# PySpur-Dev/pyspur

A visual playground for agentic workflows: Iterate over your agents 10x faster

Repository: https://github.com/PySpur-Dev/pyspur
Canonical: https://ross.abutalabs.com/products/pyspur
Homepage: https://pyspur.dev
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: agent, ai, llm, python, workflow, deepseek, framework, gemini, graph, human-in-the-loop, loops, multimodal, ollama, rag, trace, builder, tool, reasoning, agents, llms
Last push: 2026-06-29T17:53:12+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 40, longevity 50
- inputs: {"age_days": 709, "days_push": 65, "days_rel": 526, "gap_med": 0.5, "n_releases_24m": 19}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5778, forks 429 (observed 2026-08-28T04:09:29.525699+00:00)

## What it is
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
- artifact type: framework
- maturity: active
- function: agent-framework, rag, workflow-automation, llm-inference, prompt-engineering, chat-interface, web-framework
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, self-hosted, cross-platform
- tags: 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
- PySpur-Dev/pyspur (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:29.525699+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:52:50.889745+00:00, confidence not recorded.
  - readme: https://github.com/PySpur-Dev/pyspur (fetched 2026-08-28T04:09:29.525699+00:00, sha c57511ac0756)
  - homepage: https://pyspur.dev (fetched 2026-08-29T08:48:29.450233+00:00, sha 65fad27cd5ed)
  - site_page: https://docs.pyspur.dev (fetched 2026-08-29T08:48:29.452931+00:00, sha aa2a9b9d694c)
  - site_page: https://www.pyspur.dev/about-us (fetched 2026-08-29T08:48:29.455352+00:00, sha 7a688cb1db6e)
- Data as of 2026-08-30T08:39:29.467469+00:00.