Tool overview
Latitude is listed under AI Governance Safety & Evaluation AI tools.
What is Latitude?
Latitude is an open-source AI agent observability platform focused on production behavior and reliability. It collects OpenTelemetry-compatible traces, discovers recurring failures, creates signals and evaluations, alerts teams, and can dispatch coding agents such as Claude Code or Cursor with evidence to implement fixes.
Best for
Teams operating production agents whose failures outgrow manual review
Who is it for?
Decision note
Accepted for Preview after independent V411 official-source research. Apply only after failures = 0, warnings = 0, unmapped = 0, and all proposed changes are reviewed.
Key features
Agent-native traces and conversation intelligence
Automatic behavior, failure, and signal discovery
Evaluations, annotations, alerts, and regression checks
Coding-agent dispatch through MCP and integrations
Use cases
Monitor production AI agents
Discover repeated conversational failures
Create evaluations from real incidents
Send fix context to coding agents
Pros
- MIT-licensed and self-hostable
- OpenTelemetry-compatible ingestion
- Connects detected issues with remediation workflows
Cons
- Advanced cloud limits require a paid plan
- Automated remediation still needs code review
Limitations
Signal quality depends on trace coverage and annotation practice
Integration breadth is smaller than older observability platforms
Pricing details
Billing options
Pricing note
The Starter cloud plan is free with 20,000 credits per month, 30-day retention, and unlimited seats. Pro costs $99 per month with 100,000 credits and 90-day retention. Enterprise pricing is custom, and self-hosting is free under MIT.
Supported languages
- English
Integrations
OpenTelemetry
OpenAI
Anthropic
LangChain
Please log in to join the discussion.