| What it does | Air traffic control for your coding agents
| See where your AI coding agent's tokens go, cut the waste without breaking the prompt cache, and get a receipt for every saving
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Open source
| Freemium
|
|---|
| Pricing | Not given
| 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.
|
|---|
| Key features | - Task queuing with dibs run wrapping commands
- Real-time job status board for all agents
- Memory and disk resource monitoring
- Agent-to-agent messaging with dibs tell and dibs say
- Human approval workflow for irreversible actions
- Browser access via end-to-end encrypted relay at app.dibs.cc
- MCP client support for Claude with read-only or action modes
- Multi-machine job distribution with --anywhere flag
- Job scheduling at specific times with dibs later
- API rate limit sharing with quota buckets
| - 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
|
|---|
| What makes it different | - Prevents agent collisions with deterministic turn-taking on shared resources
- Automatically manages machine memory and disk to keep builds running
- Agents communicate peer-to-peer while humans only handle critical decisions
- Fully open source with no per-seat or subscription fees
- Works across multiple machines with a single encrypted board
| - 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
|
|---|
| 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 |
|---|
Tare