| What it does | AI operational intelligence for agents and AI products
| The model training platform for AI teams
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2024
| Not given
|
|---|
| Based in | US
| Not given
|
|---|
| Pricing model | Free trial
| Freemium
|
|---|
| Pricing | Not given
| Free: $0/month with $50 in credits once, 1 seat per project, every feature, console, CLI and MCP server, community Discord support. Pro: $120/month with $120 in credits every month, unlimited seats, priority support. Enterprise: Custom pricing, contact for details.
|
|---|
| 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
| - OpenTelemetry agent tracing and trace import from Langfuse, LangSmith, Braintrust and Galileo
- Generated evals and Agent Optimizer runs that return scored code diffs
- Data Workshop with dataset preparation and quality checks
- Model training with recommended settings for LoRA or full fine-tuning
- Benchmarks against your current model on the same eval set
- Hosted OpenAI-compatible inference and downloadable model weights
- Console, CLI and MCP server access
- OpenAI-compatible API for trained models
|
|---|
| 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
| - Own your trained models with downloadable weights and checkpoints
- Zero third-party training with data never leaving your pipeline
- Open source and self-hostable with Docker Compose
- Built by security and defense intelligence pioneers
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 18 ● no change since last check | 44 ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 10 |
|---|
| Citation Flow (Majestic) | 15 | 35 |
|---|
| Referring domains (Majestic) | 6 | 201 |
|---|
Overmind