Stars
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Can LLMs play Baba Is You? I built an OpenCode-based agent to find out!
PDF-derived institutional affiliations for 5,356 ICLR 2026 accepted papers — full pipeline (scrape → parse → render), clean dataset (CSV + XLSX), and treemap charts.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
One CLAUDE.md file. Keeps Claude responses terse. Reduces output verbosity on heavy workflows. Drop-in, no code changes.
Capstone disassembly/disassembler framework for ARM, ARM64 (ARMv8), Alpha, BPF, Ethereum VM, HPPA, LoongArch, M68K, M680X, Mips, MOS65XX, PPC, RISC-V(rv32G/rv64G), SH, Sparc, SystemZ, TMS320C64X, T…
Wolfram Language / Mathematica reimplementation in Rust (Wolfram oxidized)
Terminal-Bench-Science: Evaluating AI Agents on Complex Real-World Scientific Workflows in the Terminal
Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents
Measuring agents' ability to get work done on a computer
Unsupervised benchmark for evaluating CLI coding agents on bug detection
An open-source benchmark for evaluating AI agents' ability to find backdoors hidden in compiled binaries.
The HN Arcade - https://news.ycombinator.com/item?id=46793693
OpenTelemetry Benchmark - can AI trace your failed login?
GZDoom is a feature centric port for all Doom engine games, based on ZDoom, adding an OpenGL renderer and powerful scripting capabilities
Store LLM prompts in git notes. (DEV release, not for public yet)
Benchmarking Agentic LLM and VLM Reasoning On Games
View disk space usage and delete unwanted data, fast.
Claude Code Skill for browser automation with Playwright. Model-invoked - Claude autonomously writes and executes custom automation for testing and validation.
ripgrep recursively searches directories for a regex pattern while respecting your gitignore
Terminal session recorder, streamer and player 📹