agentleFS
DahunHanDahunHan/lattice/llms.txt

lattice

llms.txt8 starsChanged 7 months agoMITView on GitHub

Open-source AI agent visualization dashboard Lattice automatically scans project files and generates interactive graphs of multi-agent AI workflows. Supports CrewAI, LangGraph, AutoGen, OpenAI Agents SDK, Claude Code, and custom setups. 11 parsers, no AI models used — pure regex-based scanning.

The file

Files
llms.txt
# Lattice

> Open-source AI agent visualization dashboard

Lattice automatically scans project files and generates interactive graphs of multi-agent AI workflows. Supports CrewAI, LangGraph, AutoGen, OpenAI Agents SDK, Claude Code, and custom setups. 11 parsers, no AI models used — pure regex-based scanning.

## Quick Start
npx lattice-agents ./your-project

## Key Features
- Interactive agent workflow graph with color-coded model families
- Workflow pattern detection (Sequential, Split & Merge, Operator, Agent Teams, Headless)
- Live agent monitoring with real-time status and log streaming
- Bidirectional editing — modify agent instructions from the dashboard with diff preview
- Cost tracking per agent based on model rates and runtime
- Agent health checks and git integration
- Export to PNG, SVG, Mermaid, JSON, Markdown table
- Team grouping with visual containers
- Auto-sync file watcher
- Dark/light theme, keyboard shortcuts
- 100% local — no API keys, no telemetry, no cloud

## Links
- GitHub: https://github.com/DahunHan/lattice
- npm: https://www.npmjs.com/package/lattice-agents

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.