| What it does | Multiplayer coding harness for teams to chat, build and run bots with every AI coding agent
| A harness-agnostic framework for AI coding tools
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Open source
|
|---|
| Pricing | Free: A personal sandbox with chat, build and bots, every agent CLI, and integrations included, no credits. Pro: $50 per user per month (early-access promotional pricing; standard price is $200), billed monthly, with unlimited seats, team sharing, your own cloud or dedicated machine, $10 of AQ credi
| Not given
|
|---|
| Key features | - Chat with agents about code, data and tools with answers as tables, charts and pages
- Isolated worktrees per task with live preview and pull request review
- Standing bots that wake on schedule or event with monthly spend caps
- Crews with independent agent review
- Live multiplayer terminals and previews shared with the team
- Support for 11 coding agents: Claude Code, Codex, Cursor, Kimi Code, Grok, Antigravity, Devin, Muse Code, OpenCode, Command Code and Pi
- Integrations with Linear, GitHub, Slack, Gmail, Google Calendar, Granola, Sentry, Mercury, Vanta and Stripe
- Memory shared across agents searchable by the whole team
- API, webhooks and MCP server for automation and third-party tools
- Run on private AQ-managed sandbox, dedicated machine, or your own cloud infrastructure
| - Configure plugins, skills, MCP servers, and hooks in a single harness.yaml file
- Observatory: monitor every session, tool call, and minute of activity
- Memory: persistent knowledge graph for AI orientation
- Comparator: run prompts across Claude Code, Cursor, and Copilot side by side
- Import existing configs from multiple AI coding tools automatically
- Share complete setup via single file with teammates
- Harness Parity: verify all connected AI tools end up with identical configuration
- Cross-harness compatibility table showing actual tool capabilities
|
|---|
| What makes it different | - No setup required: start free in a sandbox AQ creates, or move to your own cloud with one click
- Keep subscriptions unmetered: your team's Claude, OpenAI and Cursor accounts are never marked up
- Shared live workspace: the whole team sees the same terminal and preview, not a replay
- Independent agent review: a second agent reviews code without seeing the builder's work
- All agents in one place: Claude Code, Codex, Cursor and 8 more, each signed in with your accounts
| - Import-first approach: reads existing configs from all your tools and converges them before you write YAML
- No marketing gloss: capability table generated at build time from actual adapter code, not hand-maintained
- Portable across tools: single harness.yaml travels with you to every machine and tool
- Open source and free: no cost beyond existing Claude subscription
- Based on open specification: Harness Protocol is vendor-neutral and JSON Schema validated
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 15 ▲ +1 (up) since last check | 16 ● no change since last check |
|---|
| Trust Flow (Majestic) | 5 | 0 |
|---|
| Citation Flow (Majestic) | 33 | 20 |
|---|
| Referring domains (Majestic) | 85 | 11 |
|---|
AQ
Harness Kit