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.
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.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 636 | 53.4% | 214 |
| Frameworks | 230 | 19.3% | 223 |
| Libraries | 94 | 7.9% | 83 |
| Agent skills | 71 | 6.0% | 70 |
| Infrastructure | 48 | 4.0% | 47 |
| Agent projects | 41 | 3.4% | 39 |
| Plugins | 33 | 2.8% | 26 |
| Rules packs | 10 | 0.84% | 4 |
| Agent SDKs | 7 | 0.59% | 7 |
| Platforms | 4 | 0.34% | 4 |
| IDE extensions | 4 | 0.34% | 4 |
| Developer tools | 4 | 0.34% | 4 |
| AI APIs | 4 | 0.34% | 4 |
| Automation platforms | 3 | 0.25% | 3 |
| SaaS products | 2 | 0.17% | 2 |
| Protocols & standards | 1 | 0.08% | 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.
| Subcategory | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Agent OrchestrationCoordinating multiple agents, plans and stateful workflows. | 671 | 401 | 173 | Lagging the catalogue |
| Agent SDKsCode and no-code frameworks for building agents. | 401 | 334 | 66 | Lagging the catalogue |
| Tool Use & Function CallingLetting models call tools, emit structured output and run code. | 275 | 133 | 90 | Thin |
Top 40 products by GitHub stars
Search the directoryProfiled 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.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | MarkItDownPython utility that converts PDF, Office, HTML, images and audio files into Markdown for LLM consumption. | Library | microsoft | 197k | 14d ago | MIT | ||
| 2 | DifyPlatform for building LLM apps and agent workflows visually with RAG pipelines, model management and app publishing. | Automation platform | LangGenius | 162k | today | LicenseRef-Dify-Open-Source-License | ||
| 3 | LangflowVisual builder for agent and RAG flows using drag-and-drop components, with flows deployable as APIs or MCP servers. | Automation platform | DataStax | 157k | today | MIT | ||
| 4 | LangChainFramework of model, tool, retriever and agent abstractions with hundreds of provider integrations; its agent API now runs on LangGraph. | Framework | LangChain | 150k | today | MIT | ||
| 5 | 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 | ||
| 6 | labelhead-artist-momentumTrending hip-hop artist momentum scores across four cultural dimensions. | MCP server | IncorporatedPartners | 116k | today | MIT | ||
| 7 | RAGFlowSelf-hostable RAG engine with deep document parsing, template-based chunking, citations and an agent builder. | Framework | infiniflow | 94k | 1d ago | Apache-2.0 | ||
| 8 | 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 | ||
| 9 | claude-flowAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev. | MCP server | ruvnet | 82k | today | MIT | ||
| 10 | ai-agents-for-beginners18 Lessons to Get Started Building AI Agents | Agent project | microsoft | 81k | 4d ago | MIT | ||
| 11 | DaytonaSandbox infrastructure that starts isolated environments for running AI-generated code quickly, with SDKs for files, git and processes. | Infrastructure | Daytona | 71k | 4mo ago | — | ||
| 12 | anything-llmStop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience | Agent project | Mintplex-Labs | 68k | today | MIT | ||
| 13 | AutoGenFramework for multi-agent conversations and event-driven agent systems that popularised conversable-agent patterns. | Framework | microsoft | 62k | 9d ago | CC-BY-4.0 | ||
| 14 | CrewAIPython framework for role-based agent teams (crews) and event-driven Flows, independent of LangChain; paired with a commercial platform for deployment. | Framework | CrewAI | 61k | today | MIT | ||
| 15 | LlamaIndexFramework for building agents and workflows over your data, with connectors, indexing, retrieval and an event-driven Workflows engine. | Framework | LlamaIndex | 53k | 1d ago | MIT | ||
| 16 | herdrthe runtime your coding agents live on | Agent project | herdrdev | 52k | 1d ago | Apache-2.0 | ||
| 17 | nanobotYour lightweight open-source personal agent. | MCP server | HKUDS | 50k | today | MIT | ||
| 18 | CowAgentOpen-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 project | zhayujie | 48k | today | MIT | ||
| 19 | 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 | ||
| 20 | AgnoPython framework and runtime for agents and multi-agent teams with memory, knowledge and a production API server (AgentOS). | Framework | Agno | 43k | 1d ago | Apache-2.0 | ||
| 21 | openhumanThe fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS. | Agent project | tinyhumansai | 43k | 1d ago | GPL-3.0 | ||
| 22 | BettaFish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。 | Framework | 666ghj | 43k | 1mo ago | GPL-2.0 | ||
| 23 | CodewhaleAn 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 project | codewhale-hq | 41k | today | MIT | ||
