AgentSidekick

Agent Infrastructure

The frameworks, runtimes, models, security and observability layers agents run on. As of 2026-11-21, 8,733 indexed products match this ecosystem (2,364 with full profiles); 4,234 were published in the last 90 days, against 1,923 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, MarkItDown leads, holding 3% of the stars of the 5,705 products here with their own repository. The most common form is MCP servers (83% of indexed products).

EcosystemSegment label: Crowded, slowing DER

Segment statistics

Whole catalogue (all 8,733 indexed products, not only profiled ones). Calculated 2026-11-21.

8,733DERIndexed products2,364 with full profiles
4,234DERLaunched, last 90 days1,923 in the 90 days before
33DERMomentum vs catalogue50 = same pace as the catalogue
3%DERLargest project's share of starsAcross 5,705 products with their own repository
0.007DERConcentration (HHI)About 142 equal-sized projects’ worth; unconcentrated
2SRCMedian starsPer product with its own repository
59%DEROpen sourceMarked open source; unknown counts as not

Crowded, slowing. Among the largest fifth of nodes at its level, but its launches grew more slowly than the catalogue’s. Size is ranked against the other ecosystem 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 0.007, attention is spread as if across about 142 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.

Products in Agent Infrastructure by product type, as of 2026-11-21
Product type IndexedShareWith a profile
MCP servers7,27583.3%1,044
Agent skills3333.8%329
Infrastructure2883.3%282
Frameworks2422.8%235
Plugins1992.3%156
Libraries1071.2%96
Rules packs951.1%31
Agent projects931.1%89
IDE extensions280.32%29
SaaS products180.21%18
Developer tools150.17%15
AI APIs130.15%13
Agent SDKs90.10%9
Protocols & standards70.08%7
Platforms70.08%7
Automation platforms40.05%4

6 categories

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.

CategoryIndexed ProfiledNew, 90 daysLabel
Agent CommerceHow agents pay, bill, meter usage and sell through marketplaces.3,6211992,284Crowded
Agent SecurityIdentity, access, governance and threat protection for agents.1,481469650Lagging the catalogue
Agent Runtime & DeploymentHosting agents in production and keeping their state.1,461487614Lagging the catalogue
Agent Frameworks & OrchestrationLibraries and platforms for building and coordinating agents.1,192735311Lagging the catalogue
Models & GatewaysAccessing, routing, serving and tuning language models.1,115601343Lagging the catalogue
Agent ObservabilitySeeing, measuring and evaluating what agents do.951440367Lagging the catalogue

Top 40 products by GitHub stars

Search the directory

Profiled products only (2,364 of 8,733), 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.

Agent Infrastructure: top profiled products by GitHub stars, 2026-11-21
#ProductTypePublisherCapabilities GitHub stars Last push LicenceSave and compare
1MarkItDownPython utility that converts PDF, Office, HTML, images and audio files into Markdown for LLM consumption.Librarymicrosoft197k14d agoMIT
2ponytailMakes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.Agent skillDietrichGebert196k23d agoMIT
3DifyPlatform for building LLM apps and agent workflows visually with RAG pipelines, model management and app publishing.Automation platformLangGenius162ktodayLicenseRef-Dify-Open-Source-License
4LangflowVisual builder for agent and RAG flows using drag-and-drop components, with flows deployable as APIs or MCP servers.Automation platformDataStax157ktodayMIT
5LangChainFramework of model, tool, retriever and agent abstractions with hundreds of provider integrations; its agent API now runs on LangGraph.FrameworkLangChain150ktodayMIT
6claude-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 + MoreAgent skillthedotmack119ktodayApache-2.0
7labelhead-artist-momentumTrending hip-hop artist momentum scores across four cultural dimensions.MCP serverIncorporatedPartners116ktodayMIT
8RAGFlowSelf-hostable RAG engine with deep document parsing, template-based chunking, citations and an agent builder.Frameworkinfiniflow94k1d agoApache-2.0
9OpenHandsOpen-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.PlatformOpenHands (All Hands AI)94ktodayMIT
10OmniRouteNever stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributorsAgent projectcheaper-inference89ktodayMIT
11MiroFishA Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物Infrastructure666ghj86k1mo agoAGPL-3.0
12dsh-our-free-model在 dsh 里装上这个插件即可,无需登录、注册或填 API Key,就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型——完全免费,不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, DeepSeek V4.1 Flash and Kimi K3 among them. Completely free, with no usage cap.Agent projectEbony-Vinyl83ktoday—
13claude-flowAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.MCP serverruvnet82ktodayMIT
14ai-agents-for-beginners18 Lessons to Get Started Building AI AgentsAgent projectmicrosoft81k4d agoMIT
15Prompt-Engineering-Guide🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.Agent projectdair-ai80k8mo agoMIT
16system_prompts_leaksLeaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, OpenAI Codex, Google Antigravity, xAI Grok, Meta Muse, Moonshot Kimi, Alibaba Qwen, Z.ai GLM ZCode, MiniMax, Cursor, Perplexity, DeepSeek and 30+ others. Updated daily.Agent projectasgeirtj72ktodayCC0-1.0
17humanizerAgent skill that removes signs of AI-generated writing from textAgent skillblader72k2d agoMIT
18DaytonaSandbox infrastructure that starts isolated environments for running AI-generated code quickly, with SDKs for files, git and processes.InfrastructureDaytona71k4mo ago—
19Mem0Memory layer that extracts, stores and retrieves long-term facts about users and sessions for agents, available as an open-source library or hosted platform.LibraryMem069k3d agoApache-2.0
20anything-llmStop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience Agent projectMintplex-Labs68ktodayMIT
21LiteLLMPython SDK and proxy server that expose 100+ model providers through an OpenAI-compatible API with keys, budgets, rate limits, fallbacks and logging.InfrastructureBerriAI64ktodayMIT
22AutoGenFramework for multi-agent conversations and event-driven agent systems that popularised conversable-agent patterns.Frameworkmicrosoft62k9d agoCC-BY-4.0
23CrewAIPython framework for role-based agent teams (crews) and event-driven Flows, independent of LangChain; paired with a commercial platform for deployment.FrameworkCrewAI61ktodayMIT
24ai-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 projectbojieli59k1mo agoApache-2.0
25gooseOpen-source, local general-purpose AI agent (desktop app and CLI) for coding, research, writing and automation that works with any LLM and is extended through MCP extensions, YAML recipes and subagents.PlatformAgentic AI Foundation (originally Block)57k1d agoApache-2.0
26cherry-studioYour AI workspace for models, agents, and productivity.Agent skillCherryHQ54ktodayAGPL-3.0
27LlamaIndexFramework for building agents and workflows over your data, with connectors, indexing, retrieval and an event-driven Workflows engine.FrameworkLlamaIndex53k1d agoMIT
28herdrthe runtime your coding agents live onAgent projectherdrdev52k1d agoApache-2.0
29nanobotYour lightweight open-source personal agent.MCP serverHKUDS50ktodayMIT
30CowAgentOpen-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install.Agent projectzhayujie48ktodayMIT
31iFixAiIndependent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.Infrastructureifixai-ai47k1d agoApache-2.0
32LangGraphLow-level orchestration framework that models agents as stateful graphs with checkpointing, human-in-the-loop interrupts and durable execution.FrameworkLangChain45ktodayMIT
33Kong AI GatewaySet of AI plugins for the Kong API gateway that proxy and govern LLM traffic with prompt guards, semantic caching, routing and MCP traffic controls.InfrastructureKong44k1d agoApache-2.0
34AgnoPython framework and runtime for agents and multi-agent teams with memory, knowledge and a production API server (AgentOS).FrameworkAgno43k1d agoApache-2.0
35openhumanThe fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.Agent projecttinyhumansai43k1d agoGPL-3.0
36agentsPlugins, agents, skills, and commands for Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, and Pi, written once in Markdown and adapted to each tool by generators with validation and evals.Agent skillwshobson43k3d agoMIT
37BettaFish微舆:人人可用的多Agent舆情分析助手,打破信息茧房,还原舆情原貌,预测未来走向,辅助决策!从0实现,不依赖任何框架。Framework666ghj43k1mo agoGPL-2.0
38OpenVikingSelf-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.Infrastructurevolcengine43ktodayAGPL-3.0
39awesome-copilotCommunity-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.Agent skillgithub41k1d agoMIT
40CodewhaleAn open-source coding agent for your terminal, written in Rust. It works with any model, can split one task across several agents, and every line of it is yours to read.Agent projectcodewhale-hq41ktodayMIT

