| What it does | AI agent observability, tracing and evaluation platform
| Catch where AI agents get stuck on your API or MCP server, rank problems by impact, and draft fixes as pull requests
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Not given
| Open source: free. Team: $199/month with 14-day free trial (1 API or MCP service, 25,000 reports/month, 15 coding-agent runs/month). Business: $799/month (up to 3 services, 250,000 reports/month, 60 coding-agent runs/month). Extra coding-agent runs: $6 each.
|
|---|
| Key features | - Trace viewer showing model calls, tool calls, and retrievals
- Cost tracking per step with latency and token counts
- Root cause detection for failures
- Live streaming and replay of agent runs
- Automatic secret redaction before data transmission
- Semantic search across runs and steps
- Support for multiple frameworks and languages
- Evaluations and datasets for quality assessment
- Slack alerts and release gates
- Collaboration and code review tools
| - Session replay for MCP servers to identify failed agent sessions
- Clustering reports by agent goals and workflows
- Priority ranking weighted by frequency, failed workflows, and affected accounts
- Claude Code generates pull requests with tests
- Review queue with diff, tests, agent reports, and evidence
- Isolated git worktree prevents unauthorized code push
- Schema validation and rate limiting for feedback
- Open Agent Feedback Protocol with TypeScript and Python SDKs
- GitHub integration for draft PR creation
|
|---|
| What makes it different | - One-line setup with automatic detection of model and tool calls
- Identifies first failure point instead of surface errors
- Per-step cost visibility with no monthly surprises
- Automatic secret stripping keeps sensitive data local
- No agent code rewriting required
| - Only AI agent failures on successful HTTP responses get detected and ranked
- Automated pull request drafts with your approval required before shipping
- Session replay captures failures even when agents don't report them
- Pay only for coding-agent runs, not feedback submission
- Open protocol and SDKs can be self-hosted at no cost
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | 1 ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 1 |
|---|
| Citation Flow (Majestic) | 22 | 14 |
|---|
| Referring domains (Majestic) | 1 | 4 |
|---|
Uncoil
Backloop