Proof of what an AI agent was allowed to do, and what it then did
Autonomous AI research agents that deliver scheduled briefings on SEC filings, earnings, and market data with cited sources
Stage
Startup
Not given
Founded
2026
Not given
Based in
Not given
US
Pricing model
Open source
Freemium
Pricing
Not given
Free tier available. Pro: $29/month with 7-day free trial, up to 7 Active Agent Slots (1 hourly plus 6 daily). Ultra: $89/month with up to 21 Active Agent Slots (3 hourly plus 18 daily). Max: $199/month with up to 42 Active Agent Slots (6 hourly plus 36 daily).
Key features
Signed permissions with passkey authentication
Receipts for each agent action with signatures
Free checker tool to verify compliance
Quantum-safe signatures (Ed25519 and ML-DSA-87)
Permission narrowing for helper agents
Permission cancellation with signed acknowledgement
JavaScript and Python libraries
LangChain and Pydantic AI middleware
Scheduled autonomous agents running on daily or hourly schedules
Live market data with interactive price and volume charts from one day to five years
Earnings call transcripts with key metrics including revenue, margins, segment results, and management guidance
SEC EDGAR filing analysis and citations
Macro data from FRED with year-over-year and month-over-month comparisons
Earnings call transcript search by meaning and theme tracking across companies
Market screening and ranking across S&P 500 stocks
Prediction market data from Polymarket on upcoming events
Multi-channel delivery via email, Discord, in-app, and SMS notifications
Open API for integration with external agents and workflows
What makes it different
Only open-source project combining machine-checkable limits, permission narrowing for helpers, and signed permission cancellation
Built entirely from published standards with no hand-made components
Free and no dependencies, sends nothing anywhere or holds money
Distinguishes between record integrity and whether agent stayed within permission
All published versions stay available for backward compatibility
Every claim in research briefings is linked to and cited from original sources
Scheduled agents run autonomously to deliver briefings before you ask
Uses live real-time data rather than trained knowledge, unlike ChatGPT
Open API allows any external agent to access grounded market research
Integrates with agent workflows via FN2 plugin for autonomous research desk management
Provared