[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"pack-detail-python-agent-frameworks-en":3,"seo:pack:python-agent-frameworks:en":61},{"code":4,"message":5,"data":6},200,"操作成功",{"pack":7},{"slug":8,"icon":9,"tone":10,"status":11,"status_label":12,"title":13,"description":14,"items":15,"install_cmd":60},"python-agent-frameworks","🐍","#4F46E5","stable","Stable","Python Agent Frameworks","Phidata, AGiXT, AutoGPT, OpenAI Swarm, CrewAI — Python-first frameworks for shipping multi-agent systems beyond the LangGraph default.",[16,28,36,44,52],{"id":17,"uuid":18,"slug":19,"title":20,"description":21,"author_name":22,"view_count":23,"vote_count":24,"lang_type":25,"type":26,"type_label":27},223,"d1627127-f788-47dc-ac98-b3464feb99f8","phidata-build-deploy-ai-agents-scale-d1627127","Phidata — Build & Deploy AI Agents at Scale","Framework for building, running, and managing AI agents at scale. Memory, knowledge, tools, reasoning, and team workflows. Monitoring dashboard included. 39K+ stars.","Phidata",333,0,"en","skill","Skill",{"id":29,"uuid":30,"slug":31,"title":32,"description":33,"author_name":34,"view_count":35,"vote_count":24,"lang_type":25,"type":26,"type_label":27},750,"6528233f-b920-475b-8ecb-a15801303634","agixt-extensible-ai-agent-automation-framework-6528233f","AGiXT — Extensible AI Agent Automation Framework","Open-source AI agent automation platform with 50+ provider integrations, plugin system, chain-of-thought workflows, and persistent memory. Self-hostable via Docker.","Agent Toolkit",264,{"id":37,"uuid":38,"slug":39,"title":40,"description":41,"author_name":42,"view_count":43,"vote_count":24,"lang_type":25,"type":26,"type_label":27},221,"6764deda-6349-4f2e-a9a0-0f867ac9d5e6","autogpt-autonomous-ai-agent-platform-6764deda","AutoGPT — Autonomous AI Agent Platform","Build and deploy autonomous AI agents that accomplish goals with minimal human input. Visual builder, marketplace, and API. The original autonomous agent. 183K+ stars.","Script Depot",293,{"id":45,"uuid":46,"slug":47,"title":48,"description":49,"author_name":50,"view_count":51,"vote_count":24,"lang_type":25,"type":26,"type_label":27},231,"d75dad10-15d3-4530-9e8c-4558ec701a27","openai-swarm-lightweight-multi-agent-orchestration-d75dad10","OpenAI Swarm — Lightweight Multi-Agent Orchestration","Educational multi-agent framework by OpenAI. Ergonomic agent handoffs, tool calling, and context variables. Minimal abstraction over Chat Completions API. 21K+ stars.","OpenAI",334,{"id":53,"uuid":54,"slug":55,"title":56,"description":57,"author_name":58,"view_count":59,"vote_count":24,"lang_type":25,"type":26,"type_label":27},623,"97fce2da-d60f-413c-a31d-527cd7aaa558","crewai-multi-agent-orchestration-framework-97fce2da","CrewAI — Multi-Agent Orchestration in Python","Python framework for orchestrating role-playing AI agents that collaborate on complex tasks. Define agents with roles, goals, and tools, then let them work together autonomously. 25,000+ stars.","CrewAI",284,"tokrepo install pack\u002Fpython-agent-frameworks",{"pageType":62,"pageKey":8,"locale":25,"title":63,"metaDescription":64,"h1":13,"tldr":65,"bodyMarkdown":66,"faq":67,"schema":83,"internalLinks":92,"citations":105,"wordCount":118,"generatedAt":119},"pack","Python Agent Frameworks: 5 alternatives to LangGraph","Phidata, AGiXT, AutoGPT, OpenAI Swarm, CrewAI — five Python-first frameworks for multi-agent systems beyond the LangGraph default. Install via TokRepo.","Five Python-native frameworks for building multi-agent systems — covering role-based crews, autonomous loops, hand-off routing, and full agent platforms. Install in one command via TokRepo.","## What's in this pack\n\nThis pack collects the **five Python-first agent frameworks** that ship enough production code to use today, ranked by GitHub stars and active commit cadence. Each one represents a different design philosophy — pick by the shape of your problem, not the brand name.