Most common integrations

Third-party services named by products in this node, whole catalogue.

IntegrationProducts Share
Solana1812.1%
GitHub710.8%
Stripe400.5%
PostgreSQL390.4%
YouTube380.4%
Ethereum320.4%
AWS300.3%
LinkedIn270.3%
Google Cloud240.3%
Kubernetes240.3%
Obsidian240.3%
Azure230.3%
Telegram210.2%
Android170.2%
Shopify170.2%

Launches per month

New Agent Infrastructure products per monthSRC

Whole catalogue, by publication month, 2024-11 to 2026-11. The last month is partial; undated products are excluded.

New Agent Infrastructure products per monthWhole catalogue, by publication month, 2024-11 to 2026-11. The last month is partial; undated products are excluded.. Products published: 25 points, latest 1,299 products in 2026-11.
Show the data as a table
New Agent Infrastructure products per month. Whole catalogue, by publication month, 2024-11 to 2026-11. The last month is partial; undated products are excluded.
Products published (products)
2024-118
2024-1212
2025-0118
2025-0215
2025-0329
2025-0434
2025-0537
2025-0620
2025-0730
2025-0822
2025-0948
2025-1051
2025-1135
2025-1248
2026-0182
2026-02256
2026-03375
2026-04546
2026-05425
2026-06471
2026-07805
2026-08814
2026-09935
2026-101,750
2026-111,299

Related opportunities

Opportunity radar

Scored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.

OpportunityCompetitionConfidenceScore
Coverage gap: Task PlanningTask PlanningMediumLow63.0
Coverage gap: User Preference MemoryUser Preference MemoryMediumLow61.0
Coverage gap: Session PersistenceSession PersistenceHighLow60.0
Coverage gap: TypeScript Agent FrameworksTypeScript Agent FrameworksHighLow59.6
Coverage gap: No-code Agent BuildersNo-code Agent BuildersHighLow59.2
Coverage gap: Background AgentsBackground AgentsMediumLow59.1
Coverage gap: LoggingLoggingMediumLow59.1
Coverage gap: Cross-model ConsultationCross-model ConsultationHighLow58.8
Coverage gap: Stateful Workflow GraphsStateful Workflow GraphsHighLow58.4
Coverage gap: Red TeamingRed TeamingHighLow58.1
Coverage gap: Agent HostingAgent HostingMediumLow57.5
Coverage gap: Model RoutingModel RoutingHighLow57.3
Coverage gap: Performance MonitoringPerformance MonitoringHighLow55.5
Coverage gap: Usage MeteringUsage MeteringHighLow55.1
Coverage gap: Code Execution SandboxesCode Execution SandboxesHighLow54.1

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 .