| What it does | Codebase intelligence platform for AI agents and teams
| Autonomous coding agent for Mac with multi-model AI router, design studio, and desktop assistant
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2024
| Not given
|
|---|
| Based in | Not given
| IL
|
|---|
| Pricing model | Freemium
| Free
|
|---|
| Pricing | Free: 2 public repos, 10 AI answers/month. Pro: $15/month (moving to $20/month in November, or $16/month yearly), includes private repos, auto-sync on every push, security scanning, $5/month AI credits. Teams: $20/seat/month with 3-seat minimum, includes 25 shared repos, shared $5/seat/month credit
| Free with Bring Your Own Keys (BYOK); users provide their own API keys for Claude, GPT, Gemini, Grok, or local Ollama at zero markup
|
|---|
| Key features | - Code health scoring with defect prediction
- Blast radius and change impact detection
- Auto-generated documentation rebuilt on every commit
- Git intelligence: hotspots, owners and coupling detection
- Architecture and decision tracking
- MCP tools for Claude Code and Cursor
- PR bot with change review and test detection
- Security scanning: CVEs, secrets and reachability
- Dead code detection and unused exports
- Change Records with policy enforcement
| - Multi-model Smart Router (Claude, GPT, Gemini, Grok, Ollama) with bring your own keys at zero markup
- Autonomous code review with fresh reviewer verification before presenting diffs
- Canvas-first Design Studio for websites, landing pages, 3D scenes and film
- EXO desktop assistant that takes meetings, watches calendar, answers on iMessage
- iPhone remote control for real-time agent control with WebRTC streams
- Isolated worktrees keep your branch untouched until approval
- iOS Simulator automation driven by the agent
- Opt-in unrestricted model for security research, red teams, fiction, and medicine
- Local-first architecture with zero telemetry
|
|---|
| What makes it different | - Open source under AGPL-3.0, self-hostable with no LLM calls required to build the index
- Every published benchmark includes sample size, corpus and statistical methods
- Code health scores trained on years of real commits and defect fixes, with 0.74 AUC prediction accuracy
- Eliminates need to switch tools: integrates with Claude Code, Cursor, VS Code, GitHub and team dashboards
| - Wins 10 out of 12 blind code reviews compared to raw model APIs
- Design Studio wins 6 out of 6 blind design tests against raw models
- Bring your own keys across all providers at zero markup unlike Cursor and Windsurf
- Local-first architecture with zero telemetry and private execution
- Integrated iPhone companion for remote approval and monitoring
|
|---|
| 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) | 11 ▲ +1 (up) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 8 | 0 |
|---|
| Citation Flow (Majestic) | 34 | 0 |
|---|
| Referring domains (Majestic) | 244 | 1 |
|---|
Repowise
Exody