Python Agent Frameworks
Agent frameworks for Python. As of 2026-11-21, 75 indexed products offer it (54 with full profiles), in 10 forms: 40 MCP servers, 13 Frameworks, 5 Infrastructure, 5 Libraries. 18 were published in the last 90 days, against 6 in the 90 days before. MarkItDown has the most GitHub stars, 34% of the total across 68 products with their own repository.
CapabilitySegment label: Established DERScored as an opportunity
Available as
All in the directoryProfiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.
MCP servers 40 indexed · 20 profiled
Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | agency-orchestrator🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 276 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id/ar) · zero-code YAML · auto-verified acceptance · Web Studio / Desktop / Docker · 15 LLM providers (11 key-free). 一句话组建你的「一人公司」AI 专家团队,几分钟交付完整方案;验收自动核验,网页 / 桌面 / Docker 全渠道。 | jnMetaCode | 2.5k | 10d ago | ||
| 2 | mcp-memory-serviceOpen-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation. | doobidoo | 2.1k | 1d ago | ||
| 3 | AI-GatewayLabs to explore AI Models, MCP servers, and Agents with the AI Gateway powered by Azure API Management and Microsoft Foundry 🚀 | Azure-Samples | 1.0k | 5d ago | ||
| 4 | haiku.ragLocal-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval | ggozad | 665 | 1d ago | ||
| 5 | agenticosOpen-source, self-hosted AI agent platform for your company's AI teammates. Build, run and govern agents on your own servers and models: shared chat, RAG, skills, a real browser, 4,700+ MCP servers, budgets, approvals and an audit trail. An alternative to ChatGPT Enterprise and Grok Bot. Apache-2.0, built on Pydantic AI. | vstorm-co | 525 | today | ||
| 6 | PlanExeMCP server for generating rough-draft project plans from natural-language prompts. | PlanExeOrg | 404 | 6d ago | ||
| 7 | AI-companyMulti-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashboard. No LangChain/AutoGen — pure CC native integration. | CronusL-1141 | 378 | 3d ago | ||
| 8 | mcp-server-mas-sequential-thinkingAn advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP. | FradSer | 307 | 7d ago | ||
| 9 | www-project-agent-memory-guardRuntime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0. | OWASP | 209 | today | ||
| 10 | flexible-graphragGraphRAG, RAG, LlamaIndex, LangChain, 15 Prop Graph, 4 RDF, 10 Vector, 3 Search DBs. 14 data srcs, auto sync, Alfresco, Nuxeo, SharePoint, Box, CMIS, S3,GCS,Azure, web. KG auto-bld, Ontologies, 13 LLM providers, Docling, LlamaParse, LiteParse, Hybrid Search, AI Chat. TypeScript React, Vue, Angular, Python, REST, MCP, OpenArch, Langflow, CocoIndex. | stevereiner | 204 | today |
Frameworks 13 indexed · 12 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | AutoGenFramework for multi-agent conversations and event-driven agent systems that popularised conversable-agent patterns. | microsoft | 62k | 9d ago | ||
| 2 | LlamaIndexFramework for building agents and workflows over your data, with connectors, indexing, retrieval and an event-driven Workflows engine. | LlamaIndex | 53k | 1d ago | ||
| 3 | AgnoPython framework and runtime for agents and multi-agent teams with memory, knowledge and a production API server (AgentOS). | Agno | 43k | today | ||
| 4 | DSPyFramework for programming LM pipelines as declarative modules with signatures, then compiling them with optimisers that tune prompts and weights against metrics. | Stanford NLP | 39k | 2d ago | ||
| 5 | Pydantic AIType-safe Python agent framework built around Pydantic validation, dependency injection, structured outputs and graph-based control flow. | pydantic | 21k | today | ||
| 6 | AG2Community fork of AutoGen 0.2 for multi-agent conversations, group chats and tool use, maintained independently of Microsoft. | ag2ai | 5.1k | today | ||
| 7 | full-stack-ai-agent-templateFull-stack AI app generator — FastAPI + Next.js with AI Agents, RAG, streaming, auth, and 20+ integrations out of the box. | vstorm-co | 2.0k | 1d ago | ||
| 8 | pydantic-deepagentsOpen-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model. | vstorm-co | 1.1k | 22d ago | ||
| 9 | MARTI[ICLR 2026] A Framework for LLM-based Multi-Agent Reinforced Training and Inference | TsinghuaC3I | 575 | 3mo ago | ||
| 10 | pydantic-ai-skillsThis package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills. | DougTrajano | 381 | today |
Infrastructure 5 indexed · 5 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | LLPhantLLPhant - A comprehensive PHP Generative AI Framework using OpenAI GPT 4. Inspired by Langchain | LLPhant | 1.7k | 2d ago | ||
| 2 | openinferenceOpenTelemetry Instrumentation for AI Observability | Arize-ai | 1.3k | today | ||
| 3 | llm-pythonLarge Language Models (LLMs) tutorials & sample scripts, ft. langchain, openai, llamaindex, gpt, chromadb & pinecone | onlyphantom | 932 | 8d ago | ||
| 4 | palico-aiBuild, Improve Performance, and Productionize your AI Application | palico-ai | 343 | 1y ago | ||
| 5 | agentcanvasVisualize Pydantic AI agent workflows from Logfire traces as an interactive HTML diagram — tools, nested sub-agents, tokens and exact cost. | vstorm-co | 84 | 3mo ago |
Libraries 5 indexed · 5 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | MarkItDownPython utility that converts PDF, Office, HTML, images and audio files into Markdown for LLM consumption. | microsoft | 197k | 14d ago | ||
| 2 | smolagentsMinimal Python library for agents that write and execute Python code as their actions, with sandboxed execution options and Hub integration. | Hugging Face | 30k | 1d ago | ||
