| What it does | An approval layer for unattended AI agents that halts risky actions for human approval before execution
| Fix your AI agent while it's still running
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Free
|
|---|
| Pricing | Self-hosted: Free (MIT licensed). Hosted Indie: $49/mo (2 seats, monthly governed-action ceiling, 30-day retention, email support). Hosted Team: $199/mo (10 seats, higher governed-action ceiling, 90-day retention, org-scoped rate limits, priority support).
| Free account for Circuit and Jack. The debugger is free and open source under MIT license.
|
|---|
| Key features | - Intercepts risky agent actions before execution
- Works with Claude Code, Codex, Hermes, OpenClaw, and MCP
- Policy-based risk scoring and decision making
- Remote approvals from phone or browser
- Signed audit ledger with replayable records
- Calibrated interruptions that reduce false positives
- Enforcement liveness monitoring via synthetic probes
- Self-hosted (MIT licensed) or managed hosting options
- Approvals inbox with decision ledger and policies
- Agent defense documentation with assumptions and shields
| - Debug failing agent calls with full visibility into inputs, outputs, prompts and tokens
- Edit arguments and retry the real call
- Inject a result and skip the call entirely
- Visual canvas to design agents and generate code
- Replay runs as test cases without keys or cost
- Circuit: durable workflows that pause instead of fail
- Jack: convert OpenAPI specs to OAuth-protected MCP servers
- Works with Vercel AI SDK, Anthropic, OpenAI, LangGraph and Python
|
|---|
| What makes it different | - Only approval layer that protects unattended runs that walk away
- Signed ledger with replayable audit records and explicit signature verification
- Self-hosted with no infrastructure lock-in or vendor dependency
- Learns from your approvals to reduce interruptions automatically
- Honest about enforcement boundaries across different integrations
| - Holds failing calls mid-execution so you can inspect and fix them without rerunning
- Local-first debugger that runs on your machine with no account needed
- Open source under MIT license
- Integrates with existing code in two lines
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 7 ▼ −1 (down) since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 3 | 0 |
| Citation Flow (Majestic) | 30 | 7 |
| Referring domains (Majestic) | 88 | 1 |