Connect your ad accounts to Claude and ChatGPT to run campaigns, get reports, and block wasted spend by asking
High-assurance infrastructure for AI agents
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
US
Pricing model
Free trial
Open source
Pricing
7-day free trial (no card required initially), then $49/month for Unlimited plan with unlimited tool calls across all platforms and accounts. Team plan: $49 per seat per month, minimum 2 seats.
Not given
Key features
Real-time campaign reporting and performance analysis across all connected accounts
Wasted spend detection and blocking of underperforming search terms
All changes require explicit user approval before execution
Works with Claude, ChatGPT, Cursor, Windsurf, Codex, Gemini CLI, Grok and other MCP-compatible clients
Harpe: chooses what an AI agent reads under a token budget with consistent results
Kibisis: keeps agent memory on your hardware with AES-256-GCM encryption
Argus: append-only record that detects edits with cryptographic verification
No network code by default for local and disconnected use
MIT License with published code, benchmarks and raw results
What makes it different
Read all platforms together in one chat instead of switching between separate dashboards
Integrated competitor research without needing ad account access
No API keys or passwords required; uses OAuth with encrypted tokens
Measured empirical validation across 6,111 questions outperforming full-context models
Zero plaintext on disk with encrypted vaults matching plaintext accuracy
78.3% fewer tokens sent to the model with a 1,200-token budget per turn
Preserves conversational chronology and relational qualifiers under token budgets