| 24 | oh-my-claudecodeTeams-first Multi-agent orchestration for Claude Code | Framework | Yeachan-Heo | 41k | today | MIT | ||
| 25 | DSPyFramework for programming LM pipelines as declarative modules with signatures, then compiling them with optimisers that tune prompts and weights against metrics. | Framework | Stanford NLP | 39k | 2d ago | MIT | ||
| 26 | AgentScopePython multi-agent framework with message-based agent communication, tool use, memory and a visual studio for debugging. | Framework | Alibaba (AgentScope) | 36k | 1d ago | Apache-2.0 | ||
| 27 | CuaOpen-source infrastructure for computer-use agents: sandboxed macOS, Linux and Windows VMs plus an agent SDK. | Infrastructure | Cua | 33k | today | MIT | ||
| 28 | OpenAI 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. | API | openai | 32k | 1d ago | Apache-2.0 | ||
| 29 | Deep AgentsAgent harness on LangGraph that adds planning tools, a virtual filesystem and subagent spawning for long-running, multi-step tasks. | Framework | LangChain | 31k | today | MIT | ||
| 30 | ComposioIntegration platform with managed OAuth and thousands of tools across apps, exposed to agent frameworks via SDKs and MCP. | SaaS product | Composio | 31k | today | MIT | ||
| 31 | OpenAI Agents SDKLightweight SDK for multi-agent workflows with agents, handoffs, guardrails, sessions and built-in tracing; works with OpenAI and other model providers. | SDK | openai | 31k | today | MIT | ||
| 32 | smolagentsMinimal Python library for agents that write and execute Python code as their actions, with sandboxed execution options and Hub integration. | Library | Hugging Face | 30k | 1d ago | Apache-2.0 | ||
| 33 | SimOpen-source visual canvas for building and deploying agent workflows, self-hosted or cloud. | Automation platform | Sim | 30k | today | Apache-2.0 | ||
| 34 | MastraTypeScript framework for agents, workflows, RAG, memory and evals, with a local dev playground and deploy targets for common hosts. | Framework | Mastra | 30k | today | Apache-2.0 | ||
| 35 | Semantic KernelSDK for integrating LLMs into .NET, Python and Java apps through plugins, function calling and agent abstractions. | Framework | microsoft | 29k | today | MIT | ||
| 36 | AI 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. | SDK | vercel | 28k | today | Apache-2.0 | ||
| 37 | HaystackPython framework for composing pipelines and agents from components for retrieval, generation and tool use, aimed at production RAG and search. | Framework | deepset | 27k | today | Apache-2.0 | ||
| 38 | awesome-claude-code-subagentsA collection of 100+ specialized Claude Code subagents covering a wide range of development use cases | Agent project | VoltAgent | 27k | 19d ago | MIT | ||
| 39 | Agent2Agent 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. | Protocol | Linux Foundation (A2A Project) | 27k | 1d ago | Apache-2.0 | ||
| 40 | daprDapr is a portable runtime for building distributed applications across cloud and edge, combining event-driven architecture with workflow orchestration. | Agent project | dapr | 26k | 2d ago | Apache-2.0 |
Most common integrations
Third-party services named by products in this node, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| GitHub | 16 | 1.3% |
| AWS | 7 | 0.6% |
| Slack | 7 | 0.6% |
| Blender | 6 | 0.5% |
| PostgreSQL | 6 | 0.5% |
| n8n | 6 | 0.5% |
| Kubernetes | 5 | 0.4% |
| Telegram | 5 | 0.4% |
| Vercel | 5 | 0.4% |
| Android | 4 | 0.3% |
| Azure | 4 | 0.3% |
| Discord | 4 | 0.3% |
| Solana | 4 | 0.3% |
| Google Cloud | 3 | 0.3% |
| Stripe | 3 | 0.3% |
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.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-11 | 2 |
| 2024-12 | 6 |
| 2025-01 | 12 |
| 2025-02 | 7 |
| 2025-03 | 13 |
| 2025-04 | 19 |
| 2025-05 | 20 |
| 2025-06 | 11 |
| 2025-07 | 19 |
| 2025-08 | 13 |
| 2025-09 | 20 |
| 2025-10 | 17 |
| 2025-11 | 15 |
| 2025-12 | 17 |
| 2026-01 | 25 |
| 2026-02 | 84 |
| 2026-03 | 90 |
| 2026-04 | 72 |
| 2026-05 | 61 |
| 2026-06 | 62 |
| 2026-07 | 65 |
| 2026-08 | 81 |
| 2026-09 | 103 |
| 2026-10 | 110 |
| 2026-11 | 81 |
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: Task PlanningTask Planning | Medium | Low | 63.0 |
| Coverage gap: TypeScript Agent FrameworksTypeScript Agent Frameworks | High | Low | 59.6 |
| Coverage gap: No-code Agent BuildersNo-code Agent Builders | High | Low | 59.2 |
| Coverage gap: Stateful Workflow GraphsStateful Workflow Graphs | High | Low | 58.4 |
| Coverage gap: Code Execution SandboxesCode Execution Sandboxes | High | Low | 54.1 |
| Coverage gap: Python Agent FrameworksPython Agent Frameworks | High | Low | 53.4 |
| Coverage gap: Structured OutputsStructured Outputs | High | Low | 52.1 |
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 .