MetaGPT
byDeepWisdom (FoundationAgents)Open sourceMIT (opens in a new tab)listed Jun 3, 2026
MetaGPT is an open-source (MIT) Python multi-agent framework that assigns software-company roles such as product manager, architect, and engineer to LLM agents following standard operating procedures. Activity has slowed: the last PyPI release was 0.8.2 in March 2025 and the last commit was in January 2026. Its team at DeepWisdom now focuses on Atoms (formerly MGX), a hosted app builder.
Freshness note: AI-agent behavior can change after model releases, client updates, pricing changes, or new default settings. Use the aggregate score as a historical baseline and check recent reviews plus model/runtime context before deciding.
- Pricing
- Open-source and free to self-host; you pay for your own LLM API keys
- Model backbone
- Bring your own model
- Setup complexity
- Complex setup
- Last reviewed
- Awaiting reviews
- Recent signal
- Awaiting reviews
Build MetaGPT? Get a claim link →
What reviewers consistently say.
No reviewer patterns for MetaGPT yet.
No consensus yet
Once people review MetaGPT, Ruling will summarize recurring strengths and limitations here.
Write the first reviewNo community reviews yet.
Used MetaGPT? Your field report can seed the first Ruling signal.
Be the first to review MetaGPT
Share where it worked, where it failed, and whether it deserves a spot in a real team workflow.
Write a reviewSimilar agents.
Frameworks & Indie agents you might also consider, sorted by aggregate score.

AutoGPT is Significant Gravitas's agent platform. The current AutoGPT Platform, source-available under the PolyForm Shield license, lets users build agent workflows and run them in the hosted cloud or self-hosted. The hosted product centers on Otto, an assistant that hands work to specialist Experts for tasks like content, sales research, and scheduling. The original 2023 autonomous agent remains as MIT-licensed AutoGPT Classic.
Open-source orchestration runtime for agentic workloads. Defines tasks, workspaces, network policies, and model configuration, with sandboxed execution, resource limits, and suspend/resume support. Runs on Agent Substrate and provides Kubernetes deployment manifests for operating agent fleets.
BabyAGI is Yohei Nakajima's experimental Python framework for self-building autonomous agents. The current version is built on functionz, which stores functions and their dependencies in a database and adds a web dashboard for managing and logging them. The original 2023 task-loop BabyAGI is preserved in the babyagi_archive repo. The author says it is not meant for production use.
