Latitude is an observability and quality platform for AI agents. It helps developers find and fix failure modes before they reach production.
Most tools give you logs. Latitude gives you issues: failure modes with states and evals attached.
This is the 8th launch from Latitude. View more
Latitude
Launched this week
Open-source AI agent monitoring platform. Latitude automatically detects all the ways your agents fail at scale, and gives your coding agent the tools to fix it.
Free
Launch Team / Built With
Latitude
Hey there, it's Cesar, founder of Latitude.
Until now, companies have focused on collecting quantitative data about their products: user counts, churn rates, conversion. Qualitative insight was reserved for corporates who could afford to hire an agency. But agents changed that. We have the single most valuable source of knowledge about our product sitting right in front of us, and we're not using it. No one at your company talks to your users as much as your agent does. Latitude exists to tap into that.
Latitude does 3 things:
1. See what your agent really does in production
Latitude clusters thousands of conversations into one clear picture: what people ask for, and where they hesitate, escalate, or drop off.
2. Catch what's breaking before users do
When your agent keeps failing the same way, Latitude collapses those moments into one signal: the problem, how often it fires, and why. It detects issues automatically, or you set your own. Either way, you hear about problems first, and evals are created automatically for each signal.
3. Fix it without leaving your editor
The MCP server brings your signals, traces, and searches straight into your coding agent. Turn real failures into a dataset and verify the fix worked before you ship.
Latitude is open source and MIT licensed. Try it at latitude.so
@heycesr The debugging angle for AI agents is clever. Did you start with observability/logging first, or did you build this after seeing specific failure patterns your team kept hitting? Wondering what the biggest debugging blind spot was.
Per-turn token cost breakdown is exactly what's missing from most setups.
Can you see which specific tool calls or subagents are the worst offenders, or is it more of an aggregate view?
Latitude
@boyuan_deng1 you can see specific costs per tool calls and subagents, and we also have a dedicated dashboard for tool calls, where you can see duration, error rate, number of times called...
Triforce Todos
Congrats on the launch!
Does the install track historical sessions too, or only sessions going forward from when you run the command?
Latitude
@abod_rehman only sessions going forward. Time from installation to first trace is very fast, usually < 5 minutes!
Really love that Latitude is open source and MIT licensed, but for teams with strict compliance needs, does self-hosting keep all conversation data fully on-premise?
Latitude
@crystalmei yes
The "gives your coding agent the tools to fix it" line is what I'd want to see in practice — most observability tools stop at surfacing the failure mode. When Latitude clusters a set of failures, how does that get back into the coding agent: an MCP server, a CLI, or a generated eval/test the agent runs against? And since it's open source, can I self-host so the production conversation traces stay in my own infra, or does evaluation route through your hosted backend?
For teams running Claude Code across multiple repos does this give you a unified view or is it siloed per project?
Latitude
@alexander_gray3 This is a discussion we've had internally many times. Now you have a unified view, but you can use the tags (each repo has a different tag) to filter and see the metrics for one single repo.
The clustering of conversations into discrete failure modes is the clever part. Most observability tools dump raw traces and leave you to find patterns yourself. We've spent time manually sifting logs to spot recurring failures. How does the automatic issue detection work? Does it use embedding clustering on trace outputs, or is there a rule-based approach?