Lists (1)
Stars
Smart, Fast & Lossless session compaction for Pi. No LLM calls - produces structured, transcript-preserving summaries using pure extraction and formatting.
DeepSeek Harness: Everything is a Plugin.
Agent skill: make LLMs write docs in ASD-STE100 Simplified Technical
Diction is Open Source self-hosted alternative to WisprFlow - iOS speech-to-text keyboard
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.
Textream is a free macOS teleprompter app for streamers, interviewers, and presenters. It highlights your script in real-time as you speak, displayed in a beautiful Dynamic Island overlay. With ext…
A Python module privacy checker for keeping public interfaces intentional.
mindroom-ai / mindroom-nio
Forked from matrix-nio/matrix-nioA Python Matrix client library, designed according to sans I/O (http://sans-io.readthedocs.io/) principles
An open-source library for hardware test instrumentation
Open, agent-agnostic MCP server exposing macOS computer use to any MCP client (Claude Code, Cursor, Codex, …). Background-safe, works on every app.
A framework for building agentic apps
A modernized, complete, self-contained TeX/LaTeX engine, powered by XeTeX and TeXLive.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static bin…
Ultra small package to set the number of threads in e.g., OpenBLAS
Use pipefunc in combination with executorlib
Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.
sakgoyal / kaldialign
Forked from pzelasko/kaldialignPython wrappers for Kaldi Levenshtein's distance and alignment code.
Hundreds of models & providers. One command to find what runs on your hardware.
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Nix binary cache proxy service -- with local caching and signing.
Your code is under new management. Agents that review your code.
Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B c…
Turn images into flowing particle animations. Built with js, webgl / glsl, and html5 canvas
A HTTP credential proxy and vault for AI agents like Claude Code, OpenClaw, Hermes, custom agents + harnesses, and more.
A Python Matrix client library, designed according to sans I/O (http://sans-io.readthedocs.io/) principles