 11 forms: 678 MCP servers, 55 Infrastructure, 18 Agent skills, 15 Frameworks. 312 were published in the last 90 days, against 223 in the 90 days before. claude-mem has the most GitHub stars, 13% of the total across 699 products with their own repository.
CapabilitySegment label: Crowded, slowing DER
Available as
All in the directoryProfiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.
MCP servers 678 indexed · 203 profiled
Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | claude-flowAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev. | ruvnet | 82k | today | ||
| 2 | XERJThe search engine for AI agents: cited answers from your local code, docs, specs and logs. | xerj-org | 19k | today | ||
| 3 | HonchoMemory that reasons: continual learning for stateful agents. Better context, fewer tokens. | plastic-labs | 8.2k | today | ||
| 4 | osaurusOwn your AI. The open-source agent harness for macOS. Run local or cloud models with persistent memory, skills, tools, and autonomous execution. Built in Swift. | osaurus-ai | 8.2k | today | ||
| 5 | obsidian-wikiMemory for agents in a markdown vault you own: search, read, write, recap, context packs. | Ar9av | 3.8k | 1d ago | ||
| 6 | aoci-codeA persistent, Git-versioned map of your whole codebase and database schema that coding agents read before they touch anything. Local-first MCP server + CLI in Go: a governed repository index of code knowledge that gives Claude Code, Codex, Cursor, and opencode long-term context, memory, and code intelligence. | aoci-spec | 2.8k | 1d ago | ||
| 7 | mcp-memory-serviceOpen-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation. | doobidoo | 2.1k | 1d ago | ||
| 8 | IWE (iwe.md)Markdown knowledge base as agent memory. Runs against the notes directory it is started in. | iwe-org | 1.8k | today | ||
| 9 | deja-vu — Coding Agent Memory & Session SearchLocal memory & session search across forty-nine coding agents: Claude Code, Codex, Cursor. | vshulcz | 1.6k | today | ||
| 10 | deja-vuLocal memory & session search across forty-nine coding agents: Claude Code, Codex, Cursor. | vshulcz | 1.6k | today |
Infrastructure 55 indexed · 55 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | MiroFishA Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物 | 666ghj | 86k | 1mo ago | ||
| 2 | OpenVikingSelf-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. | volcengine | 43k | today | ||
| 3 | tidbTiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling. | pingcap | 41k | today | ||
| 4 | MemoriMemori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises. | MemoriLabs | 18k | 1mo ago | ||
| 5 | memvidMemory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory. | memvid | 17k | 4mo ago | ||
| 6 | semanticaGraph-Native Semantic Layer for Trustworthy Enterprise AI | semantica-agi | 15k | 4d ago | ||
| 7 | EverOSOne portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows. | EverMind-AI | 14k | 1d ago | ||
| 8 | utopiaWorld's first open-source enterprise world model. | deeplethe | 8.7k | today | ||
| 9 | letta-codeAgents that self-improve with experience | letta-ai | 3.9k | today | ||
| 10 | agentic-context-engine🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai | kayba-ai | 2.6k | 1mo ago |
Agent skills 18 indexed · 16 profiled
Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | claude-memPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More | thedotmack | 119k | today | ||
| 2 | gentle-aiGentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in. | Gentleman-Programming | 9.4k | today | ||
| 3 | obsidian-second-brainPersistent memory for Claude Code, Codex and 6 other AI agents, stored as plain markdown in your Obsidian vault. New: Crew, one shared logbook so Claude Code, Codex, Cursor and Grok Bot know what each other did. 48 commands: semantic search, self-rewriting notes, key-less research, scheduled agents. | eugeniughelbur | 5.4k | 2d ago | ||
| 4 | gentle-shellGentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live tasks, Git diffs, persistent memory, and permission controls into one terminal interface. Powered by Gentle AI and Organic Driven Development (ODD). | Gentleman-Programming | 2.9k | today | ||
| 5 | qualitylayerPlan, implement and verify software with your favorite coding agents. Work in the App or browser, or in your own terminal, IDE or agent app. | maxritter | 2.2k | today | ||
| 6 | sno-stationWhen Claude Code hits its usage limit, Codex picks the task up from the same memory. Sno Station puts Codex, Claude Code, Cursor, Hermes Agent and OpenClaw on one squad: they hand work to each other and review each other's code. Open source, runs on your computer. | sno-ai | 1.0k | today | ||
| 7 | AgentChatAgentChat 是一个基于 LLM 的智能体交流平台,内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作,Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术,实现高效的知识检索与工具调用,使用 FastAPI 构建高性能后端服务。 | Shy2593666979 | 935 | 1mo ago | ||
| 8 | compass-skills司南:个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents | dongshuyan | 772 | today | ||
| 9 | ai-memory-vaultGive your AI a real, persistent memory. The open-source system plus templates that turn an Obsidian vault into your AI's working memory. No vector database, just markdown. | jaredrhod | 742 | 2mo ago | ||
