Hi everyone,
I’m building AgentLantern, an open-source devtool for CrewAI projects.
The goal is to make CrewAI-based projects easier to understand, document, analyze, and visualize, especially when the project starts to grow with multiple agents, tasks, tools, and configuration files.
AgentLantern currently provides three main features:
- Lantern Docs: generates a browsable documentation site from your CrewAI project by statically reading the source code and configuration files. No LLM calls, no API keys.
- Lantern Lint: checks CrewAI projects before runtime and helps detect design issues such as missing fields, broken references, or configuration problems.
- Lantern Play: runs the project and opens a pixel-art runtime viewer where you can observe agents working, delegating, calling tools, and producing outputs.
The project is still early, and I’m mainly looking for feedback from CrewAI users: what would be useful, what is missing, and what kind of problems you face when working on real CrewAI projects.
Docs: AgentLantern
I’d be happy to discuss here if anyone has thoughts, suggestions, or wants to test it on a CrewAI project.