Agent Runtime & Deployment
Hosting agents in production and keeping their state. As of 2026-11-21, 1,461 indexed products match this category (487 with full profiles); 614 were published in the last 90 days, against 394 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, claude-mem leads, holding 9% of the stars of the 1,170 products here with their own repository. The most common form is MCP servers (86% of indexed products).
CategorySegment label: Lagging the catalogue DER
Segment statistics
Whole catalogue (all 1,461 indexed products, not only profiled ones). Calculated 2026-11-21.
Lagging the catalogue. Mid-sized for its level, with launches growing more slowly than the catalogue’s. Size is ranked against the other category nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).
Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.036, attention is spread as if across about 28 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is unconcentrated. Stars measure attention, not usage or quality.
Which product forms serve it
The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 1,258 | 86.1% | 300 |
| Infrastructure | 70 | 4.8% | 70 |
| Frameworks | 35 | 2.4% | 35 |
| Agent skills | 30 | 2.1% | 28 |
| Plugins | 15 | 1.0% | 10 |
| Libraries | 15 | 1.0% | 14 |
| Agent projects | 15 | 1.0% | 14 |
| Rules packs | 11 | 0.75% | 4 |
| SaaS products | 3 | 0.21% | 3 |
| IDE extensions | 3 | 0.21% | 3 |
| Platforms | 2 | 0.14% | 2 |
| AI APIs | 2 | 0.14% | 2 |
| Agent SDKs | 1 | 0.07% | 1 |
| Protocols & standards | 1 | 0.07% | 1 |
2 subcategories
Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.
| Subcategory | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Memory & StatePersisting agent memory, sessions and checkpoints. | 850 | 345 | 320 | Crowded, slowing |
| Agent DeploymentRunning agents and MCP servers as hosted services. | 631 | 154 | 300 | Lagging the catalogue |
Top 40 products by GitHub stars
Search the directoryProfiled products only (487 of 1,461), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | 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 | Agent skill | thedotmack | 119k | today | Apache-2.0 | ||
| 2 | OpenHandsOpen-source platform for AI coding agents comprising a Python Software Agent SDK and Agent Server, the Agent Canvas browser client, and a managed OpenHands Cloud with GitHub, GitLab, Slack and Jira integrations. | Platform | OpenHands (All Hands AI) | 94k | today | MIT | ||
| 3 | MiroFishA Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物 | Infrastructure | 666ghj | 86k | 1mo ago | AGPL-3.0 | ||
| 4 | claude-flowAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev. | MCP server | ruvnet | 82k | today | MIT | ||
| 5 | DaytonaSandbox infrastructure that starts isolated environments for running AI-generated code quickly, with SDKs for files, git and processes. | Infrastructure | Daytona | 71k | 4mo ago | — | ||
| 6 | 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. | Library | Mem0 | 69k | 3d ago | Apache-2.0 | ||
| 7 | 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 | Agent project | bojieli | 59k | 1mo ago | Apache-2.0 | ||
| 8 | LangGraphLow-level orchestration framework that models agents as stateful graphs with checkpointing, human-in-the-loop interrupts and durable execution. | Framework | LangChain | 45k | today | MIT | ||
| 9 | OpenVikingSelf-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. | Infrastructure | volcengine | 43k | today | AGPL-3.0 | ||
| 10 | 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. | Infrastructure | pingcap | 41k | today | Apache-2.0 | ||
| 11 | CogneeMemory engine that turns documents and conversations into a knowledge graph plus vector index, exposed through add/cognify/search operations. | Library | topoteretes | 33k | 1d ago | Apache-2.0 | ||
| 12 | GraphitiPython library for building temporally aware knowledge graphs from episodes of data, with hybrid semantic, keyword and graph search for agent memory. | Library | Zep AI | 33k | 1d ago | Apache-2.0 | ||
| 13 | SupermemoryMemory and context API that ingests content and user interactions and serves relevant memories to LLM applications; also has a consumer app. | API | Supermemory | 32k | today | MIT | ||
| 14 | LettaPlatform for stateful agents with self-editing memory blocks, archival memory and a server that persists agents; originated as MemGPT. | Framework | Letta | 26k | 1mo ago | Apache-2.0 | ||
| 15 | AG-UI (Agent-User Interaction Protocol)Event-based protocol that streams agent state, messages, tool calls and UI updates between an agent backend and a frontend application. | Protocol | CopilotKit | 21k | today | MIT | ||
| 16 | XERJThe search engine for AI agents: cited answers from your local code, docs, specs and logs. | MCP server | xerj-org | 19k | today | Apache-2.0 | ||
| 17 | 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. | Infrastructure | MemoriLabs | 18k | 1mo ago | — | ||
| 18 | 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. | Infrastructure | memvid | 17k | 4mo ago | Apache-2.0 | ||
| 19 | waoowaoo首家工业级全流程 AI 影视生产平台。Industry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows. | Agent project | waooAI | 15k | 2mo ago | — | ||
