LLM Frontend for Power Users.

Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

Materials from CoE sponsored meetups

Pleasanter is a no-code/low-code development platform that runs on .NET. You can quickly create business applications with simple operations.

Learn it. Build it. Ship it for others.

Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI, Factory Droid Coding.

Attention router for CLI coding-agent swarms in tmux—monitor and respond from your phone.

Mobile client for Codex and Claude — control coding agents from your phone via WebSocket bridge

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Browser Harness | Self-healing harness that enables LLMs to complete any task.

The sandbox agent framework.

🔥 A production-ready base for agent-driven software

"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"

Light, fluffy, and always free - The AWS Local Emulator alternative

Transform ugly ahh calendar screenshots into good looking ones. Manual mode also supported.

Autonomous development pipeline on GitHub Actions and Claude Code CLI. Picks issues from a project board, implements them, fixes CI failures, and merges green PRs without human touch.

Production-grade engineering skills for AI coding agents.

Skills for Real Engineers. Straight from my .agents directory.

One CLAUDE.md file. Keeps Claude responses terse. Reduces output verbosity on heavy workflows. Drop-in, no code changes.

The design language that makes your AI harness better at design.

AI agents running research on single-GPU nanochat training automatically

An Open-Source Asynchronous Coding Agent

Managed Claude Stack - Reproducible AI infrastructure for Claude Code

Create polished demo videos without editing skills. Mac/Windows/Linux

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA