Wraps any OpenAI API interface as Responses with MCPs support so it supports Codex. Adding any missing stateful features. Ollama and Vllm compliant.

A pure Python HTML5 parser that just works. No C extensions to compile. No system dependencies to install. No complex API to learn.

"AnyTool: Universal Tool-Use Layer for AI Agents"

ProxLB - An advanced resource scheduler and load balancer for Proxmox clusters.

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

A proxy for minimax-m2, enabling interleaved thinking, and tool calls.

Explanation and full RCE PoC for CVE-2025-55182

Open-Source Frontier Voice AI

Stock and Crypto real-time market data visualization demo

Kubernetes operator for GPU-accelerated LLM inference - air-gapped, edge-native, production-ready

Open Source AI Platform - AI Chat with advanced features that works with every LLM

A research prototype of a human-centered web agent

Go monorepo for a framework to build Linux block devices in userspace

Examples, end-2-end tutorials and apps built using Liquid AI Foundational Models (LFM) and the LEAP SDK

These are commands I use with agents, mostly Claude

Docs for GGUF quantization (unofficial)

Next-gen AI+IoT framework for T2/T3/T5AI/ESP32/and more – Fast IoT and AI Agent hardware integration

🔬 Industrial-grade static analysis for all popular programming languages. Catch 1000+ bug patterns before production

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade archite…

Open Source project using LLMs to translate subtitles (SRT, SSA/ASS, VTT)

Apply the mergeide.reg hack to kvm compatible windows images.

Natural language control for Python CLI tools using locally-trained SLMs (CPU inference)

Vibe code games, to see the progression of LLM abilities

Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.

LLM inference in C/C++

A debugging and profiling tool that can trace and visualize python code execution