| 10 | claude-brainGive Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single .mv2 file you can git commit, scp, or share. Native Rust core with sub-ms operations. | memvid | 585 | 10mo ago |
Frameworks 15 indexed · 15 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | kungfuYour agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and your own execution surface. | kungfu-systems | 4.5k | today | ||
| 2 | magic-contextUnbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit. | cortexkit | 2.5k | today | ||
| 3 | ouroborosOuroboros — self-creating AI agent. Born Feb 16, 2026. | razzant | 1.7k | today | ||
| 4 | Agentlas-OSThe Open-Source AI Agent OS inspired by OpenAI Dots, Meta Muse, OpenClaw, Hermes & Mem0. Autonomous 3-tier headhunting, Receipt & Verifier loops, scoped memory, and BYOM for Claude Code, Codex & Cursor. | agentlas-ai | 1.4k | today | ||
| 5 | mnemonLLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime. | mnemon-dev | 732 | 2d ago | ||
| 6 | agentosTypeScript AI agent framework: cognitive memory, dynamic personalities, emergent behaviors and self-building designs | framerslab | 691 | today | ||
| 7 | Deuz-SDKTypeScript AI SDK and agent framework with zero dependencies. Build production AI agents and multi-agent swarms: durable execution, long-term memory, hybrid RAG, MCP client/server, A2A, human-in-the-loop approvals, CodeAct sandboxes, realtime voice. One streaming API, 29 providers: Claude, GPT, Gemini, Grok, DeepSeek, Ollama. Node, Bun, Deno, edge. | Deuz-AI | 508 | 1mo ago | ||
| 8 | flowcraftProduction-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline. | GizClaw | 410 | 1d ago | ||
| 9 | agenticaOne person, a team of agents: CLI, Web, Desktop & Python SDK with multi-session collaboration, persistent memory, and self-evolving skills. 一个人,一支 Agent 团队:支持多终端协作、持久记忆与技能自进化的 AI Agent 框架。 | shibing624 | 366 | today | ||
| 10 | agent-systems-handbookAgent Systems Handbook by Prompthon — A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend focus: Gemini Interactions API and managed agents, emerging agent runtimes, and production AI workflow patterns. | Prompthon-IO | 315 | 1mo ago |
Rules packs 11 indexed · 4 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | cursorkleosrMake AI Development Feel Natural in Cursor | kleosr | 325 | 1mo ago | ||
| 2 | devcontextDevContext is a cutting-edge Model Context Protocol (MCP) server designed to provide developers with continuous, project-centric context awareness. Unlike traditional context systems, DevContext continuously learns from and adapts to your development patterns and delivers highly relevant context providing a deeper understanding of your codebase. | aiurda | 49 | 1y ago | ||
| 3 | cursor10xCursor10x is a comprehensive suite of tools that enhances the A.I. agent's capabilities within the Cursor IDE, providing persistent memory across sessions, standardized task management, and enforced best practices through cursor rules. | aiurda | 26 | 1y ago | ||
| 4 | aria-knowledgeApplied reasoning, persistent agent memory, context engineering, and human-governed trust for AI coding agents — Claude Code, Claude Cowork, Codex, Cursor, Antigravity. Compatible with Obsidian. | mikeprasad | 19 | 3d ago |
Agent projects 9 indexed · 8 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | ai-agent-book《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码 | bojieli | 59k | 1mo ago | ||
| 2 | MemOSSelf-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support. | MemTensor | 12k | 1d ago | ||
| 3 | obsidian-mindA self-organizing Obsidian vault that gives AI coding agents persistent memory. | breferrari | 5.6k | 1mo ago | ||
| 4 | awesome-harness-engineeringAwesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration. | ai-boost | 5.2k | today | ||
| 5 | OB1Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat channel — any AI plugs in. No middleware, no SaaS. | NateBJones-Projects | 4.8k | today | ||
| 6 | LongMemoryLocal persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc. | CaviraOSS | 4.6k | 11d ago | ||
| 7 | agent-memoryLong-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key. | tigerless-labs | 4.3k | 9d ago | ||
| 8 | claude-code-memory-setupUp to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify. Persistent memory, codebase knowledge graphs, and chat import pipeline. 🇧🇷 PT-BR included. | lucasrosati | 1.1k | 1mo ago |
Plugins 9 indexed · 6 profiled
6 of these are Claude plugins, which Claude Code documents (protocol-level). DER
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | memsearchA persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus. | zilliztech | 2.9k | 2d ago | ||
| 2 | claude-smartTurns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode. | ReflexioAI | 796 | today | ||
| 3 | rememberContinuous memory for Claude Code. Extracts, summarizes, and compresses conversations into tiered daily logs. Claude remembers what you did yesterday. | digital-process-tools | 215 | today | ||
| 4 | total-recallPersistent memory plugin for Claude Code. Tiered memory system with write gates, correction propagation, and slash commands. | davegoldblatt | 203 | 9mo ago | ||
