GH Repository · PySpur-Dev
pyspur
A visual playground for agentic workflows: Iterate over your agents 10x faster
- stars
- 5,785
- 30-day movement
- +31/day
- Related entries
- 60
- Connections
- 3
dockeragent-appTypeScriptbuilderllmstraceagentaireasoningllmpythonframeworkworkflowhuman-in-the-loopragloopsdeepseektoolmultimodalgeminigraphagentsollama
PySpur is a visual playground for building and iterating on agentic workflows, described as letting you iterate over your agents 10x faster. Its topics indicate graph-based workflow building with loops, human-in-the-loop steps, RAG, multimodal inputs, tracing, and support for multiple LLM providers including DeepSeek, Gemini, and Ollama.
You want to design and refine agent workflows visually instead of writing and rerunning orchestration code each iteration.
Use it to
- Build agent workflows on a visual graph canvas
- Add human-in-the-loop approval steps
- Trace agent runs to debug behavior
- Prototype RAG pipelines with different LLM providers
- Test loops and reasoning steps in agents
For Developers building and iterating on LLM agent workflows
- Role
- agent-app
- Language
- TypeScript
- Licence
- Apache-2.0
- Forks
- 428
- Open issues
- 29
- Last push
- 2026-06-29
- Latest release
- v0.0.1 · 2025-01-03
topicsagentsllmworkflowvisual-builderragtracing