AgentSidekick

Agent Frameworks & Orchestration

Libraries and platforms for building and coordinating agents. As of 2026-11-21, 1,192 indexed products match this category (735 with full profiles); 311 were published in the last 90 days, against 204 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, MarkItDown leads, holding 5% of the stars of the 1,040 products here with their own repository. The most common form is MCP servers (53% of indexed products).

CategorySegment label: Lagging the catalogue DER

Segment statistics

Whole catalogue (all 1,192 indexed products, not only profiled ones). Calculated 2026-11-21.

1,192DERIndexed products735 with full profiles
311DERLaunched, last 90 days204 in the 90 days before
19DERMomentum vs catalogue50 = same pace as the catalogue
5%DERLargest project's share of starsAcross 1,040 products with their own repository
0.016DERConcentration (HHI)About 62 equal-sized projects’ worth; unconcentrated
113SRCMedian starsPer product with its own repository
77%DEROpen sourceMarked open source; unknown counts as not

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 0.016, attention is spread as if across about 62 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 Frameworks & Orchestration by product type, as of 2026-11-21
Product type IndexedShareWith a profile
MCP servers63653.4%214
Frameworks23019.3%223
Libraries947.9%83
Agent skills716.0%70
Infrastructure484.0%47
Agent projects413.4%39
Plugins332.8%26
Rules packs100.84%4
Agent SDKs70.59%7
Platforms40.34%4
IDE extensions40.34%4
Developer tools40.34%4
AI APIs40.34%4
Automation platforms30.25%3
SaaS products20.17%2
Protocols & standards10.08%1

3 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.

SubcategoryIndexed ProfiledNew, 90 daysLabel
Agent OrchestrationCoordinating multiple agents, plans and stateful workflows.671401173Lagging the catalogue
Agent SDKsCode and no-code frameworks for building agents.40133466Lagging the catalogue
Tool Use & Function CallingLetting models call tools, emit structured output and run code.27513390Thin

