Security●●●Banger
OnGarde – Runtime content security proxy for self-hosted AI agents
Transparent proxy blocks agent leaks to LLM APIs without touching agent code.
Solve My ProblemSlick
antimaterial
213mo ago
Back to browse
On-device Chrome extension that blocks credential leaks to LLM chats
by GBillington·Jun 3, 2026·5 points·0 comments
AI Analysis
●●SolidSolve My ProblemNiche Gem
Local neural network catches leaks in 150ms with zero telemetry.
Strengths
- •On-device inference means paste content never leaves the browser.
- •Supports all major LLM chat platforms including Claude and Copilot.
- •Auditable source code with no analytics or outbound network calls.
Weaknesses
- •Browser security extensions already exist from established vendors.
- •Chrome-only limits reach for Firefox and Safari users.
Category
Target Audience
Developers and professionals using AI chat tools
Similar To
Privacy Badger · DuckDuckGo Privacy Essentials
Similar Projects
AI/ML●●Solid
NeuralForge – Fine-Tune LLMs on Your Mac Using Apple Neural Engine
Fine-tune LLMs on Apple Neural Engine using reverse-engineered private frameworks — genuinely novel approach.
WizardryBig BrainNiche Gem
khaeldur
112mo ago
Security●Mid
EyesOff – On-device AI that catches shoulder surfers
Single-feature shoulder surf detector with no depth beyond face detection.
Niche Gem
Two_hands
102mo ago
AI/ML●●●Banger
Orion – Native Training LLMs on the Apple Neural Engine Without CoreML
Direct ANE access bypasses CoreML to enable training—genuinely novel Apple Silicon unlock.
WizardryZero to OneBig Brain
mechramc
213mo ago
Security●●●Banger
ClawShield – Open-source firewall for agent-to-agent AI communication
Agent firewall with 16+ injection patterns, sandboxed skill scanning, detects real OpenClaw CVE exposure.
WizardrySolve My Problem
Joe_DNAI
103mo ago
Security●●Solid
VeilPhantom – Open-source on-device PII detection for AI pipelines
Phonetic embeddings catch ASR-mangled names across cultures before LLM sees them.
Big BrainSolve My Problem
nakaiwilliams
102mo ago