| What it does | The execution replay engine for AI agents
| Open-source agent harness engineering platform built on OpenTelemetry
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2024
|
|---|
| Based in | IN
| IN
|
|---|
| Pricing model | Freemium
| Open source
|
|---|
| Pricing | Free plan includes 1,000 traces/mo and 7-day retention. Starter at $29/mo adds 10,000 traces/mo and 30-day retention. Pro at $99/mo includes 50,000 traces/mo, 90-day retention, and unlimited fork replays. Teams at $399/mo provides 500,000 traces/mo, 365-day retention, up to 10 users, and 1,000 prove
| Open source (Apache 2.0): Free self-hosted with unlimited usage. Enterprise Edition: Contact sales for pricing. Cloud: Coming soon.
|
|---|
| Key features | - Record every LLM call, tool call, and error with one decorator
- Step-by-step replay of agent executions
- Fork and cascade-replay from any failing step
- Prove-the-fix verification before shipping
- Runtime guardrails and circuit breakers
- CI/CD regression gates
- Multi-agent session tracking and topology graphs
- Automatic hallucination and drift detection
- Semantic search across agent runs
- PII auto-redaction on every plan
| - OpenTelemetry-native LLM tracing for every call, tool, and retrieval
- Agent evals with LLM-as-a-judge and heuristics
- Prompt Hub for versioning and deployment without code changes
- Guardrails for prompt injection, jailbreak, and sensitive topic detection
- Vault for encrypted API key management
- OpenGround for side-by-side LLM model comparison
- GPU monitoring for utilization, memory, temperature, and power
- Coding agent observability for Claude Code, Codex, and Cursor
- Cost tracking and latency monitoring
- 56+ integrations with LLMs, frameworks, and vector databases
|
|---|
| What makes it different | - Turns production failures into regression tests that fail builds when behavior breaks
| - Self-host free forever under Apache 2.0 with unlimited usage and no per-trace fees
- OpenTelemetry-native traces exportable to Grafana, Datadog, or any OTLP backend
- Zero-code instrumentation with eBPF controller, native SDKs, or GPU collector
- Unified platform for traces, evals, guardrails, and prompts on the same production data
- Full data ownership and no vendor lock-in with exportable OpenTelemetry traces
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 5 ▲ +2 (up) since last check | 65 ● no change since last check |
|---|
| Trust Flow (Majestic) | 20 | 23 |
|---|
| Citation Flow (Majestic) | 25 | 39 |
|---|
| Referring domains (Majestic) | 115 | 483 |
|---|
Retrace
OpenLIT