# AutoGen python-v0.7.5: what's new, verdict & setup Canonical: https://theagenticweekly.com/tools/autogen · Released: 2025-09-30 · Last verified: 2026-10-25 · Evidence: Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)) · Vendor: Microsoft · Official site: https://github.com/microsoft/autogen > Microsoft's open-source multi-agent framework; its README now says the project is in maintenance mode and points to Microsoft Agent Framework. ## Verdict **Microsoft's open-source multi-agent framework; its README now says the project is in maintenance mode and points to Microsoft Agent Framework.** Good for: - Existing AutoGen projects that need reference material - Researchers studying multi-agent patterns Skip if: - You are starting a new production project: Microsoft points to Agent Framework instead Tested. Tested 2026-10-25 (America/Chicago). AutoGen 0.7.5 passed our one-tool task on a local 3B model: 3 of 3 trials; cold uv install 1.9 s. Test environment: Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key. Agent tools were pointed at a local open-weight model (Qwen2.5-3B-Instruct (Q4_K_M) through Ollama 0.40.11), so we tested the tool, not any vendor's hosted models. Not tested: Any vendor-hosted model: everything ran on a local 3B model, so tool-call reliability with frontier models is not measured here; Multi-agent flows, memory, long conversations, streaming, tracing and cloud deployment; Anything beyond one tool and one question; three trials is a smoke test, not a benchmark. These are smoke tests, not a benchmark. Full log: /tests/autogen. Test scope: - Kind and date: smoke test, 2026-10-25 (America/Chicago). Not a benchmark. - What we ran: AutoGen 0.7.5 passed our one-tool task on a local 3B model: 3 of 3 trials; cold uv install 1.9 s. - Model used: Qwen2.5-3B-Instruct (Q4_K_M) through Ollama 0.40.11 - Environment: Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key - Not tested: Any vendor-hosted model: everything ran on a local 3B model, so tool-call reliability with frontier models is not measured here; Multi-agent flows, memory, long conversations, streaming, tracing and cloud deployment; Anything beyond one tool and one question; three trials is a smoke test, not a benchmark. Full test log (commands, versions, raw output): [AutoGen 0.7.5: our test log](https://theagenticweekly.com/tests/autogen) Pricing: Official page, dated. Open-source library; costs come from the model APIs you call. (checked 2026-10-25) ## Best for - [Best AI tool for agent building](https://theagenticweekly.com/best/agent-building) (#-): Microsoft's multi-agent framework, now steering users to Microsoft Agent Framework. ## Key facts AutoGen's README says the project is no longer actively developed with new features, warns that without ongoing maintenance and security fixes vulnerabilities may remain unaddressed, and links an AutoGen to Microsoft Agent Framework migration guide. The latest release tag we saw is python-v0.7.5 from Sep 30, 2025. - License: MIT (code) and CC-BY-4.0 (docs), per GitHub - Platforms: Python and .NET - Pricing model: Free and open source - Free tier: Free to self-host - Paid plans: None listed for the library - GitHub: microsoft/autogen: 61,562 stars on 2026-10-25, last push 2026-10-16 - Latest release we saw: python-v0.7.5, 2025-09-30 - How to start: For new work, follow Microsoft's migration guide to Microsoft Agent Framework; for existing code, pin python-v0.7.5. - python-v0.7.5 (2025-09-30): the newest release listed on the official page or repository when we read it on 2026-10-25. ## How to set it up: Get started with AutoGen These steps come from the vendor's own pages as read on 2026-10-25. We ran AutoGen on 2026-10-25; the test log lists what was and was not covered. 1. **Get access.** For new work, follow Microsoft's migration guide to Microsoft Agent Framework; for existing code, pin python-v0.7.5. 2. **Check the limits and costs first.** Free to self-host. Open-source library; costs come from the model APIs you call. ## Pros and cons Pros: - MIT-licensed code - Large community Cons: - Maintenance mode per its own README - Last release tag we saw is from Sep 2025 - Our test was one small task on a local 3B model; it does not show behaviour with hosted models or larger jobs ## Alternatives - [Semantic Kernel](https://theagenticweekly.com/tools/semantic-kernel): Microsoft's model-agnostic SDK for building AI agents; its README calls Microsoft Agent Framework the enterprise-ready successor. - [CrewAI](https://theagenticweekly.com/tools/crewai): Python framework for orchestrating role-playing, autonomous AI agents that work as a crew. - [LangGraph](https://theagenticweekly.com/tools/langgraph): Low-level framework for building long-running, stateful agents as graphs. - [Langflow](https://theagenticweekly.com/tools/langflow): MIT-licensed visual builder for AI agents and MCP servers with a very large GitHub following. - [Botpress](https://theagenticweekly.com/tools/botpress): Customer-support AI agent platform with a free plan and conversation-based paid plans. - [Gumloop](https://theagenticweekly.com/tools/gumloop): Agent builder for teams; plans start at $37 per month with 20k included credits. - [Lindy](https://theagenticweekly.com/tools/lindy): AI 'employee' builder that connects to your tools; Free plan with $50 in credits that last 7 days, then credit-based plans. - [Microsoft Copilot Studio](https://theagenticweekly.com/tools/copilot-studio): Microsoft's platform for creating and managing custom agents, workflows and apps with no code. - [Pydantic AI](https://theagenticweekly.com/tools/pydantic-ai): Python agent framework built on Pydantic types, covering agents, realtime voice, image generation and embeddings. - [Relevance AI](https://theagenticweekly.com/tools/relevance-ai): Platform for specialist AI agents for sales, customer success, marketing and HR, with an embedded deployment team. - [Voiceflow](https://theagenticweekly.com/tools/voiceflow): Platform for chat and voice AI agents for customer experience teams. - [Vercel AI SDK](https://theagenticweekly.com/tools/vercel-ai-sdk): Vercel's TypeScript SDK that gives one API across many model providers, with streaming and agent helpers. ## FAQ ### What is AutoGen? AutoGen's README says the project is no longer actively developed with new features, warns that without ongoing maintenance and security fixes vulnerabilities may remain unaddressed, and links an AutoGen to Microsoft Agent Framework migration guide. The latest release tag we saw is python-v0.7.5 from Sep 30, 2025. ### Is AutoGen free? Free to self-host. Open-source library; costs come from the model APIs you call. Checked 2026-10-25; prices change, so confirm on the vendor's page. ### What license is AutoGen under? Its license: MIT (code) and CC-BY-4.0 (docs), per GitHub. Read from the project's own pages on 2026-10-25. ## What we have not verified - Exact end-of-support dates ## Sources - [AutoGen README](https://github.com/microsoft/autogen) (fetched 2026-10-25) - [Microsoft Agent Framework migration guide](https://github.com/microsoft/autogen) (fetched 2026-10-25) ## How to cite Agentic Weekly, "AutoGen python-v0.7.5: what's new, verdict & setup", last updated 2026-10-25, https://theagenticweekly.com/tools/autogen Keep the Reported or Tested label when you quote the verdict.