Agent SDKs
Code and no-code frameworks for building agents. As of 2026-11-21, 401 indexed products match this subcategory (334 with full profiles); 66 were published in the last 90 days, against 55 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, MarkItDown leads, holding 9% of the stars of the 385 products here with their own repository. The most common form is Frameworks (47% of indexed products).
SubcategorySegment label: Lagging the catalogue DER
Segment statistics
Whole catalogue (all 401 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 subcategory 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 |
|---|---|---|---|
| Frameworks | 188 | 46.9% | 181 |
| MCP servers | 129 | 32.2% | 72 |
| Agent skills | 20 | 5.0% | 20 |
| Libraries | 16 | 4.0% | 15 |
| Infrastructure | 15 | 3.7% | 15 |
| Plugins | 8 | 2.0% | 6 |
| Agent SDKs | 7 | 1.7% | 7 |
| Agent projects | 7 | 1.7% | 7 |
| Developer tools | 4 | 1.00% | 4 |
| Platforms | 3 | 0.75% | 3 |
| Automation platforms | 2 | 0.50% | 2 |
| SaaS products | 1 | 0.25% | 1 |
| Rules packs | 1 | 0.25% | 1 |
3 capabilities
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.
| Capability | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Python Agent FrameworksAgent frameworks for Python. | 75 | 54 | 18 | Established |
| No-code Agent BuildersVisual tools for assembling agents without code. | 27 | 17 | 5 | Thin |
| TypeScript Agent FrameworksAgent frameworks for TypeScript and JavaScript. | 25 | 14 | 8 | Thin |
Top 40 products by GitHub stars
Search the directoryProfiled products only (334 of 401), 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 | 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 | ||
| 5 | RAGFlowSelf-hostable RAG engine with deep document parsing, template-based chunking, citations and an agent builder. | Framework | infiniflow | 94k | 1d ago | Apache-2.0 | ||
| 6 | 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 | ||
| 7 | ai-agents-for-beginners18 Lessons to Get Started Building AI Agents | Agent project | microsoft | 81k | 4d ago | MIT | ||
| 8 | AutoGenFramework for multi-agent conversations and event-driven agent systems that popularised conversable-agent patterns. | Framework | microsoft | 62k | 9d ago | CC-BY-4.0 | ||
| 9 | 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 | ||
| 10 | nanobotYour lightweight open-source personal agent. | MCP server | HKUDS | 50k | today | MIT | ||
| 11 | 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 | ||
| 12 | 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 | ||
| 13 | 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 | ||
| 14 | 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 | ||
| 15 | CuaOpen-source infrastructure for computer-use agents: sandboxed macOS, Linux and Windows VMs plus an agent SDK. | Infrastructure | Cua | 33k | today | MIT | ||
| 16 | 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 | ||
| 17 | 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 | ||
| 18 | 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 | ||
| 19 | 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 | ||
| 20 | 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 | ||
| 21 | 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 | ||
| 22 | Agent Development Kit (ADK)Code-first toolkit for building, evaluating and deploying single and multi-agent systems, optimised for Gemini and Google Cloud but model-agnostic. | SDK | 22k | today | Apache-2.0 | |||
| 23 | agents-towards-productionEnd-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment. | Framework | NirDiamant | 22k | 6d ago | — | ||
| 24 | Pydantic AIType-safe Python agent framework built around Pydantic validation, dependency injection, structured outputs and graph-based control flow. | Framework | pydantic | 21k | today | MIT | ||
