| What it does | AI operational intelligence for agents and AI products
| AI coding spend and usage analytics for teams
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2024
| Not given
|
|---|
| Based in | US
| Not given
|
|---|
| Pricing model | Free trial
| Freemium
|
|---|
| Pricing | Not given
| Community (self-hosted): free for up to 5 seats under Community License. Managed (hosted): free for 5 seats, then $1 per active developer per month.
|
|---|
| Key features | - Agent trace debugging with step-by-step timeline view
- LLM judge evaluations on production traces with templates
- Token spend tracking by model, agent, tool and user
- AI Assistant for natural language questions over data
- Dashboard templates for traces, analytics and spend
- OpenTelemetry native ingestion
- Correlation of traces, events and user sessions
- Silent regression detection with daily quality comparisons
- Cost leak identification from failing tools and retries
- User journey analysis joining traces with funnels and events
| - AI spend attribution per pull request and issue, showing whether work merged
- Cost forecasting showing where month's bill will land at current pace
- Alerts for developers near Claude session or weekly limits
- Seat utilization visibility showing barely-used seats
- Cost breakdown by person, tool, and model with token and latency estimates
- Device and agent configuration health reporting
- Support for local runtimes like Ollama and LM Studio
- GitHub integration to match AI usage to work and pull requests
- No keystroke surveillance, browser capture or network interception
|
|---|
| What makes it different | - Catches AI failures that don't throw errors, like silent regressions and cost leaks
- One platform connecting traces, evals, spend and product analytics for comprehensive understanding
- AI Assistant to ask questions in plain English instead of writing queries
- Compare changes against production evidence rather than demos
- Integrations with major AI frameworks without code changes to production tools
| - Unified dashboard across Claude, Cursor, Codex, and GitHub Copilot instead of separate tool dashboards
- Open-source and self-hosted option under Community License for data privacy
- Cost attribution to actual work via GitHub integration, not just tool-level bills
- Individual developer control over what data is collected and shared
- Designed for privacy-conscious teams with no keystroke or browser monitoring
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 18 ● no change since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 0 | 2 |
| Citation Flow (Majestic) | 15 | 20 |
| Referring domains (Majestic) | 6 | 12 |