AgentSend: See What Your Coding Agent Sends

Inspect outbound data from coding AI agents and mask sensitive content

Problem

Developers using coding agents don't know exactly what code, keys, or context the agent sends to model providers, nor whether sensitive data leaks. Existing tools either only log or only redact—there's no lightweight local view for quick inspection and masking.

Solution

A local proxy or CLI that intercepts outbound requests from coding agents, shows a structured view of what's sent (code snippets, file paths, env vars), and lets developers mask sensitive fields with rules or regex. Per-project retention policies.

Users

Developers and security engineers using Claude Code, Cursor, Copilot, etc., who care about data exfiltration

MVP

Local proxy to intercept HTTP requests; show files and content summaries in requests; regex/keyword masking rules; per-project config persistence; simple log export

Revenue

Open-source core + paid team tier (shared rules, audit logs, compliance reports); or per-seat subscription

Why now

Coding agents are exploding and enterprise concern about agent data egress is rising, but existing solutions are enterprise-heavy. An indie dev can build a developer-first transparency layer and later sell to teams.