- Home
- AI Prompt Generators
- Latitude
Latitude
What it is
Latitude is an open-source, MIT-licensed platform for improving production AI agents. It captures interactions as spans and groups them into sessions, giving teams a way to review multi-turn conversations and examine providers, models, token use, latency, cost, errors, tool calls, user activity, and agent memory. Semantic search, behavior clustering, and signals help identify recurring failures. Monitors can follow signals, saved searches, or raw traffic and send notifications in-app, by email, or in Slack. Teams can turn failing traces into datasets for local simulation and regression testing, and evaluations can watch live traffic for regressions. Latitude offers managed cloud or self-hosted deployment, including Docker Compose and Kubernetes. Its setup guide names TypeScript and Python SDKs and recommends an OpenTelemetry exporter for other languages. The Starter plan is free and includes 20K credits/month, 30d data retention, unlimited seats, and general channel Slack support. Pro is $99 a month, with 100K credits/month, 90d retention, unlimited seats, and priority support.
For and against
For
- Groups spans into sessions for conversation review.
- Finds recurring failures with semantic search and clustering.
- Monitors can notify by email, in-app, or Slack.
- Regression datasets support local simulation and testing.
- Managed cloud and self-hosted deployment options.
Against
- Starter retains data for 30d.
- Pro costs $99 a month.
- Enterprise pricing is custom and not listed.
The verdict
Latitude combines agent tracing, failure discovery, alerting, and regression workflows in one platform. Its free Starter plan offers a way to begin, while longer data retention and priority support are listed with Pro.
Who it suits
Latitude suits teams building and maintaining production AI agents that need to trace conversations, find repeated failures, and monitor regressions. It offers both managed cloud and self-hosted deployment options.
Plans and prices
Starter
20K credits/month · 30d data retention · unlimited seats · general-channel Slack support
Read 15 Oct 2026 · latitude.so
Pro
100K credits/month · 90d data retention · unlimited seats · priority support
Read 15 Oct 2026 · latitude.so
Enterprise
custom credit volume · custom retention · custom on-premises or cloud deployment · RBAC
Read 15 Oct 2026 · latitude.so
On the record
- Agent dispatch
- When a signal appears or escalates, Latitude can send context and sample traces to Claude Code or Cursor and open a pull request.latitude.so · read 15 Oct 2026
- API and extensibility
- Latitude exposes an API, CLI, MCP server, SDKs, webhooks, and coding-agent skills for programmatic control.docs.latitude.so · read 15 Oct 2026
- Company profile
- LinkedIn lists Latitude as a privately held software-development company founded in 2022, headquartered in San Francisco, with 2–10 employees and an additional Barcelona location.linkedin.com · read 15 Oct 2026
- Compliance
- Latitude's security documentation states it is SOC II certified and says ISO 27001 audit work and GDPR readiness review were in progress, with completion expected by the end of May 2026.docs.latitude.so · read 3 Oct 2026
- Data minimization
- Latitude says its SDKs redact common security-sensitive attributes by default and customers can configure additional redaction patterns.docs.latitude.so · read 3 Oct 2026
- Datasets and regression
- Failing traces can become datasets for local simulation and regression testing before deployment.docs.latitude.so · read 15 Oct 2026
- Deployment
- Latitude is available as managed cloud or self-hosted software, with documented single-machine Docker Compose and Kubernetes cluster deployments.docs.latitude.so · read 3 Oct 2026
- Documentation depth
- The documentation covers tracing, providers, frameworks, agent harnesses, observability, signals, experiments, monitors, datasets, security, deployment, API, MCP, CLI, integrations, and development.docs.latitude.so · read 15 Oct 2026
- Experiments
- Experiments compare traffic slices to measure differences between releases, models, or user cohorts.docs.latitude.so · read 15 Oct 2026
- Failure clustering
- Latitude groups similar failing traces into signals with examples, trends, affected users, and lifecycle states.docs.latitude.so · read 15 Oct 2026
- Failure discovery
- Semantic search, behavior clustering, and signals help teams find and track recurring production failure patterns.docs.latitude.so · read 3 Oct 2026
- Human annotations
- Users can annotate traces, spans, and outputs, with annotations feeding structured signals and evaluations.latitude.so · read 15 Oct 2026
- Integrations
- Documented integrations include OpenAI, Anthropic, Amazon Bedrock, Vercel AI SDK, LangChain, Claude Code, Slack, GitHub, Linear, webhooks, and OpenTelemetry.github.com · read 15 Oct 2026
- Legal entity
- The terms identify the provider as LATITUDE DATA, S.L., incorporated in Spain with Tax ID B09930660 and a Barcelona registered address.latitude.so · read 15 Oct 2026
- License
- Latitude is fully open source under the permissive MIT license.github.com · read 15 Oct 2026
- Limit: ecosystem maturity
- MakerStack describes Latitude’s community as younger and smaller than Langfuse’s, with fewer integrations and tutorials.makerstack.co · read 15 Oct 2026
- Limit: traffic and telemetry
- DiscoverAI cautions that useful signals need representative production traffic, sensitive telemetry requires redaction and retention controls, and automated clustering needs human calibration.discoverai.tools · read 15 Oct 2026
- Limit: usage costs
- MakerStack says credit-based Pro metering and the $20 charge per additional 10K credits can become expensive for high-traffic agents.makerstack.co · read 15 Oct 2026
