What is Latitude and what does it do?

An open-source observability platform for AI agents: one line of telemetry captures every trace, failing traces are auto-grouped into tracked signals, fixes are dispatched to coding agents, and the fix is verified against real traces.

How do I start sending traces to Latitude?

Install @latitude-data/telemetry, construct Latitude with your API key and project slug plus an instrumentation such as openai, and supported LLM calls appear as traces. Python and any OpenTelemetry-compatible runtime are also supported.

What does Agent Dispatch do?

It hands failing traces to coding agents like Claude Code or Cursor with full context, sample traces, and a deep link. The agent writes the smallest correct fix and opens a PR, and Latitude replays it against the real failing traces so fixed failures do not come back.

What does Latitude cost?

The README states you can use Latitude for free, including 20K credits per month, 30-day data retention, and unlimited seats. You sign up at latitude.so and grab an API key and project slug to get started.

Can I use Latitude from my coding agent instead of the UI?

Yes. The README says everything in the UI is also available through an MCP server and a CLI, and it suggests pasting a setup prompt into Claude Code, Cursor, Windsurf, Codex, OpenCode, or another coding agent to install the latitude-setup skill.

Is there a Jev integration in Latitude?

None is mentioned. The digest's README covers observability, signals, agent dispatch, and evals without referencing Jev or TypeSafe; this import is listed under the logicrw community list and makes no integration claim.

Which providers and frameworks does the telemetry support?

The README lists OpenAI, Anthropic, Amazon Bedrock, the Vercel AI SDK, and LangChain, describes Latitude as provider-agnostic, and notes that any OpenTelemetry-compatible runtime can send data. Python setup and provider guides are in the start-tracing docs.

Jev directory

CommunityJev Tools & CLIs

Latitude

Latitude is an open-source observability platform for AI agents: one line of telemetry captures traces, failing traces group into tracked signals, and fixes are dispatched to coding agents and replayed against real traces.

See highlights Open github.com

Stars: 4.7k
Language: TypeScript
License: MIT
Reading time: 2 min
Published by: Community
Author: Latitude
Last verified: Oct 2026

latitude-dev/latitude-llm

Organization repository on GitHub

View on GitHub

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.

Forks: 402
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

Tagscommunity catalog-import logicrw observability evals agents

Works forJev for Evaluation Jev for Verification Jev for Code

Used inJev for Software & DevTools

Languages: TypeScript Python
Platforms: MCP CLI
Capabilities: Open sourceSelf-hostedRequires API key

Highlights

Free tier: 20K credits per month, 30-day data retention, and unlimited seats, per the README.
Agent Dispatch hands failing traces to Claude Code or Cursor and replays the resulting fix against real traces.
MCP server and CLI expose everything the UI can do, according to the README.
Setup: npm install @latitude-data/telemetry, construct Latitude with an API key and project slug, then await latitude.shutdown().
Provider-agnostic telemetry spans OpenAI, Anthropic, Bedrock, Vercel AI SDK, LangChain, and OpenTelemetry ingest.

Quickstart

bash

npm install @latitude-data/telemetry

Watch out

Reviewed against the truncated README on 2026-10-15. The 20K-credits free tier is the README's own statement, its integrations list is cut off mid-sentence, and the repository contains no Jev or TypeSafe material, so the logicrw community-list placement is the only link.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

X: Microsoft-Decision-1 against Jev on a private eval

X: Vals AI's independent evaluation of Jev

X: An eval suite for System One models

X: Jev and Laya play chess instead of benchmarks

From the Jev guides

Original write-ups on what this entry is for.

Jev at home: voice pipelines, Assist routing, and sentinels

Oct 16, 2026

How Home Assistant conversation agents, macOS voice pipelines, and an advisory sentinel put a fast typed decision in the loop — one call per utterance, thresholds in code, and a daily token budget.

Jev Tools & CLIs#home-assistant#voice#automation

Read article

Search visibility, audited by decisions

Oct 16, 2026

Jev-based SEO tools split the crawl from the call: deterministic crawlers count and parse, while typed judgments rank fixes, place internal links, score search results, and track AI-answer mentions — with costs and caveats attached.

Jev Tools & CLIs#seo#search-visibility#audits

Read article

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.

Jev Tools & CLIs#gateway#vercel#cloudflare

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Latitude

Highlights

Quickstart

Questions about this entry

What is Latitude and what does it do?

How do I start sending traces to Latitude?

What does Agent Dispatch do?

What does Latitude cost?

Can I use Latitude from my coding agent instead of the UI?

Is there a Jev integration in Latitude?

Which providers and frameworks does the telemetry support?

Reactions & coverage

More Jev resources like this

From the Jev guides

From the Jev AI model community