| What it does | An engine for long-running agents that rebuilds its prompt under a cap and runs on your budget
| Human approval infrastructure for AI agents and automation workflows
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Prototype: free during beta, then from December 16, 2026 it costs $1 per 1,000 agent calls after 1,000 monthly included calls. Production: $20 a month with 20,000 agent calls included, then $1 per 1,000 calls after that. Top-ups: $1 per 1,000 calls, from $10 to $500 at a time, never expiring.
| Developer: Free forever with 250 Actions/month, 3 Sources, 3 Watches, 7-day history. Pro: $10/month ($120/year, save 17%) with 1,000 Actions/month, unlimited Sources, 20 Watches, 30-day history, additional Actions at $8 per 1,000-pack. Team: $49.17/month ($590/year, save 17%) with 5,000 Actions/mont
|
|---|
| Key features | - Prompt rebuilt from journal under token cap at each step to keep it bounded as history grows
- Spending limits checked before each model call at token prices you declare
- Resume after crash without repeating finished actions
- Tool calls returned as actions for your code to carry out
- Proof of what ran: check prompts, re-run engine, download hash-chained journal
- Integrations with Vercel AI SDK, OpenAI Agents SDK, LangGraph, Mastra, Pydantic AI
- MCP server for Claude Code, Claude Projects and Codex
- Works with any model via bring-your-own-key
- TypeScript and Python clients for HTTP API access
| - Typed decisions (Boolean, choice, text, number, rating, structured forms)
- Heartbeat Watches for silent-work detection
- Action Controls for safe follow-up operations
- Multi-surface inboxes (web, mobile, Slack, CLI, MCP)
- Model Context Protocol (MCP) integration
- Signed receipts and durable decision history
- Mobile app for iOS (15+) with push alerts
- Slack approval integration (Beta)
- CLI with bounded long-poll waiting
- Integration guides for GitHub Actions, n8n, LangGraph, OpenAI Agents SDK
|
|---|
| What makes it different | - Bounded prompt under a fixed cap while history grows, so costs per call stop climbing on long sessions
- Every run recorded with cryptographic proof: rebuilable prompts, hash-chained journal, re-runnable engine
- Resumes from crash without repeating finished actions using stable idempotency keys
- Budget enforcement before each model call, not reactive overage billing
- No model key storage or logging; your provider bills you directly
| - Durable decision records that survive client disconnections and restarts
- Reduces median approval time significantly in production environments
- Unified API across multiple approval surfaces without building custom dashboards
- Source-scoped identity for independent credential rotation across runners
- Built-in monitoring for stalled background work with heartbeat watches
|
|---|
| 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) | Not checked yet ● no change since last check | 5 ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 7 |
|---|
| Citation Flow (Majestic) | 9 | 24 |
|---|
| Referring domains (Majestic) | 4 | 42 |
|---|
Argentic
ActionBox