| What it does | AI deep research API that checks every cited claim against its source
| An engine for long-running agents that rebuilds its prompt under a cap and runs on your budget
|
|---|
| Stage | Startup
| MVP
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | US
| Not given
|
|---|
| Pricing model | Paid
| Freemium
|
|---|
| Pricing | Not given
| 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 | - Searches 45+ structured sources including SEC filings, statistics agencies, scholarly indexes, books and government records
- Workspace vault with searchable full-text source storage and independence clustering
- Integrated MCP server for Claude, Cursor, ChatGPT and other clients
- Contradiction mapping identifies and investigates disagreements in evidence
- Automatic report generation with verified citations before shipping
- Citation verification API for external documents
- Markdown import and export for vault documents
- Integrated Answers MCP with ask and search tools for AI agents
| - 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 | - Every cited claim is verified against the original source before report delivery
- Searches structured sources like SEC filings and scholarly databases alongside the open web in one call
- Delivers answers with word-for-word quotes so readers can verify in one click
- Open-source CLI that powers the hosted service, maintaining feature parity
- Pay-as-you-go pricing with no minimum commitment or sales team required
| - 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) | 32 ▲ +4 (up) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 13 | 0 |
|---|
| Citation Flow (Majestic) | 31 | 9 |
|---|
| Referring domains (Majestic) | 71 | 4 |
|---|
Hyperresearch
Argentic