HN Showcase
Back to browse
GitHub Repository

A zero-latency, local-first runtime firewall for LLMs. Intercept every prompt and response locally to stop data leaks and runaway token costs.

16 starsPython

Stop letting Claude Code burn your tokens and leak API keys

by ashishp15·Jun 9, 2026·3 points·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidSolve My ProblemShip It

Local firewall for AI agents stops token burn before requests leave your machine.

Strengths
  • •YAML policy engine lets you define hard cost limits per session.
  • •Python SDK and CLI cover both local agents and production apps.
  • •Zero-latency claim suggests efficient local interception without cloud roundtrips.
Weaknesses
  • •Local-only approach misses centralized team visibility across multiple machines.
  • •Competing against established cloud gateways like Portkey and Helicone.
Target Audience

Developers using AI coding agents like Claude Code or Cursor

Similar To

Portkey · Helicone · LangFuse

Similar Projects

Other○Pass

Burn, baby, burn (those tokens)

Funny satire on AI hype, but literally just a script to waste money.

dtnewman
135301mo ago
Security●●●Banger

Phantom – Let AI use your API keys without leaking them

Proxy tokens worthless if leaked, real keys never enter LLM context windows.

Big BrainSolve My ProblemDark Horse
masonwyatt23
202mo ago