| What it does | An engine for long-running agents that rebuilds its prompt under a cap and runs on your budget
| The brand layer for agents
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| 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.
| Free: 1,000 credits and one free brand creation (one-time). Plus: $20/month (5,000 credits/month). Pro: $35/month (10,000 credits/month). Max: $50/month (20,000 credits/month). Scale: $65/month (30,000 credits/month). Annual billing is 10% off on every plan. Top-ups available at $0.50 per 100 credit
|
|---|
| 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
| - Request brand brief with guidance and assets for each task
- Image review to check work against brand guidelines
- Connect to ChatGPT, Claude, Cursor and other AI tools via MCP
- REST API integration into products and workflows
- Create brands from website, brand guides or files
- Automatic brand updates propagate to connected AI tools
- Separate brands for client management in teams
- Checks logo, colors, typography and copy in reviews
|
|---|
| 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
| - Maintains shared brand context across multiple AI tools and agents automatically
- Gives each task relevant brand guidance without manual copying into every tool
- Enables agencies to keep client brands separate with no limits on number of brands
- Single source of truth for brand that updates across all connected tools instantly
|
|---|
| 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 | 40 ● no change since last check |
| Trust Flow (Majestic) | 0 | 8 |
| Citation Flow (Majestic) | 9 | 36 |
| Referring domains (Majestic) | 4 | 217 |