| What it does | AI Agents for Document OCR + Workflows
| An engine for long-running agents that rebuilds its prompt under a cap and runs on your budget
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free plan with 10,000 monthly credits; Starter at $50/month with 40,000 credits; Pro at $500/month with 400,000 credits; Enterprise with custom pricing. Additional pay-as-you-go credits available. Pricing based on a credit system where 1,000 credits equals $1.25.
| 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.
|
|---|
| Key features | - Agentic OCR parsing with semantic understanding for complex document layouts
- Support for 130+ file formats including PDFs, Office docs, images, and spreadsheets
- Structured data extraction with schema-based, LLM-powered agents
- Document classification and splitting based on natural language rules
- Enterprise-grade RAG indexing and retrieval pipeline
- Handwritten text parsing and structured extraction
- Table and chart extraction with structured row and column relationships
- Cloud SaaS or VPC deployment with flexible data residency options
| - 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
|
|---|
| What makes it different | - 4x cheaper than frontier labs, 5x more accurate than other APIs
- Auto-correction loops with recursive checks that detect and fix errors automatically
- Task-specific specialist agents that route content to the right expert
- HIPAA, GDPR, and SOC2 compliant with enterprise-grade security
| - 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
|
|---|
| 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) | 82 ▲ +1 (up) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 33 | 0 |
|---|
| Citation Flow (Majestic) | 56 | 9 |
|---|
| Referring domains (Majestic) | 10381 | 4 |
|---|
Argentic