Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.
- claude-code
- codex
- ghostty
- terminal
89,572 visible repositories in the index
1–24 of 32 · Most stars
Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.
AIHawk: AI job application bot, automated job search, job hunting, auto-apply to resume-matching jobs while you sleep.
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
Visualize any GitHub codebase: free interactive architecture diagrams and one-minute explainer videos. Replace 'hub' with 'diagram' in any GitHub URL.
Plan, run and supervise fleets of agents from task to merged PR. Desktop (macOS, Windows, Linux) + iPhone & Android apps. Supports Claude Code, Codex & 35+ coding agents.
TranslatedCage: a lightweight virtual machine specialized for Claude, completely preventing network leaks. Adapted to multiple platforms, with support for multi-account management, remote deployment, and mobile control.
TranslatedA skill that turns SRT subtitles into whiteboard hand-drawn animation with a warm beige paper background and flowing handwriting strokes: mask-based zone masking and arrangement + stream continuous strokes (ink→color).
Automated Binance trading bot with pluggable strategies, historical backtesting, a live dashboard, and connect an AI agent over MCP
Agent skill: make LLMs write docs in ASD-STE100 Simplified Technical
Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.
Add expert SwiftUI Best Practices guidance to your AI coding tool (Agent Skills open format).
Open Source AI trading agent that operates autonomously across 1000+ markets - Polymarket, Kalshi, Binance, Hyperliquid, Solana DEXs, 5 EVM chains. Scans for edge, executes instantly, manages risk while you sleep. Agent commerce protocol for machine-to-machine payments. Self-hosted. Built on Claude.
Desktop app and web server to browse, search and analyze your AI coding assistant history — Claude Code, Codex CLI, GitHub Copilot, Gemini CLI, Cursor, OpenCode and more. 100% offline.
Open-source local AI audio & music studio for macOS & Windows. TTS, voice cloning, songs with lyrics, and multi-track scores — 100% offline, zero API fees.
Open source Grok Bot alternative, Bring your own agent and subscription: message Claude Code, Codex, Gemini CLI, Cursor, Copilot and 40+ AI agents as bots on your own computer, from iPhone, Mac, Windows, Linux or terminal. Agent-agnostic and free. Also a Muse and Dots alternative. Built in Rust.
Add expert Swift Concurrency guidance to your AI coding tool (Agent Skills open format): safe concurrency, performance optimization, and Swift 6 migration.
Cluely - The invisible desktop assistant that provides real-time insights, answers, and support during meetings, interviews, presentations, and professional conversations.
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
Claude Code like Sub-Agents & Workflow Orchestration for Pi — parallel execution, live widget, fleet view, custom agent types, mid-run steering, claude compatible dynamic workflows and more ...
支持 AnyRouter、AgentRouter 的多平台多账号签到,理论兼容所有基于 NewAPI、OneAPI 的平台。
蒸餾李宏毅老師的skill,結合Karpathy的LLM,Fable 5和GPT6 加持 以及 本人親自訪談
The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard | Fable 5 Level Coding for a Fifth the Price - or on a Single GPU
Lightweight Claude Code statusLine: 5h/7d rate-limit usage, reset countdowns, model + context window, prompt-cache age — one line, 3 styles × 9 themes, daemon fast-mode