DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with independent solvers, scorer and runners.
- benchmark
- calibration
- decision-making
- evaluation
47,133 repositories indexed
3,265–3,288 of 4,657 · Most stars
DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with independent solvers, scorer and runners.
Generic eBPF runtime
TranslatedLocal-first Rust TUI/CLI for auditing AI coding-agent sessions: cost, tokens, latency, failures, and health
Run language-model agents in Minecraft with Mineflayer tools, persistent sessions and shell sandboxes.
Dreamento (DReam ENgenieering TOolbox): a Python-based software for dream engineering while monitoring/analyzing real-time EEG data.
Generic template interface for Crystal
Free studio for fursuit patterns and furry art. Local, portable, no account.
Generates reproducible ruby/bundler app environment with Nix
PHP Iteration Tools Library
A frontend framework for chillout-mode development 🥤 JSX components on generators*, fast mobx-like state management and exclusive cssx style system
Free, open-source SEO audits inside OpenAI Codex CLI. Port of claude-seo: 26 skills, 19 specialist roles, technical SEO / schema / GEO / local / ecommerce.
ComfyUI custom node: one-click character reference sheet (character card) generation, auto slice & recomposition for Qwen-Image 2.1
Facil generates F# data access source code from SQL queries and stored procedures. Optimized for developer happiness.
Json library that uses .NET 5 Source Generators
A 35B diffusion language model.
Generate Keyboard Walk Dictionaries for cracking
Magento specific extension for PHPStan
Generate scaffold project layout for Go.
Javascript Generalized Parser Combinators
[unmaintained] FakerElixir generates fake data for you.
One app for every document. Built for AI agents. An open-source desktop office suite written in Rust: documents, spreadsheets, slides, PDF, Markdown, code and rich text, opened, edited and saved in one row of file tabs. The same binary is a command line that AI agents call directly.
Codex plugin for OpenPencil — an interactive Rust/WASM canvas for AI-assisted UI design. Create editable .op files from prompts, refine selected elements, generate image assets, and install with one prompt on macOS, Windows, and Linux.
This project is a Blazor Interop C# Generator, has a sample against the BabylonJS library.
Your software. Your distribution. Your terms.