| What it does | Finds reproducible bugs and runtime vulnerabilities by running your product in a production-like sandbox
| Platform to evaluate, trace, monitor and security test AI agents
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | FR
| Not given
|
|---|
| Pricing model | Free trial
| Freemium
|
|---|
| Pricing | Free for open source projects. Paid plans available for commercial use; specific pricing not listed.
| Free plan at $0 forever with 5,000 spans/month, 25 test runs/month, 100 evaluator executions/month, 2 custom evaluators, 5 datasets, 2 prompts, 5 users, 3 projects, 7-day data retention. Pro plan at $39 per month with 200,000 spans/month plus $5 per 100k additional spans, 100 test runs/month, 5,000
|
|---|
| Key features | - Builds a sandbox that replicates production environment
- Mocks or emulates third-party services like payments, mail and APIs
- Provides failing test for every defect found
- Maps product architecture and reads code for suspicions
- Validates security issues with real exploits against sandbox
- Crawls every link and finds missing routes
- Runs locally or in the cloud
| - Observability and tracing of every LLM call, tool invocation and decision point with latency, cost and token usage metrics
- Evaluation to score agent answers before release against traces that broke
- Simulation to test agents with realistic users before launch
- Red teaming to find injection, tool abuse and data leaks before launch
- Prompt management with versioning and deployment controls
- Online evaluation to score real conversations in production
- Agent Insights to spot patterns and detect drift
- Real-time alerts on cost, latency, errors and quality regressions
- Support for 14+ LLM providers and 12+ frameworks
- MCP server for querying and debugging traces from inside IDE
|
|---|
| What makes it different | - Catches bugs code review misses by running the actual product instead of just reading diffs
- Every bug comes with a reproducible failing test that proves it
- Finds runtime vulnerabilities by firing real exploits against the sandbox
- Tests untested integrations and hard-to-mock async services
- Free for open source projects
| - Single platform that covers the entire AI agent lifecycle from prompt management through production monitoring, instead of scattered tools
- Built on OpenTelemetry standards for native observability across frameworks you already use
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 25 ▲ +1 (up) since last check | 13 ▼ −1 (down) since last check |
|---|
| Trust Flow (Majestic) | 9 | 10 |
|---|
| Citation Flow (Majestic) | 27 | 26 |
|---|
| Referring domains (Majestic) | 63 | 32 |
|---|
heal
Netra