AI Agents repositories

pi-textbook

A hands-on course that walks through building a Pi-style coding agent from scratch across 15 checkpoints, starting from an offline agent trajectory.

Claude-of-Duty

A browser-based first-person shooter built entirely with procedural generation and orchestrated AI agents, featuring 55k lines of Three.js/WebGL2 code and no art assets.

grok-app

Grok App is a desktop command center built with Tauri 2 that wraps the local Grok Build CLI into a graphical workbench for managing sessions, projects, media, automations, and accounts.

story-to-handdrawn-video

A Remotion-based tool that converts Chinese story text or ordered hand-drawn images into vertical hand-drawn diary-comic animation with handwritten captions, left-to-right reveals, optional page-curl transitions, and silent H.264 output for post-production dubbing.

agentacct

agentacct is a local-first dashboard that reads coding agent session logs to display token usage, estimated costs, tasks, and evidence, all without sending data off your machine.

cindy

Consider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。

graph-engineering

Graph Engineering is a discipline for designing the topologies that AI agents use to remember (knowledge graphs) and work (task graphs), packaged as a practical skill file and reference material.

thinking-orbs

A React component library that renders six hand-tuned animated thought orb loading indicators on a plain 2D canvas, with two purpose-tuned sizes and automatic theme detection for AI and agent UIs.

labs-OO-Agents

labs-OO-agents

Finn-loop

Finn-loop is a set of three Claude Code skills that create a human-gated AI software factory by linking Linear issue creation, automated PR building, and automated PR review, with all merges performed by humans.

VibeGamer

An experimental project that uses an LLM-powered AI agent to autonomously play the game Turmoil, with self-play, memory accumulation, and strategy evolution over time.

open-kritt

open·kritt is an open-source, self-hosted platform that orchestrates AI agents to perform focused, parallel code analysis for finding real vulnerabilities, with de-duplication and validation.

BossConsole

BOSS is an open-source, multi-platform desktop harness for AI agents that provides a governed environment with an embedded browser, terminal, code editor, plugin system, and over 100 MCP tools, allowing any agent to operate autonomously while the user stays in control.

collective-intelligence

Ailin¹ is an open-source collective intelligence engine where tens of thousands of AI models collaborate through dozens of coordination strategies, applying structured diversity and independent reasoning to improve reliability, auditability, and resilience.

pireel

Pireel Studio is an open-source, backend-free AI video editor for talking-head videos that runs entirely in the browser with no account or server required.

nativ

Nativ is a native macOS app that lets you run AI models locally on Apple silicon, offering chat, model management, performance analytics, and an OpenAI/Anthropic-compatible API server.

caspian-sdk

Caspian is an open-source SDK and gateway that lets AI agents communicate across multiple channels (Slack, Discord, Telegram, email, etc.) through a single handler, eliminating per-channel adapter code.

claude-thermos

claude-thermos is a lightweight proxy that automatically keeps Claude Code's prompt cache warm during long subagent runs, preventing expensive cache rewrites that can waste ~20% of your API bill.