AgentFlow

Repository facts

Stars

2,060

Forks

239

Open issues and pull requests

16

Primary language

Python

License

MIT License (MIT)

Owner

lupantech · Personal account

Created

Sep 27, 2025

Last push

Feb 8, 2026

Topics

• agentic-ai
• agentic-systems
• llms
• llms-reasoning
• multi-agent-systems
• reinforcement-learning
• tool-augmented

Rank #3,576 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Related projects

Projects that share this one’s GitHub topics.

• 8,686

  Rank 8,686: christopherkarani/Swarm

  Type-safe tools, on-device inference, multi-agent workflows, memory, and guardrails, in one Swift-native runtime

  584 starsSwiftMITLast push Oct 2, 2026

• 374

  Rank 374: google/adk-python

  An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

  21,900 starsPythonApache-2.0Last push Oct 18, 2026

• 5,534

  Rank 5,534: cognizant-ai-lab/neuro-san-studio

  A playground for neuro-san

  1,163 starsPythonApache-2.0Last push Oct 16, 2026

• 750

  Rank 750: OpenPipe/ART

  Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and…

  10,807 starsPythonApache-2.0Last push Oct 15, 2026

• 882

  Rank 882: oumi-ai/oumi

  Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

  9,403 starsPythonApache-2.0Last push Oct 15, 2026

• 4,066

  Rank 4,066: google/adk-java

  An open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

  1,753 starsJavaApache-2.0Last push Oct 18, 2026