| 20 | E2BFirecracker microVM sandboxes that agents use to run untrusted code, with SDKs for files, processes and a code interpreter. | Infrastructure | E2B | 15k | today | Apache-2.0 | ||
| 21 | semanticaGraph-Native Semantic Layer for Trustworthy Enterprise AI | Infrastructure | semantica-agi | 15k | 4d ago | MIT | ||
| 22 | EverOSOne portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows. | Infrastructure | EverMind-AI | 14k | 1d ago | Apache-2.0 | ||
| 23 | MCP TypeScript SDKOfficial TypeScript SDK for MCP clients and servers with stdio and Streamable HTTP transports. | SDK | Agentic AI Foundation (Linux Foundation) | 14k | 2d ago | MIT AND Apache-2.0 | ||
| 24 | 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. | Agent project | MemTensor | 12k | 1d ago | Apache-2.0 | ||
| 25 | bishengBISHENG is an open-source enterprise Agent platform for building, deploying, and managing AI applications. It combines AI agents, workflows, RAG and knowledge management, desktop agent integration, and vibecoding app hosting with unified model management, evaluation, observability, access control, and enterprise administration. | Infrastructure | dataelement | 12k | 1d ago | Apache-2.0 | ||
| 26 | astridAstrid is a portable, capability-secure operating system for composable software. | Agent project | astrid-runtime | 10k | today | Apache-2.0 | ||
| 27 | sphereA Web3 wallet and agent platform for the Unicity network - crypto wallet, DMs, group chat, and marketplace. | Agent project | unicity-sphere | 9.6k | 2d ago | — | ||
| 28 | 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. | Agent skill | Gentleman-Programming | 9.4k | today | MIT | ||
| 29 | utopiaWorld's first open-source enterprise world model. | Infrastructure | deeplethe | 8.7k | today | Apache-2.0 | ||
| 30 | HonchoMemory that reasons: continual learning for stateful agents. Better context, fewer tokens. | MCP server | plastic-labs | 8.2k | today | AGPL-3.0 | ||
| 31 | 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. | MCP server | osaurus-ai | 8.2k | today | MIT | ||
| 32 | Yuxi可私有部署的多租户知识智能体平台:统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows. | Agent project | xerrors | 7.7k | 1d ago | MIT | ||
| 33 | open-multi-agentSelf-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it. | Framework | open-multi-agent | 7.1k | 4d ago | MIT | ||
| 34 | agents-cliThe CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud. | Agent project | 6.4k | 4d ago | Apache-2.0 | |||
| 35 | obsidian-mindA self-organizing Obsidian vault that gives AI coding agents persistent memory. | Agent project | breferrari | 5.6k | 1mo ago | MIT | ||
| 36 | 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. | Agent skill | eugeniughelbur | 5.4k | 3d ago | MIT | ||
| 37 | awesome-harness-engineeringAwesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration. | Agent project | ai-boost | 5.2k | today | — | ||
| 38 | nonoagent runtime security - zero trust, zero setup, zero latency agent sandboxing | Agent project | nolabs-ai | 5.1k | 1d ago | Apache-2.0 | ||
| 39 | OB1Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat channel — any AI plugs in. No middleware, no SaaS. | Agent project | NateBJones-Projects | 4.8k | today | — | ||
| 40 | LongMemoryLocal persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc. | Agent project | CaviraOSS | 4.6k | 11d ago | Apache-2.0 |
Most common integrations
Third-party services named by products in this node, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| PostgreSQL | 17 | 1.2% |
| Obsidian | 16 | 1.1% |
| 15 | 1.0% | |
| Solana | 7 | 0.5% |
| YouTube | 6 | 0.4% |
| GitHub | 5 | 0.3% |
| Google Ads | 5 | 0.3% |
| Google Analytics | 4 | 0.3% |
| Google Cloud | 4 | 0.3% |
| Google Maps | 4 | 0.3% |
| SAP | 4 | 0.3% |
| Slack | 4 | 0.3% |
| AWS | 3 | 0.2% |
| Google Calendar | 3 | 0.2% |
| Redis | 3 | 0.2% |
Launches per month
New Agent Runtime & Deployment products per monthSRC
Whole catalogue, by publication month, 2024-12 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-12 | 3 |
| 2025-02 | 3 |
| 2025-03 | 3 |
| 2025-04 | 3 |
| 2025-05 | 6 |
| 2025-06 | 5 |
| 2025-07 | 5 |
| 2025-08 | 6 |
| 2025-09 | 10 |
| 2025-10 | 14 |
| 2025-11 | 7 |
| 2025-12 | 9 |
| 2026-01 | 17 |
| 2026-02 | 43 |
| 2026-03 | 88 |
| 2026-04 | 84 |
| 2026-05 | 94 |
| 2026-06 | 101 |
| 2026-07 | 181 |
| 2026-08 | 152 |
| 2026-09 | 167 |
| 2026-10 | 233 |
| 2026-11 | 164 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
| Opportunity | Competition | Confidence | Score |
|---|---|---|---|
| Coverage gap: User Preference MemoryUser Preference Memory | Medium | Low | 61.0 |
| Coverage gap: Session PersistenceSession Persistence | High | Low | 60.0 |
| Coverage gap: Background AgentsBackground Agents | Medium | Low | 59.1 |
| Coverage gap: Agent HostingAgent Hosting | Medium | Low | 57.5 |
Limits of these numbers
- Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
- About half of the catalogue matches no node at all, so absolute counts understate every category.
- Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
- Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.
Page data last updated .