AI sales agent that finds qualified leads, runs LinkedIn and email outreach, follows up automatically, and creates content
Proof of what an AI agent was allowed to do, and what it then did
Stage
Not given
Startup
Founded
Not given
2026
Based in
US
Not given
Pricing model
Freemium
Open source
Pricing
Pro: $59/month (or $47.20/month billed quarterly, save 10%) or $59/month (or $47.20/month yearly, save 20%) - includes 2 AI agents, up to 2,000 prospects found per month, 2 sending accounts, 35 Content credits and 50 enrichment credits per month, 7-day free trial. Growth: $100/month (or $80/month bi
Not given
Key features
AI prospect search with plain English descriptions of ideal customers
Verified email and LinkedIn profiles with current role validation against live LinkedIn
Multichannel outreach sequences combining LinkedIn and email in one workflow
AI personalization based on website research and buying signals
LinkedIn content generation and scheduling in your own voice
Unified inbox sorted by buying intent across LinkedIn and email
Autopilot mode for replies and meeting booking
Multi-account sending with safe daily limits
Sales analytics and intent scoring based on 18 buying signals
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
What makes it different
Covers both inbound and outbound pipeline in one platform instead of multiple disconnected tools
Uses real buying signals like hiring, job changes and competitor engagement to reach prospects at the right time
Learns your voice from existing posts and generates content that matches your style instead of generic AI copy
Integrates with popular AI agents like Claude and ChatGPT for pipeline management
Costs under $50/month compared to $5,000/month for a human SDR
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