ai-agent

Latitude: AI Monitoring

Monitor AI errors with Latitude, for startup founders, backed by 4.4k+ GitHub stars

From the repo · “Open-source observability for AI agents. Find where your agents fail, dispatch your coding agent to fix it, and verify the fix against real traces.”

4,734 stars+12★ this week403 forksTypeScriptGuide quality 8/10 · reviewed Jul 12Updated 10/22/2026100% free · open source
What it does

Latitude monitors AI errors and provides insights to improve model performance, specifically designed for startup founders to track and resolve AI issues efficiently.

When to use it
  • •When deploying AI models to production and wanting to monitor their performance in real-time
  • •When experiencing unexplained errors or inconsistencies in AI model outputs
  • •When needing to compare and contrast different AI model versions or configurations
Ready-to-paste prompt
Run `latitudectl models create --name my-model --type huggingface --endpoint https://my-model-endpoint.com` to create a new AI model configuration in Latitude
Heads up: Make sure to have Node.js (version 16 or higher) and npm installed on your system, as Latitude requires these dependencies to run
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/latitude-llm && curl -fsSL https://workflowstacks.com/api/skills/latitude-llm/claude-skill -o ~/.claude/skills/latitude-llm/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Latitude: AI Monitoring works
Codeflow
Free to inspect

Latitude: AI Monitoring is a very large TypeScript project (~797k lines across 6041 code files, plus 174 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~797k lines · 6041 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js · Docker
Needs API keys (.env)
TypeScript 80%Python 11%Rust 8%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    package.json
    Dependencies and the commands it exposes
  4. 4
    .env.example
    The API keys and settings you must provide
  5. 5
    examples/migrations/linguaai-v1-to-v2/README.md
    A worked example — copy this to get going
What's in each folder
apps/Sub-packages / plugins1269 files
packages/ui/Frontend / UI251 files
packages/cli/Command-line entry points75 files
docs/Documentation206 files
examples/Examples you can copy29 files
packages/domain/Package1823 files
packages/sdk/SDKs / client libraries1681 files
packages/platform/Package946 files
READMEHas testsDocumentedCI checksDocker readyExamples includedMIT licenseUpdated this month
Quick Actions
Details
Creator
latitude-dev
Language
TypeScript
Category
ai-agent
Published
6/28/2024

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/latitude-llm.svg)](https://workflowstacks.com/skills/latitude-llm?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.