| What it does | AI skill package for code quality, security and architecture checks integrated into Claude Code and OpenAI Codex
| Memory, rules and git blame for your coding agents
|
|---|
| Stage | Established
| Startup
|
|---|
| Founded | 2007
| Not given
|
|---|
| Based in | DE
| DE
|
|---|
| Pricing model | Paid
| Freemium
|
|---|
| Pricing | Company licence 142.80 € one-off (incl. 19% VAT, equals 120.00 € net), first 30 days of updates included. Optional subscription: 29.75 € per month incl. VAT (25.00 € net), cancellable monthly. With purchase: 22.31 € per month incl. VAT for 6 months (−25%), then 29.75 € per month.
| Free for personal use with all features; Team plan $20 per active seat per month, billed yearly (minimum 3 seats). First 10 teams pay $10 per active seat for 12 months.
|
|---|
| Key features | - Seven quality gates enforcing approvals, migrations, dependencies, data verdicts, defect claims, option questions and legal text checks
- Four command latches that block destructive operations before execution
- 22 detectors built from real incidents
- Five review modes and 15 hooks for different task sizes
- Council of five advisers with root-cause analysis and retrospectives
- Autopilot mode for unattended runs
- Works on macOS, Linux and Windows with Python 3.9 or newer
- Two separate editions for Claude Code and OpenAI Codex
- 27 skills and 14 review agents included
| - Session storage with secret redaction on local machine before upload
- Git blame integration showing which agent session wrote each code line
- Memory across agents allowing pickup of previous work
- Handoff between agents when Claude hits token limits
- Rules from corrections that persist across all agent sessions
- Session condensing showing only key moments and code
- Team rules reviewed like pull requests before reaching agents
- Team memory persisting when members leave
- Session attribution on pull requests showing which commits came from sessions
- MCP server for agents to search and learn from shared sessions
|
|---|
| What makes it different | - Proven improvement: average 5.7 points with Code Guardian vs 5.0 without across benchmark tests
- Built from 120+ real software projects and 20+ years of development experience
- Deterministic safety checks that block dangerous commands before execution, not after in reports
- Buy once, use permanently with optional updates subscription
| - Real sessions only, no fabricated runs, showing actual agent failures and interventions
- Secrets redacted on your machine before any data leaves, with server-side verification
- Open source MIT plugin with full control over your data
- Works with five different coding agents from one plugin
- Team data stays on your own PostgreSQL server if you choose
|
|---|
| 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) | 55 ▲ +1 (up) since last check | 10 ● no change since last check |
|---|
| Trust Flow (Majestic) | 18 | 2 |
|---|
| Citation Flow (Majestic) | 20 | 35 |
|---|
| Referring domains (Majestic) | 196 | 10 |
|---|
Code Guardian
KeepPlain