\n\n| # | Framework | Style | Best for |\n|---|---|---|---|\n| 1 | Phidata | data-app-style agents | dashboards + tool-calling agents |\n| 2 | AGiXT | full agent platform | self-hosted multi-provider |\n| 3 | AutoGPT | autonomous loop | open-ended goal pursuit |\n| 4 | OpenAI Swarm | hand-off routing | lightweight multi-agent |\n| 5 | CrewAI | role-based crews | sequential team workflows |\n\nThe list intentionally excludes LangGraph (covered as a default in most LangChain stacks) and the JS-only frameworks. It covers the design space Python users actually pick from when LangGraph's StateGraph feels too heavyweight.\n\n## Why \"stay in Python\" matters\n\nMost teams have a Python data stack already — pandas, FastAPI, Postgres drivers, the ML libs. Switching to a TypeScript or Go agent runtime means rewriting the data plumbing for one feature. These five frameworks sidestep that entirely. They run inside your existing FastAPI service, share your venv, and call the same DB driver your backend already uses.\n\nThe trade-off shape:\n- **Phidata** is the most \"Python-y\" — agents are classes with tool methods, very SQLAlchemy-flavored. Best when your agent IS a data app (dashboards, internal tools).\n- **AGiXT** is a full platform with a UI, provider abstraction, chains, extensions. Heaviest install, most features out of the box.\n- **AutoGPT** is the autonomous-loop archetype — goal in, plan + execute + reflect, repeat. Heavier on token cost; lighter on dev work.\n- **OpenAI Swarm** is the smallest — agents hand off to each other via a `transfer_to_X()` function. Experimental but the cleanest mental model for routing.\n- **CrewAI** lets you define `Agent`, `Task`, `Crew` objects — explicit roles, sequential or hierarchical execution. Great for \"marketing → review → publish\" pipelines.\n\n## Install in one command\n\n```bash\n# Install the pack — drops requirements + example agents into your project\ntokrepo install pack\u002Fpython-agent-frameworks\n\n# Or pick one\ntokrepo install crewai\ntokrepo install openai-swarm\ntokrepo install autogpt\n```\n\nThe TokRepo CLI fetches each framework's getting-started template, places it under `agents\u002F\u003Cframework>\u002F`, and adds dependencies to `pyproject.toml` or `requirements.txt`. Run `pytest agents\u002F` to validate the examples before wiring to your real prompts.\n\n## Common pitfalls\n\n- **Don't use AutoGPT for closed-form tasks.** Its strength is open-ended goals. For \"summarize this PDF\" you'll burn tokens reflecting on a problem that has one obvious step.\n- **Swarm is experimental, not production.** OpenAI ships it as a \"design pattern\" repo. Use the routing pattern; build the production loop yourself or copy it into a maintained fork.\n- **CrewAI sequential mode hides parallelism.** If two tasks have no dependency, declare them parallel — sequential mode runs everything end-to-end even when not needed.\n- **Phidata's storage layer assumes Postgres.** SQLite works for local dev but the storage interface is built around `JSONB`. Plan a real Postgres for any deployed run.\n- **AGiXT updates fast.** The schema between minor versions has broken before. Pin a specific tag in production and read the changelog before upgrading.