#
Lists (2)
Starred repositories
Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
This is a cleanroom deobfuscation of the official Claude Code npm package.
Exploring the Model Context Protocol (MCP) through practical guides, clients, and servers I've built while learning about this new protocol.
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
Enhanced MCP server for deep web research
Build datasets using natural language
A powerful VSCode extension that enables MCP server usage in Copilot, giving it access to MCP tools, resources, and more.
Multi AMD GPU Setup for AI Development on Ubuntu with ROCM
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Accessible large language models via k-bit quantization for PyTorch.
A Gradio web UI for Large Language Models with support for multiple inference backends.
Hyperlight is a lightweight Virtual Machine Manager (VMM) designed to be embedded within applications. It enables safe execution of untrusted code within micro virtual machines with very low latenc…
A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
Sky-T1: Train your own O1 preview model within $450
A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models.
Fully open reproduction of DeepSeek-R1
Model Context Protocol Servers
Everything you need to build state-of-the-art foundation models, end-to-end.
Build effective agents using Model Context Protocol and simple workflow patterns
Make websites accessible for AI agents