| What it does | The agent observability and evaluation platform.
| AI agent testing and evaluation that turns unpredictable agents into reliable production systems
|
|---|
| Stage | Established
| Growing
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| NL
|
|---|
| Pricing model | freemium
| freemium
|
|---|
| Pricing | Not given
| Free Developer plan forever with 50k events/month. Growth plan at €29/core-seat/month with 200k included events, then €5 per 100k additional events. Storage €3/GB beyond 30-day included retention. Enterprise with custom pricing.
|
|---|
| Key features | - Trace observability with OpenTelemetry compliance
- Comprehensive evaluation framework for span, trace, and session evals
- Alyx AI engineering agent for debugging and fixing issues
- Agent-first debugging for coding agents
- ADB datastore for GenAI traces in open formats
- Phoenix open-source platform for local-first tracing and evaluation
- Online evaluations on production traces
- Integration with 40+ models, frameworks, and AI tools
- Built on OpenInference and OpenTelemetry standards
- Certified security and compliance including SOC 2, ISO, PCI, GDPR, HIPAA
| - Agent simulations with simulated users
- Red teaming and adversarial testing
- LLM-based evaluation and scoring
- Full production observability and tracing
- Prompt versioning and A/B testing
- Voice agent simulation and testing
- Multi-modal evaluation
- OpenTelemetry native instrumentation
- Claude Code usage tracking
- Enterprise SSO and RBAC
|
|---|
| What makes it different | - Built by founders of OpenInference, the leading open standard for GenAI observability
- Signal surfaces what matters, uncovers root causes, and generates review-ready fixes automatically
- Processes 1 trillion spans and runs 1 billion evals per year at scale
- Flexible deployment with data staying under customer control
- Open-source-first approach with local-first option via Phoenix
| - Works framework-agnostically with any agent framework without rewrite
- Simulations with real user behavior from scenario descriptions
- Fully automated testing from PM goals to pull requests with Langy
- Self-hosted, hybrid, or cloud deployment with full control
- Production traces queryable at search speed with AI search
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 78 ● no change since last check | 53 ● no change since last check |
|---|
| Trust Flow (Majestic) | 34 | 25 |
|---|
| Citation Flow (Majestic) | 54 | 45 |
|---|
| Referring domains (Majestic) | 5527 | 852 |
|---|