Agent reliability simulator — chaos engineering for AI agents
floww is a LLM eval & observability product. It focuses on testing and improving the reliability of AI agents through simulation and chaos engineering techniques. It is built as an open-source project for AI engineers and researchers. floww is open source under the MIT license. It runs on the web and the command line.
sushaan-k builds and maintains floww, and the product first shipped in 2026. Development happens publicly on GitHub with 14 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — floww occupies a relatively distinct niche. Key capabilities include agent simulation, chaos engineering, and reliability testing.
Latest indexed changes and source events
Other apps tracked under the same category.
