PySpur-Dev/pyspur

Health v2 · maintenance only

Adoption not part of the score

5792 stars · 429 forks observed · 2026-09-26

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

PySpur is an open-source visual playground and builder for AI agent workflows, letting engineers build agents via drag-and-drop UI or Python code, run test cases, inspect traces, and deploy. It includes built-in RAG, loops, human-in-the-loop steps, multimodal inputs, and agent evaluation tooling.

Use cases

• build ai agents visually without writing boilerplate
• debug and trace llm agent workflow failures
• run evals and test cases against my agent
• add rag with parsing chunking and embedding to a pipeline
• build workflows with human approval steps
• compare different llm vendors for my agent
• deploy an agent workflow to production

When to choose

• you want rapid visual iteration and debugging of agentic workflows
• you need built-in evals, tracing, and test cases in one place
• you want RAG, loops, and human-in-the-loop out of the box
• you prefer Python extensibility with simple custom node registration

When to avoid

• you need a lightweight code-only agent library with no UI
• your workflow is simple enough that a framework adds overhead
• you require deep customization of the visual editor itself
• you need a fully managed hosted platform rather than self-hosting

Facets

framework · maturity active

agent-framework rag workflow-automation llm-inference prompt-engineering chat-interface web-framework artificial-intelligence large-language-models developer-tools python self-hosted cross-platform visual-builder drag-and-drop human-in-the-loop agent-evals multimodal llm-workflow trace-visualization structured-outputs vector-database yc-startup ai-agents retrieval-augmented-generation automation web-server docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="PySpur-Dev/pyspur")