| What it does | Open-source agent harness engineering platform built on OpenTelemetry
| Give your coding agents names so you remember who's doing what
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2024
| Not given
|
|---|
| Based in | IN
| US
|
|---|
| Pricing model | Open source
| Free
|
|---|
| Pricing | Open source (Apache 2.0): Free self-hosted with unlimited usage. Enterprise Edition: Contact sales for pricing. Cloud: Coming soon.
| Not given
|
|---|
| Key features | - 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
| - Assigns unique names to agent sessions from customizable rosters
- Integrates with Claude Code, Codex, tmux, and herdr
- Pre-built rosters including Lord of the Rings, Harry Potter, NBA Legends, and more
- End-to-end encrypted cloud storage for cross-machine sessions
- API endpoint for building custom dashboards and integrations
|
|---|
| What makes it different | - 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
| - Notifications and messages from agents are instantly traceable by their assigned names
- Works across multiple machines and cloud environments with optional end-to-end encryption
- Playful roster themes encourage restraint in spinning up too many concurrent agent sessions
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 63 ▼ −2 (down) since last check | 1 ▲ +1 (up) since last check |
|---|
| Trust Flow (Majestic) | 23 | 0 |
|---|
| Citation Flow (Majestic) | 39 | 0 |
|---|
| Referring domains (Majestic) | 483 | 0 |
|---|
OpenLIT
rostr