Open-source devtool for AI agent projects [P]

Hi everyone,

We are building AgentLantern, an open-source devtool for AI agent projects.

The idea is simple: as agent-based projects grow, it becomes harder to understand how agents, tasks, tools, and configuration files are connected. AgentLantern aims to make these projects easier to document, analyze, validate, and visualize.

I started with CrewAI support, but the goal is to progressively extend AgentLantern to other agent frameworks.

AgentLantern currently provides three main features:

• Lantern Docs: generates browsable documentation from source code and configuration files, without LLM calls or API keys.
• Lantern Lint: statically checks agent projects to detect design or configuration issues before runtime.
• Lantern Play: runs the project and opens a pixel-art runtime viewer to observe agents working, delegating, calling tools, and producing outputs.

The project is still early, and I’m mainly looking for feedback from people building with AI agents, multi-agent systems, or devtools.

here is a demo video showing the execution of a multi-agent system: 3_mins_Video

Docs: https://brellsanwouo.github.io/agentlantern/

we’d be happy to hear your thoughts.