🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
Repository Index
47,133 repositories indexed
1–18 of 18 · Most stars
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
The malleable knowledge base for you and your team. Powered by Markdown and Lua.
Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.
Trigger functions or evaluate cron expressions in JavaScript or TypeScript. No dependencies. Most features. Node. Deno. Bun. Browser.
A TypeScript-to-Luau Compiler for Roblox
Markdown preview plugin for Neovim
Lua IDE/Debugger Plugin for VSCode
Enhance the security of your web applications effortlessly with AWS Firewall Factory. Safeguard your valuable assets through seamless WAF deployment, updates, and staging, all centrally managed with AWS Firewall Manager.
Intellisense and Linting for Lua in VSCode
Extensive math expression evaluator library for JavaScript and Node.js
Advanced multi-language networking framework for Roblox
An affordable and reliable Tally Light that works via WiFi based on NodeMCU / ESP8266. Supports multiple video mixers.
Terminal toolkit for exploring prediction markets, evaluating signals, and managing trading exposure.
A Javascript to PICO-8 Lua transpiler
Library for serializing and deserializing PocketBase filter syntax.
The E2E AI testing tool | No ML Overhead
📈 Management and evaluation at Hackathons events - My Course conclusion work.