| 5 | altk-evolveSelf improving agents through iterations | AgentToolkit | 142 | 1d ago | ||
| 6 | synappticJust like the elite potential of a high-drive Belgian Malinois, an AI system's raw capabilities are wasted when deployed without proper structure. The technological value is no longer found in creating the drive, but in mastering the leash. Synapptic gives your AI Assistant persistent memory that updates in real time, saving you tokens and time. | appcuarium | 23 | 15d ago |
Libraries 6 indexed · 6 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Mem0Memory layer that extracts, stores and retrieves long-term facts about users and sessions for agents, available as an open-source library or hosted platform. | Mem0 | 69k | 3d ago | ||
| 2 | CogneeMemory engine that turns documents and conversations into a knowledge graph plus vector index, exposed through add/cognify/search operations. | topoteretes | 33k | today | ||
| 3 | GraphitiPython library for building temporally aware knowledge graphs from episodes of data, with hybrid semantic, keyword and graph search for agent memory. | Zep AI | 33k | 1d ago | ||
| 4 | LangMemLibrary of tools and background processes for extracting, consolidating and searching long-term agent memory on LangGraph stores. | LangChain | 1.8k | 5d ago | ||
| 5 | sample-agentic-frameworks-on-awsBuild Agentic AI solutions on AWS, using latest OSS Agentic Frameworks. | aws-samples | 267 | 5mo ago | ||
| 6 | superqodeThe harness interoperability layer for coding agent. Agent to Agent connect over ACP, A2A and UHP | SuperagenticAI | 67 | today |
AI APIs 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | SupermemoryMemory and context API that ingests content and user interactions and serves relevant memories to LLM applications; also has a consumer app. | Supermemory | 32k | today |
IDE extensions 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | DamoclesAn AI coding agent that runs as a standalone desktop app for Windows, macOS and Linux, and as a VS Code extension. Chat with Claude, GPT and other models, approve diffs, rewind checkpoints, and use persistent memory, subagents, teams and MCP, powered by the Pi agent runtime. | Aizenvolt | 82 | today |
Platforms 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)Google Cloud's platform for building, deploying, governing and optimizing agents, including Agent Studio (low-code), the Agent Development Kit, Agent Garden templates, Agent Runtime, Memory Bank, Sandbox, Registry, Gateway and evaluation tooling, with access to Gemini and third-party models. | Google Cloud | — | — |
Which platforms these forms can reach
All platformsProtocol-level: the platform documents support for the standard. No specific pairing has been tested.
MCP servers 678 indexed here
36 platforms document MCP support CUR.
ContinueOpenCodeClaude CodeCodexGemini CLIZedOpenHandsClineWarpgooseQwen CodeBolt (bolt.new)KiroAmazon Bedrock AgentCoreAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)Augment CodeChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJetBrains AI AssistantJunieLovableMicrosoft Copilot StudioReplit AgentTabninev0
Agent skills 18 indexed here
26 platforms document Agent Skills support CUR.
OpenClawOpenCodeClaude CodeCodexGemini CLIOpenHandsWarpgooseBolt (bolt.new)KiroAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)ChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJunieReplit AgentTabnine
Platforms publishers name
| Platform | Profiled products naming it |
|---|---|
| Claude Code | 47 |
| Codex | 32 |
| Cursor | 21 |
| OpenClaw | 11 |
| OpenCode | 10 |
| Claude Desktop | 2 |
| Google Antigravity | 2 |
| ChatGPT | 2 |
| Gemini CLI | 2 |
| GitHub Copilot | 1 |
Integrations most often paired
Third-party services named by products with this capability, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| Obsidian | 14 | 1.7% |
| PostgreSQL | 13 | 1.6% |
| GitHub | 3 | 0.4% |
| Docker | 2 | 0.2% |
| Redis | 2 | 0.2% |
| AWS | 1 | 0.1% |
| Chroma | 1 | 0.1% |
| Cloudflare | 1 | 0.1% |
| Discord | 1 | 0.1% |
| Elasticsearch | 1 | 0.1% |
| Kubernetes | 1 | 0.1% |
| 1 | 0.1% |
Keywords that trigger this capability
Matched as whole words, ignoring case, in a product's name, description and repository topics.
| Keyword | Products matched |
|---|---|
| agent memory | 474 |
| long-term memory | 77 |
| persistent memory | 202 |
| memory layer | 29 |
| mem0 | 15 |
| memory bank | 4 |
| conversation memory | 3 |
Segment statistics
Whole catalogue (804 indexed products). Calculated 2026-11-21.
Crowded, slowing. Among the largest fifth of capabilities, but its launches grew more slowly than the catalogue’s. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.054 means stars are spread as if across about 19 equally popular projects — unconcentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.
Limits
- Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
- Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
- Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
- Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.
Page data last updated .