| What it does | Codebase intelligence platform for AI agents and teams
| Run coding agents and AI models on your own computer, accessible from any screen
|
|---|
| Stage | Startup
| MVP
|
|---|
| Founded | 2024
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| 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: no subscription for local and LAN work, 30 minutes per month of remote viewing. Lyre Pro: $15 per month billed monthly, includes no time limit on remote viewing and 50 GB of application relay traffic per account per month. Lyre AI: $100 per month billed monthly, includes no time limit on remot
|
|---|
| 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
| - Run coding agents and AI models locally on your computer
- Access from phone, desktop, and browser simultaneously
- Support for React, Vite, Next.js, Expo-web, and Capacitor projects
- Live app preview and file diff alongside chat
- Direct LAN connections without server relay
- End-to-end encrypted relay for remote access
- App-only sharing that hides source code and agents
- Support for local models via Ollama and llama.cpp
- Automatic AI provider fallback across multiple accounts
|
|---|
| 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
| - Keeps your projects on your computer without uploading to servers for local and LAN work
- Works across desktop, mobile, and browser with the same workspace
- Free unlimited local and LAN viewing without subscriptions
- No vendor lock-in with support for any AI provider or local model
- Built by a single developer actively shipping features in public
|
|---|
| 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 |
| Trust Flow (Majestic) | 8 | 0 |
| Citation Flow (Majestic) | 34 | 19 |
| Referring domains (Majestic) | 244 | 2 |