Interactive Brokers MCP Server

Open-source AI coworker, with memory

autonomous harness engineering

cull the compromised

An open-source alternative to Claude Cowork (powered by opencode)

Generate UI screens from text prompts and extract their HTML and screenshots programmatically.

A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claud…

Running a big model on a small laptop

Offline multi-agent simulation & prediction engine. English fork of MiroFish with Neo4j + Ollama local stack.

HTTP proxy that fixes malformed tool calls from Qwen3-Coder LLM models for seamless integration with OpenCode

Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

Visual testing tool for MCP servers

A module for controlling the TP-Link Tapo P100 Plugs

Access models from OpenAI, Groq, local Ollama, and others by setting llm-router as Cursor's Base URL

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.

Agentic RL Training at Scale

🔥 Clone and recreate any website as a modern React app in seconds

Async pipelined version of Verl

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …

Scripts for training Qwen 2.5 VL with ms-swift and GRPO

Build your own visual reasoning model

An Open-source RL System from ByteDance Seed and Tsinghua AIR

Repository for write-ups of Sofia Santos' OSINT exercises

Wrapper of 50+ image matching models with a unified interface

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Find possible locations of shadows around the world

Natural Language to Overpass Query Language