Developer Tool / AI Authorization / Security
Open-source authorization engine for AI agents that adds confidence-based gating, human review, policy-as-code, and audit logging. The repo shows quickstart code, local demo steps, SDK installs, and self-hosting options.
The page clearly describes a real AI-security product for agent authorization, and the repository gives enough evidence for a useful public listing: purpose, quickstart usage, install commands, integration targets, and deployment options. It also shows concrete safeguards like prompt-injection filtering, confidence gating, human review, and audit trails.
The snapshot does not show licensing terms beyond the repo file list, pricing or hosted product details, or independent proof of maintenance beyond commit count and stars. It also does not fully document API endpoints, configuration options, or limits for the risk and review workflows.
Last evaluated 8 hours ago. Current rank #149. Up 2 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.
