| What it does | The model training platform for AI teams
| Check your AI coding agent's config before it runs
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| GE
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: $0/month with $50 in credits once, 1 seat per project, every feature, console, CLI and MCP server, community Discord support. Pro: $120/month with $120 in credits every month, unlimited seats, priority support. Enterprise: Custom pricing, contact for details.
| Free browser scan available with no account. Paid plans: Individual $9/month (up to 1 developer), Team $49/month (up to 10 developers), Business $129/month (up to 50 developers). Enterprise plans available with custom quote.
|
|---|
| Key features | - OpenTelemetry agent tracing and trace import from Langfuse, LangSmith, Braintrust and Galileo
- Generated evals and Agent Optimizer runs that return scored code diffs
- Data Workshop with dataset preparation and quality checks
- Model training with recommended settings for LoRA or full fine-tuning
- Benchmarks against your current model on the same eval set
- Hosted OpenAI-compatible inference and downloadable model weights
- Console, CLI and MCP server access
- OpenAI-compatible API for trained models
| - Scans CLAUDE.md, .mcp.json, .claude/settings.json and related configuration files
- Detects risky permissions and allow rules such as Bash, * or bypassPermissions
- Flags hook commands that use the network, pipe into a shell or decode and run
- Identifies unpinned MCP packages and auto-confirm flags
- Identifies instructions to exfiltrate secrets
- Detects instructions that override or hide agent actions
- Runs in CLI, GitHub Actions, git hooks and browser
- Outputs findings in text, JSON or SARIF 2.1.0 format
- Compares git revisions with diff mode for pull request checks
|
|---|
| What makes it different | - Own your trained models with downloadable weights and checkpoints
- Zero third-party training with data never leaving your pipeline
- Open source and self-hostable with Docker Compose
- Built by security and defense intelligence pioneers
| - Never executes code - reads files as text only
- Fixed deterministic rules that always give the same results
- Identifies real vulnerabilities like backdoored postmark-mcp and CVE-2025-6514 in mcp-remote
- Free browser scan requires no installation or account
- Works across multiple AI agent tools: Claude Code, Cursor, Codex and Gemini CLI
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 44 ● no change since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 10 | 0 |
| Citation Flow (Majestic) | 35 | 0 |
| Referring domains (Majestic) | 201 | 0 |