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
9,217–9,240 of 14,002 · 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.
A mode to facilitate interactive data visualization using Vega from within emacs
TranslatedSee which McDonald's benefits are about to expire, which are worth using, and which are not worth spending money on just because they are expiring. A WorkBuddy Skill built on the official McDonald's MCP: read-only queries of coupons and points, and, based on your budget, up to two meal plans priced through the official interface. McDonald's coupon & points expiry assistant — a WorkBuddy Skill on the official McDonald's MCP. Read-only queries, official price calculation, max 2 budget-friendly plans.
Expose all events from an Amcrest device to an MQTT broker
Simple Reverse Proxy with Caching, written in Go, using Redis.
Implementation of Chrome extension APIs for Electron
TranslatedLocal-first Rust TUI/CLI for auditing AI coding-agent sessions: cost, tokens, latency, failures, and health
Kademlia DHT K-bucket implementation as a binary tree
AET - a system that detects visual changes on web sites and performs basic page health checks
Multi-agent research execution system: paper reproduction, benchmark evaluation, AutoResearch and claim-evidence graphs
ComfyUI Timeline Studio for MiniMax H3: multi-shot video, visual memory across scenes and angles, and local or cloud Story writing.
A Common Lisp library for building TUIs
A promise-based Node.JS library for the Blizzard Battle.net Community Platform API
"Docker Push Readme" - a Docker CLI plugin to update container repo docs
Dreamento (DReam ENgenieering TOolbox): a Python-based software for dream engineering while monitoring/analyzing real-time EEG data.
neowiki.nvim: full-featured minimalist Vimwiki successor for instant notes & GTD 🚀📝
:non-potable_water: Is a lightweight HTTP router that sticks to the std "net/http" implementation
A Cordova plugin displaying music controls in notifications (cordova-plugin-music-controls)
A Go implementation of in-toto. in-toto is a framework to protect software supply chain integrity.
A collection of TUIs for Neovim
Tools for the Computer Incident Response Team :computer:
Python implementation of the Packed Executable iDentifier (PEiD)
Fast octet-vector/stream I/O for Common Lisp
Common Lisp I/O library