Developer Tool / Security
A loopback HTTPS proxy that swaps placeholders for real API keys at request time, keeping secrets out of the agent process. It uses Bitwarden Secrets Manager and supports scoped bindings for hosts, methods, and paths.
The page clearly describes a real AI-adjacent security tool with a specific purpose: just-in-time secret injection for agents and other processes. The README gives enough detail on how it works, what problem it solves, and the core flow of placeholder-to-secret substitution to support a useful directory listing.
The snapshot does not show install commands, a working example end to end, or any screenshots/demo output. It’s also hard to tell how mature the project is beyond the README and repository structure.
Last evaluated 8 days ago. Current rank #279. Down 6 spots 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.
Browser extension that scans pastes for credentials and PII before they reach LLM chat sites, with local on-device inference and no network calls.
Open-source runtime for multi-agent AI systems with job scheduling, DAG orchestration, shared memory, tool execution, and real-time observability.
