latitude-dev/latitude-llm

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.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 11 minutes ago
Added to GitGenius on September 14th, 2026
Created on June 28th, 2024
Open Issues & Pull Requests: 93 (+1)
GitHub issues: Enabled
Number of forks: 388
Total Stargazers: 4,646 (+0)
Total Subscribers: 15 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 23.7 hours
Mean response time: 64.0 days
90th percentile: 264.8 days
Tracked items: 497

Most active contributors

Sign in to see contributor activity.

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "llm" is answered fastest, typically in under an hour, while "p2" waits about 2 weeks. Only 10% of issues opened in the past year have been closed. Three people close 86% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 26
New in 7 days: 0
Closed in 7 days: 4
Avg open age: 38 days
Stale 30+ days: 2
Stale 90+ days: 0

Recent activity

Opened in 7 days: 0
Closed in 7 days: 2
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • Stale (143)
  • enhancement (75)
  • 🐛 bug (71)
  • llm (68)
  • p1 (63)
  • p2 (22)
  • p3 (16)
  • good first issue (15)

Detailed Description

Latitude is an open-source observability platform for AI agents that enables monitoring, debugging, and automated remediation of agent failures.

The platform addresses the challenge of understanding why AI agents fail and fixing those failures at scale. It captures detailed traces of agent execution, surfaces where errors occur, and integrates a coding agent that can automatically generate and test fixes against real execution traces. This approach combines observability with automated remediation, allowing teams to identify failure patterns and resolve them without manual intervention for each occurrence.

Teams building production AI agents should adopt this tool if they need visibility into agent behavior and want to reduce the manual effort of debugging and fixing failures. It suits projects where agents run at scale and failures need rapid resolution. The platform is particularly valuable when you want to move beyond passive monitoring toward active self-healing systems that can detect and correct their own errors.

The project maintains active development with regular commits and builds passing consistently. The tool is distributed across multiple package ecosystems, with both Node.js and Python implementations available for integration into different technology stacks.