Lists (4)
Starred repositories
Chrome's on-device Gemini Nano, served as if it were OpenAI. Cross-platform sister of apfel.
A private hardware voice intercom for a small circle of kids. ESP32-S3 units that ring a friend by name; outbound-only, AES-256-GCM audio, no accounts, no rooms, no recordings.
git worktrees + tmux windows for zero-friction parallel dev
CLI/TUI for managing multiple AI agent sessions in isolated git environments with real-time status monitoring, task tracking, and inter-agent messaging.
A browser UI for Claude Code, Codex, and Gemini CLI — the terminal agent you already use, rendered faithfully, with generative UI on top: readable output, live pinned dashboards, every session at a…
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by ou…
A lightweight, FastAPI-powered adaptive server that automatically turns files and Python modules into fully functional REST APIs.
Self-hosted OpenAI-compatible mock server — test your LLM integrations without exposing your API key. By Axium.
Run local image, text, speech, vision, music, and video workflows, plus model management and a loopback OpenAI-compatible API server. The repo ships the core libraries and the mere.run executable.
OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
A lightweight, fast, terminal-based markdown research tool inspired by Obsidian
TUI Application to manage Obsidian notes directly from the terminal
TUI dashboard builder that lets you visualize data from scripts and APIs right in your console
shadcn-style components for gsx — copy-in, type-checked, server-rendered
Generate fictional names and verification phrases from phonological rules
A powerful Rust library and CLI tool to unify and orchestrate multiple LLM, Agent and voice backends (OpenAI, Claude, Gemini, Ollama, ElevenLabs...) with a single, extensible API. Build, chain, eva…
a shell-pipe language for image manipulation, built on libvips
Break the loop. GitHub, Gmail, Slack and anything with a webhook pushed straight into your Codex threads.
Memory your agent can trust — every answer carries its source; when it doesn't know, it says so. Hermetic, local, MCP.
Write commit messages, grep by meaning, turn English into shell — small composable CLI tools backed by an LLM. Local by default (no API key) or any cheap hosted model.
Akashic is an open-source Palantir alternative for connecting, exploring, and analyzing complex data. Fully self-hosted, privacy-first, and requiring no API keys.
Core development repository. gitHub: Vsn 6 (2020 - ), Vsn 5 (2018 - 2020), Vsn 4 (2014-2017). Sourceforge: Vsn 3 (2009-2013), Vsn 1 & 2 (2005-2009)
A physics sandbox that runs in your terminal: rigid bodies, n-body gravity, cloth, and fluid, projected in 3D onto braille with no GPU.
Point it at any web page and it finds the video, extracts the stream, transcodes it and casts in real time to your TV. It even burns subtitles….