| What it does | See where your AI coding agent's tokens go, cut the waste without breaking the prompt cache, and get a receipt for every saving
| Open-source runtime for computer-use agents
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Open source
|
|---|
| Pricing | Free for open source (Wrapped, all fixes with undo, receipt, skill, plugin, MCP server). Team: $30 per developer, or 10% of verified savings, whichever is lower (spend by engineer, cost per merged PR, CI gate). Enterprise: contact for self-hosted, SSO, finance exports, procurement-grade reports.
| Not given
|
|---|
| Key features | - Session log analysis with token pricing breakdown
- Categorized spending attribution by startup context, tool output, sub-agents, and cache rebuilds
- Safe automatic fixes for output trimming and cache countdown
- Undo capability for all changes
- Receipt comparing cost-per-commit before and after with 90% confidence range
- Shareable card with visualization of token usage
- Command output trimming to reduce context bloat
- Cache expiration countdown in status line
- MCP server integration for any agent
- Claude Code plugin with skill and MCP server
| - Works with any OpenAI-compatible model
- Ready-wait mechanism instead of fixed sleeps
- Batches actions and bounds model calls
- Desktop pause, resume and fork with memory
- MCP server for Claude Code and Cursor
- Graded rollouts for computer-use RL
- Works with full desktops
- Supports multiple sandbox providers
|
|---|
| What makes it different | - Reads actual logs your agent already keeps, not a third-party service
- Fixes only trim new content without rewriting cache to preserve prompt optimization
- Open source under Apache 2.0 with no incentive to make you spend more tokens
| - 1.48x faster than Anthropic's computer-use reference loop on the same model
- 19 points more success than OSWorld's Qwen agent at same speed
- Reduces rollout time by 40-53% by eliminating unnecessary waiting
- Published benchmarks run same model on same desktops with reproducible results
- Works with any model and sandbox provider
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 0 | 0 |
| Citation Flow (Majestic) | 0 | 0 |
| Referring domains (Majestic) | 0 | 0 |