Skip to main content
📖 The AI Tool Bible
PySpur preview image
PySpur logo

PySpur

Not yet source-checked

Open-source agent builder with a drag-and-drop canvas, Python escape hatch, and a built-in test harness.

Machine-drafted from the vendor's site · not yet source-checkedProfile updated Link checked How we rate

FreemiumAgentsMulti-model7.0 / 10

In short

PySpur is an open-source, self-hostable agent builder featuring a drag-and-drop canvas, Python support, and built-in testing for rigorous evaluation.

Best for

Pick PySpur if you want a self-hostable, git-friendly agent builder that takes evaluation as seriously as orchestration.

Skip if

Skip it if you need a hosted, zero-ops SaaS today or a deep catalog of pre-built integrations.

PySpur is an open-source framework for building, testing, and deploying AI agents. It pairs a visual drag-and-drop workflow editor with first-class Python so engineers can sketch a pipeline graphically, then drop into code for custom tools, evaluators, or nodes. Agents are exported as JSON, which makes them easy to diff, code-review, and roll out via the same git flow you already use for the rest of your stack.

The differentiator is the emphasis on the iteration loop. Most agent frameworks (LangGraph, CrewAI, etc.) leave you to bolt on your own test rig; PySpur ships test-case definition, batch evaluation, and failure inspection in the core product, which is closer in spirit to LangSmith than to a pure orchestration library. It's Apache-2.0 licensed with 5,500+ GitHub stars, installs via pip, and runs equally well on a laptop, a cloud VM, or your own hardware. A managed Cloud tier and Python/TypeScript SDKs are flagged as forthcoming.

PySpur is model-agnostic: you wire up whichever LLM provider the node calls, so you can mix Claude, GPT, open-weight models, or local Ollama within one graph. It's a sensible pick for teams that want a self-hosted alternative to closed visual builders like Flowise Cloud or Relevance AI, particularly where the agent graph needs to live next to the rest of your application code.

Editor's take

PySpur is one of the more thoughtful open-source agent frameworks because it treats the test loop as a first-class citizen, not a tutorial appendix. The visual-plus-Python model is the right compromise, and Apache 2.0 plus JSON exports keep it from feeling like a walled garden. The trade-off is youth: docs and integrations are still catching up to the big-name competitors.

— The AI Tool Bible editorial team

Pros

  • ✅ Apache-2.0 licensed and pip-installable, runs fully self-hosted
  • ✅ Visual canvas plus Python escape hatch, no lock-in to a DSL
  • ✅ Built-in test cases and failure inspection, not an afterthought
  • ✅ Agents export as JSON so they diff cleanly in git

Cons

  • ⚠️ Managed cloud and official SDKs are still on the roadmap
  • ⚠️ Smaller ecosystem than LangGraph or LlamaIndex
  • ⚠️ Visual builders can hide complexity that bites at scale

Facts

Platforms
api
API available
Yes
Free trial
Yes
Open source
Yes (license: Apache-2.0)
GitHub stars
5,810 (checked Nov 13, 2026)
Last GitHub push
Jun 29, 2026
First commit
Sep 2024
Model used
Multi-model
Package downloads (30 d)
53 · pypi pyspur · checked Nov 19, 2026
Hacker News
4 stories · top 365 points · last Mar 6, 2025 · checked Nov 19, 2026
Earliest Wayback capture
2024-11-21 (earliest archived capture of the site, not a launch date)

Where this tool sits

Use cases

agent-orchestrationagent-evaluationvisual-workflow-builderself-hosted-agentstool-use

Frequently asked

How much does PySpur cost?
PySpur operates on a freemium model. The Basic plan costs $10, the Pro plan is $20, and Enterprise pricing requires contacting sales. The core framework is open-source and Apache-2.0 licensed.
Is PySpur suitable for self-hosting?
Yes, PySpur is designed to be self-hostable and git-friendly. It runs on laptops, cloud VMs, or your own hardware, allowing agents to live next to your application code.
Can I use Python with PySpur?
Yes, PySpur pairs a visual editor with first-class Python support. Engineers can sketch pipelines graphically and drop into code for custom tools, evaluators, or nodes.
Does PySpur support multiple AI models?
PySpur is model-agnostic. You can wire up various LLM providers, including Claude, GPT, open-weight models, or local Ollama, within a single agent graph.
What are the main alternatives to PySpur?
Alternatives include LangGraph, CrewAI, Flowise Cloud, and Relevance AI. PySpur differentiates itself by including test-case definition and batch evaluation in the core product, unlike many orchestration libraries.
See alternatives to PySpur →

Explore related

Reviews