Skip to content

AgentLantern

AgentLantern is a suite of developer tools for multi-agent LLM systems.

Point it at any agent project — it detects the framework automatically, documents the architecture, checks design issues, and can visualize supported crews while they run.


Lantern Tools

AgentLantern is organized around a small CLI surface. Each command does one job and can be used from the root of an agent project or with an explicit project path.

bash
lantern web      # generate and serve docs for the current project
lantern lint     # inspect project quality without LLM calls
lantern play     # open the live animated run viewer

Supported Frameworks

Frameworklantern docslantern lintlantern play
CrewAI✅ Full analysis✅ 13 rules✅ Live runtime
Google ADK✅ Full analysis✅ Common rules✅ Live runtime
LangGraph✅ Full analysis✅ Graph rules✅ Live runtime
AutoGen✅ Full analysis✅ Common rules✅ Live runtime
Smolagents✅ Full analysis✅ Common rules✅ Live runtime
OpenAI Agents SDK✅ Full analysis✅ Common rules✅ Tracing runtime
Additional Python ecosystems✅ Dedicated analysis✅ Common rules✅ Lifecycle runtime
Mastra / Vercel AI SDK / JS/TS✅ Dedicated analysis✅ Common rulesProcess + logs
Semantic Kernel .NET/Java✅ Dedicated analysis✅ Common rulesProcess + logs
Other Python or JS/TS frameworksGeneric analysis✅ Common rulesBest effort

Framework detection is automatic — no configuration needed.


Installation

bash
pip install "agentlantern @ git+https://github.com/brellsanwouo/agentlantern.git"
# or (recommended)
uv tool install git+https://github.com/brellsanwouo/agentlantern.git

Verify:

bash
lantern --help

See the full Installation guide.

Released under the MIT License.