| 3 | sample-agentic-frameworks-on-awsBuild Agentic AI solutions on AWS, using latest OSS Agentic Frameworks. | aws-samples | 267 | 5mo ago | ||
| 4 | awesome-agent-orchestration⭐ Curated list of AI Agent frameworks: AutoGen, CrewAI, MetaGPT, LangGraph, Swarms. Multi-Agent Systems, Swarm Intelligence, A2A Protocol, MCP Protocol. LLM Agents, Agentic AI, Agent Workflows. | vivy-yi | 114 | 8mo ago | ||
| 5 | agentweavePre-inference tool and agent routing for MCP, A2A and tool-rich LLM systems. Reduce candidate tools before model inference with policy-aware routing and recovery. | sauravsingla | 42 | 1mo ago |
Agent skills 3 indexed · 3 profiled
Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | agent-governancePatterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen) | github | — | 1d ago | ||
| 2 | langfuseExpert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. | sickn33 | — | 1d ago | ||
| 3 | agents-llamaindexData framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications. | davila7 | — | today |
Developer tools 3 indexed · 3 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Arize PhoenixSelf-hostable tracing and evaluation tool built on OpenTelemetry/OpenInference for inspecting LLM and agent runs, datasets and experiments. | Arize-ai | 12k | today | ||
| 2 | AgentOpsSDK and dashboard for monitoring agent sessions, tool calls, costs and failures, with integrations for CrewAI, OpenAI Agents SDK, AG2 and others. | AgentOps | 6.0k | 4mo ago | ||
| 3 | LangWatchPlatform for LLM tracing, evaluations and agent simulation testing, self-hosted or cloud. | langwatch | 5.0k | today |
Agent projects 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | ai-agents-for-beginners18 Lessons to Get Started Building AI Agents | microsoft | 81k | 4d ago | ||
| 2 | building-a-coding-agent-from-scratch-courseLearn harness engineering by building Claude Code from scratch. Free, open-source course: 8 articles, 6 videos, 1 codebase. | itsdecodingai | 1.2k | 28d ago |
Plugins 2 indexed · 2 profiled
2 of these are Claude plugins, which Claude Code documents (protocol-level). DER
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | ai-doc-genAI-powered multi-agent system that automatically analyzes codebases and generates comprehensive documentation. Features GitLab integration, concurrent processing, and multiple LLM support for better code understanding and developer onboarding. | divar-ir | 772 | 4mo ago | ||
| 2 | pydantic-aiWrite accurate Pydantic AI code from the start. Up-to-date patterns, decision trees, and common gotchas for agents, tools, structured output, streaming, and multi-agent apps. | pydantic | 156 | 23d ago |
SaaS products 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Pydantic LogfireOpenTelemetry-based observability service with first-class tracing for LLM calls, Pydantic AI agents and general Python apps, queryable with SQL. | pydantic | 4.6k | today |
Agent SDKs 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Microsoft Agent FrameworkSDK and runtime for building agents and graph-based multi-agent workflows in .NET and Python; successor that merges Semantic Kernel and AutoGen concepts. | microsoft | — | — |
Which platforms these forms can reach
All platformsProtocol-level: the platform documents support for the standard. No specific pairing has been tested.
MCP servers 40 indexed here
36 platforms document MCP support CUR.
ContinueOpenCodeClaude CodeCodexGemini CLIZedOpenHandsClineWarpgooseQwen CodeBolt (bolt.new)KiroAmazon Bedrock AgentCoreAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)Augment CodeChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJetBrains AI AssistantJunieLovableMicrosoft Copilot StudioReplit AgentTabninev0
Agent skills 3 indexed here
26 platforms document Agent Skills support CUR.
OpenClawOpenCodeClaude CodeCodexGemini CLIOpenHandsWarpgooseBolt (bolt.new)KiroAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)ChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJunieReplit AgentTabnine
Platforms publishers name
| Platform | Profiled products naming it |
|---|---|
| Claude Code | 3 |
| ChatGPT | 1 |
Integrations most often paired
Third-party services named by products with this capability, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| Azure | 2 | 2.7% |
| AWS | 1 | 1.3% |
| Chroma | 1 | 1.3% |
| Discord | 1 | 1.3% |
| GitHub | 1 | 1.3% |
| GitLab | 1 | 1.3% |
| Microsoft Excel | 1 | 1.3% |
| OneDrive / SharePoint | 1 | 1.3% |
| Pinecone | 1 | 1.3% |
Keywords that trigger this capability
Matched as whole words, ignoring case, in a product's name, description and repository topics.
| Keyword | Products matched |
|---|---|
| langchain | 0 |
| llamaindex | 23 |
| autogen | 31 |
| pydantic ai | 14 |
| smolagents | 1 |
| agno | 2 |
| dspy | 4 |
Segment statistics
Whole catalogue (75 indexed products). Calculated 2026-11-21.
Established. Mid-sized among capabilities, with launches roughly in step with the catalogue. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.170 means stars are spread as if across about 6 equally popular projects — moderately concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.
Scored as an opportunity
Score breakdownCoverage gap: Python Agent Frameworks: score 53.4 HEU, competition High, confidence Low. Only 75 indexed products match "Python Agent Frameworks", against 401 in Agent SDKs overall.
Limits
- Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
- Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
- Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
- Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.
Page data last updated .