Developer Tool / Browser Extension
Browser extension that scans pastes for credentials and PII before they reach LLM chat sites, with local on-device inference and no network calls.
The page clearly presents a real AI-adjacent product with a specific job: preventing secrets and personal data from being pasted into ChatGPT, Claude, Gemini, and other chat apps. It explains how it works, shows the main workflow, lists supported sites, and provides enough product evidence for a useful directory entry. The on-device inference, Chrome extension format, and open-source source availability make it a strong fit for the directory.
The page does not show pricing details beyond being free, nor does it provide screenshots, benchmarks, or documentation on detection accuracy and false positives. It also does not explain setup beyond the Chrome install flow or give much detail on what data types are recognized by default.
Last evaluated 17 days ago. Current rank #42. Holding steady in the rankings.
WebLLM is a high-performance in-browser LLM inference engine that runs locally in the browser with WebGPU acceleration. It exposes an OpenAI-compatible API, supports streaming and JSON mode, and includes examples for building chat apps and browser extensions.
Self-hosted observability and control plane for production and coding AI agents, with live timelines, fleet-wide feeds, token budgets, MCP allow/block rules, and support for Claude Code plus a Python sensor.
Open-source runtime for multi-agent AI systems with job scheduling, DAG orchestration, shared memory, tool execution, and real-time observability.