| 25 | rocketride-serverRocketRide is an open source AI meta-harness with the only enterprise-grade runtime built on C++. Build, test and publish durable agents that scale in production. | MCP server | rocketride-org | 20k | today | MIT | ||
| 26 | openfangOpen-source Agent Operating System | Framework | RightNow-AI | 18k | 4mo ago | Apache-2.0 | ||
| 27 | CAMELMulti-agent framework for role-playing agent societies, synthetic data generation and large-scale agent simulations. | Framework | camel-ai | 18k | 5d ago | Apache-2.0 | ||
| 28 | SuperAGI<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably. | Infrastructure | TransformerOptimus | 18k | 1y ago | MIT | ||
| 29 | Trigger.devBackground job and durable task platform for TypeScript with retries, queues and realtime run updates, often used for agents. | Infrastructure | Trigger.dev | 17k | today | Apache-2.0 | ||
| 30 | eigentEigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex | Agent skill | eigent-ai | 16k | 1d ago | Apache-2.0 | ||
| 31 | Arize PhoenixSelf-hostable tracing and evaluation tool built on OpenTelemetry/OpenInference for inspecting LLM and agent runs, datasets and experiments. | Developer tool | Arize-ai | 12k | today | Elastic-2.0 | ||
| 32 | omnigentOmnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device. | Framework | omnigent-ai | 11k | today | Apache-2.0 | ||
| 33 | xiaozhi-esp32-server本项目为xiaozhi-esp32提供后端服务,帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server. | MCP server | xinnan-tech | 11k | 2d ago | MIT | ||
| 34 | hiveMulti-Agent Harness for Production AI | Agent skill | aden-hive | 11k | 4d ago | Apache-2.0 | ||
| 35 | VoltAgentTypeScript agent framework with memory, workflows, supervisor/sub-agent patterns and a companion observability console. | Framework | VoltAgent | 11k | 15d ago | MIT | ||
| 36 | PraisonAIAI Agents Framework with Self Reflection and MCP support | MCP server | MervinPraison | 9.4k | 1d ago | MIT | ||
| 37 | Strands AgentsModel-driven agent SDK where the model plans and calls tools in a loop; supports Amazon Bedrock and other providers and deploys to AWS services. | SDK | Amazon Web Services | 9.3k | 1d ago | Apache-2.0 | ||
| 38 | evolverThe GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai | Framework | EvoMap | 8.7k | 1d ago | GPL-3.0 | ||
| 39 | Claude Agent SDKSDK that exposes the agent loop behind Claude Code (file and shell tools, subagents, hooks, permissions, context compaction) for building custom agents in Python or TypeScript. | SDK | Anthropic | 8.6k | today | MIT | ||
| 40 | MiroThinkerMiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively. | Framework | MiroMindAI | 8.5k | 4mo ago | Apache-2.0 |
Most common integrations
Third-party services named by products in this node, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| n8n | 5 | 1.2% |
| Azure | 4 | 1.0% |
| GitHub | 4 | 1.0% |
| Kubernetes | 4 | 1.0% |
| Vercel | 4 | 1.0% |
| PostgreSQL | 3 | 0.7% |
| AWS | 2 | 0.5% |
| Android | 2 | 0.5% |
| Slack | 2 | 0.5% |
| Stripe | 2 | 0.5% |
| Chroma | 1 | 0.2% |
| Discord | 1 | 0.2% |
| GitLab | 1 | 0.2% |
| Google Calendar | 1 | 0.2% |
| Google Cloud | 1 | 0.2% |
Launches per month
New Agent SDKs 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 | 8 |
| 2025-02 | 4 |
| 2025-03 | 2 |
| 2025-04 | 8 |
| 2025-05 | 6 |
| 2025-06 | 6 |
| 2025-07 | 9 |
| 2025-08 | 9 |
| 2025-09 | 9 |
| 2025-10 | 6 |
| 2025-11 | 3 |
| 2025-12 | 5 |
| 2026-01 | 5 |
| 2026-02 | 33 |
| 2026-03 | 38 |
| 2026-04 | 27 |
| 2026-05 | 22 |
| 2026-06 | 16 |
| 2026-07 | 21 |
| 2026-08 | 24 |
| 2026-09 | 25 |
| 2026-10 | 22 |
| 2026-11 | 12 |
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: TypeScript Agent FrameworksTypeScript Agent Frameworks | High | Low | 59.6 |
| Coverage gap: No-code Agent BuildersNo-code Agent Builders | High | Low | 59.2 |
| Coverage gap: Python Agent FrameworksPython Agent Frameworks | High | Low | 53.4 |
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 .