\n\n## When this pack alone isn't enough\n\nIf your problem is one Python-only service, this pack is enough. If you have:\n- a **Java\u002FSpring backend** → see [Agent Frameworks Across Languages](\u002Fen\u002Fpacks\u002Fagent-frameworks-multilang) for Spring AI and LangChain4j\n- a **TypeScript edge function** → same multilang pack covers Mastra\n- a **non-LLM evaluator gating step** → pair with [LLM Eval & Guardrails](\u002Fen\u002Fpacks\u002Fllm-eval-guardrails)\n\nYou can also combine: a CrewAI orchestrator written in Python that calls a Spring AI agent in Java for a specific tool, evaluated by Promptfoo before shipping. The frameworks here are agent runtimes — they don't dictate the rest of your stack.",[68,71,74,77,80],{"q":69,"a":70},"Are these frameworks free?","All five are MIT or Apache 2.0 open source — no per-seat costs, no usage caps from the framework itself. You'll still pay for the LLM API behind them (OpenAI, Anthropic, etc), and AGiXT's hosted version costs money. Self-hosting any of the five is genuinely free, including Phidata's optional managed dashboard.",{"q":72,"a":73},"How does CrewAI compare to LangGraph?","CrewAI is role-based and sequential by default — you describe Agents and Tasks, then assemble a Crew. LangGraph is graph-based — you draw nodes and edges yourself. CrewAI is faster to express team workflows; LangGraph is better when control flow is irregular or has cycles. Many teams prototype in CrewAI then port hot paths to LangGraph for control.",{"q":75,"a":76},"Will any of these work with Claude Code or Cursor?","These frameworks are runtimes, not editor integrations. You build agents with them, then run as a Python service. Your editor (Claude Code, Cursor) is where you write the code, but the agent itself runs as your service. For editor-side subagents, see Awesome Claude Code Subagents pack instead.",{"q":78,"a":79},"Difference vs Multi-Agent Frameworks pack?","Multi-Agent Frameworks is platform-agnostic — it includes JS, Go, and Python options side-by-side for comparison shopping. This pack is Python-only, deeper into the Python design choices. If you're committed to Python, start here. If you're picking the language too, start with Multi-Agent Frameworks.",{"q":81,"a":82},"What's the operational gotcha with AutoGPT?","It will happily loop forever if you don't cap iterations or token budget. The default config can spend $50 of OpenAI credits in a single 'analyze the market' task before noticing it's circling. Always set max_iterations, max_cost_in_usd, and a strict goal — vague goals plus unlimited budget is the failure mode.",{"@context":84,"@type":85,"name":13,"description":86,"numberOfItems":87,"publisher":88},"https:\u002F\u002Fschema.org","CollectionPage","Phidata, AGiXT, AutoGPT, OpenAI Swarm, CrewAI — Python-first frameworks for multi-agent systems beyond LangGraph.",5,{"@type":89,"name":90,"url":91},"Organization","TokRepo","https:\u002F\u002Ftokrepo.com",[93,97,101],{"url":94,"anchor":95,"reason":96},"\u002Fen\u002Fpacks\u002Fmulti-agent-frameworks","Multi-Agent Frameworks","platform-agnostic comparison across languages",{"url":98,"anchor":99,"reason":100},"\u002Fen\u002Fpacks\u002Fagent-frameworks-multilang","Agent Frameworks Across Languages","non-Python stacks (Java, Rust, TS)",{"url":102,"anchor":103,"reason":104},"\u002Fen\u002Fpacks\u002Fllm-eval-guardrails","LLM Eval & Guardrails","score every agent change before ship",[106,110,114],{"claim":107,"source_name":108,"source_url":109},"OpenAI Swarm experimental multi-agent framework","openai\u002Fswarm","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fswarm",{"claim":111,"source_name":112,"source_url":113},"CrewAI role-based orchestration","crewAIInc\u002FcrewAI","https:\u002F\u002Fgithub.com\u002FcrewAIInc\u002FcrewAI",{"claim":115,"source_name":116,"source_url":117},"AutoGPT autonomous agent project","Significant-Gravitas\u002FAutoGPT","https:\u002F\u002Fgithub.com\u002FSignificant-Gravitas\u002FAutoGPT",646,"2026-05-02T15:00:00Z"]