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.

7 starsPython

Stop letting Claude Code burn your tokens and leak API keys

by ashishp15·Jun 9, 2026·1 point·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
1353025d 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