Chatroulette for developers — anonymous terminal chat while you wait on Claude Code. npm: devroulette-cli

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

A town for agents, built by agents.

The most agent-ergonomic browser automation

Use your most capable model to audit your codebase and write plans for cheaper models to execute.

Desktop Companion for Hermes Agent

Generate production-ready Lottie animations with Claude Code or Codex

Tool to build & run portable, lightweight, self-contained virtual machines.

Lexa - Fast local code intelligence for humans and AI agents. Lexa turns a codebase into a portable, queryable graph so every tool can work from the same stable view of the project.

Self-hosted AI workspace.

AI agent skills created by me: Dan McAteer

agents can read each others minds (session logs)

The Zero-Dependency, Sub-Millisecond AI Memory System for Hermes Agents and Everyone Else!

Open-source American english TTS model. 6 voices and a high performance inference library for Apple Silicon.

Open TTS is a local-first text-to-speech studio with separate web and Electron apps, shared WebGPU browser inference, and optional desktop local runtimes powered by a Rust bridge.

MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenario…

Blazing-fast Rust token usage tracker for Codex and Claude Code with unified reports, live monitoring, CLI/TUI/GUI dashboards.

🛰️ A CLI tool for tracking token usage from OpenCode, Claude Code, 🦞OpenClaw (Clawdbot/Moltbot), Pi, Codex, Gemini, Cursor, AmpCode, Factory Droid, Kimi, and more! • 🏅Global Leaderboard + 2D/3D Con…

Ultra-low-latency, high-throughput multiprocess transport over SHM and mmap. LMAX-Disruptor-style cross-process ring substrate.

Fast and memory-efficient classical machine learning operators

Git-native, provenance-backed context capsules for coding agents.

Distributed object-capability authorization with ZK proofs

Mac Pro 2019 local AI setup guides for Ubuntu, ROCm, AMD MPX GPUs, PyTorch, vLLM, Ollama, Infinity Fabric Link, and related experiments.

ML software (llama.cpp, ComfyUI, vLLM) builds for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60