Top 40 products by GitHub stars

Search the directory

Profiled products only (735 of 1,192), 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 Frameworks & Orchestration: 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
2DifyPlatform for building LLM apps and agent workflows visually with RAG pipelines, model management and app publishing.Automation platformLangGenius162ktodayLicenseRef-Dify-Open-Source-License
3LangflowVisual builder for agent and RAG flows using drag-and-drop components, with flows deployable as APIs or MCP servers.Automation platformDataStax157ktodayMIT
4LangChainFramework of model, tool, retriever and agent abstractions with hundreds of provider integrations; its agent API now runs on LangGraph.FrameworkLangChain150ktodayMIT
5claude-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
6labelhead-artist-momentumTrending hip-hop artist momentum scores across four cultural dimensions.MCP serverIncorporatedPartners116ktodayMIT
7RAGFlowSelf-hostable RAG engine with deep document parsing, template-based chunking, citations and an agent builder.Frameworkinfiniflow94k1d agoApache-2.0
8OpenHandsOpen-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
9claude-flowAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.MCP serverruvnet82ktodayMIT
10ai-agents-for-beginners18 Lessons to Get Started Building AI AgentsAgent projectmicrosoft81k4d agoMIT
11DaytonaSandbox infrastructure that starts isolated environments for running AI-generated code quickly, with SDKs for files, git and processes.InfrastructureDaytona71k4mo ago—
12anything-llmStop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience Agent projectMintplex-Labs68ktodayMIT
13AutoGenFramework for multi-agent conversations and event-driven agent systems that popularised conversable-agent patterns.Frameworkmicrosoft62k9d agoCC-BY-4.0
14CrewAIPython framework for role-based agent teams (crews) and event-driven Flows, independent of LangChain; paired with a commercial platform for deployment.FrameworkCrewAI61ktodayMIT
15LlamaIndexFramework for building agents and workflows over your data, with connectors, indexing, retrieval and an event-driven Workflows engine.FrameworkLlamaIndex53k1d agoMIT
16herdrthe runtime your coding agents live onAgent projectherdrdev52k1d agoApache-2.0
17nanobotYour lightweight open-source personal agent.MCP serverHKUDS50ktodayMIT
18CowAgentOpen-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
19LangGraphLow-level orchestration framework that models agents as stateful graphs with checkpointing, human-in-the-loop interrupts and durable execution.FrameworkLangChain45ktodayMIT
20AgnoPython framework and runtime for agents and multi-agent teams with memory, knowledge and a production API server (AgentOS).FrameworkAgno43k1d agoApache-2.0
21openhumanThe fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.Agent projecttinyhumansai43k1d agoGPL-3.0
22BettaFish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
23CodewhaleAn 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
24oh-my-claudecodeTeams-first Multi-agent orchestration for Claude CodeFrameworkYeachan-Heo41ktodayMIT
25DSPyFramework for programming LM pipelines as declarative modules with signatures, then compiling them with optimisers that tune prompts and weights against metrics.FrameworkStanford NLP39k2d agoMIT
26AgentScopePython multi-agent framework with message-based agent communication, tool use, memory and a visual studio for debugging.FrameworkAlibaba (AgentScope)36k1d agoApache-2.0
27CuaOpen-source infrastructure for computer-use agents: sandboxed macOS, Linux and Windows VMs plus an agent SDK.InfrastructureCua33ktodayMIT
28OpenAI APIAPI for GPT and reasoning models via the Responses and Chat Completions endpoints, with built-in tools such as web search, file search, code interpreter and computer use.APIopenai32k1d agoApache-2.0
29Deep AgentsAgent harness on LangGraph that adds planning tools, a virtual filesystem and subagent spawning for long-running, multi-step tasks.FrameworkLangChain31ktodayMIT
30ComposioIntegration platform with managed OAuth and thousands of tools across apps, exposed to agent frameworks via SDKs and MCP.SaaS productComposio31ktodayMIT
31OpenAI Agents SDKLightweight SDK for multi-agent workflows with agents, handoffs, guardrails, sessions and built-in tracing; works with OpenAI and other model providers.SDKopenai31ktodayMIT
32smolagentsMinimal Python library for agents that write and execute Python code as their actions, with sandboxed execution options and Hub integration.LibraryHugging Face30k1d agoApache-2.0
33SimOpen-source visual canvas for building and deploying agent workflows, self-hosted or cloud.Automation platformSim30ktodayApache-2.0
34MastraTypeScript framework for agents, workflows, RAG, memory and evals, with a local dev playground and deploy targets for common hosts.FrameworkMastra30ktodayApache-2.0
35Semantic KernelSDK for integrating LLMs into .NET, Python and Java apps through plugins, function calling and agent abstractions.Frameworkmicrosoft29ktodayMIT
36AI SDKTypeScript toolkit providing a unified API across model providers for text generation, structured output, tool calling and agent loops, plus React/Svelte/Vue UI hooks for streaming chat.SDKvercel28ktodayApache-2.0
37HaystackPython framework for composing pipelines and agents from components for retrieval, generation and tool use, aimed at production RAG and search.Frameworkdeepset27ktodayApache-2.0
38awesome-claude-code-subagentsA collection of 100+ specialized Claude Code subagents covering a wide range of development use casesAgent projectVoltAgent27k19d agoMIT
39Agent2Agent Protocol (A2A)Open protocol for agents built on different frameworks to discover each other through Agent Cards and exchange tasks, messages and artifacts over HTTP, JSON-RPC or gRPC.ProtocolLinux Foundation (A2A Project)27k1d agoApache-2.0
40daprDapr is a portable runtime for building distributed applications across cloud and edge, combining event-driven architecture with workflow orchestration.Agent projectdapr26k2d agoApache-2.0

Most common integrations

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

IntegrationProducts Share
GitHub161.3%
AWS70.6%
Slack70.6%
Blender60.5%
PostgreSQL60.5%
n8n60.5%
Kubernetes50.4%
Telegram50.4%
Vercel50.4%
Android40.3%
Azure40.3%
Discord40.3%
Solana40.3%
Google Cloud30.3%
Stripe30.3%

Launches per month

New Agent Frameworks & Orchestration products per monthSRC

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

New Agent Frameworks & Orchestration 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 81 products in 2026-11.
Show the data as a table
New Agent Frameworks & Orchestration 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)
2024-112
2024-126
2025-0112
2025-027
2025-0313
2025-0419
2025-0520
2025-0611
2025-0719
2025-0813
2025-0920
2025-1017
2025-1115
2025-1217
2026-0125
2026-0284
2026-0390
2026-0472
2026-0561
2026-0662
2026-0765
2026-0881
2026-09103
2026-10110
2026-1181

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: TypeScript Agent FrameworksTypeScript Agent FrameworksHighLow59.6
Coverage gap: No-code Agent BuildersNo-code Agent BuildersHighLow59.2
Coverage gap: Stateful Workflow GraphsStateful Workflow GraphsHighLow58.4
Coverage gap: Code Execution SandboxesCode Execution SandboxesHighLow54.1
Coverage gap: Python Agent FrameworksPython Agent FrameworksHighLow53.4
Coverage gap: Structured OutputsStructured OutputsHighLow52.1

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 .