Explore the directory

An out-of-tree vLLM plugin that restores GGUF quantization support after it was removed from vLLM's own codebase, letting vLLM serve GGUF-quantized text and vision-language models.

• Inference

A Unity Editor tool that lets an AI assistant create and edit ProBuilder meshes through natural language, covering primitive shapes, extrusion, beveling, material assignment and mesh merging.

• MCP servers

An MCP server plugin for the Tabby terminal that gives an AI assistant 36 tools to run commands, manage tabs, open SSH profiles and transfer files over SFTP, gated by a confirmation dialog.

• MCP servers
• Terminals

A structured planning workflow for AI coding agents that inserts an understand, spec, implement and complete cycle before code is written, keeping requirements and task files in git.

• Coding agents

A curated set of AWS platform-engineering skills, authored by AWS solutions architects and delivered through Claude Code or the Kiro CLI, meant to shorten onboarding for AWS and Kubernetes platform work.

• Agent skills
• Hosting

A toolkit that collects content from Git, Confluence, JIRA, public documentation sites and local files, vectorizes it into a Qdrant database, and serves it back through an MCP search server.

• MCP servers
• RAG

A quantization codec and kernel pack, plus an auto-tuning launcher, for running large language models efficiently on older NVIDIA Pascal and Volta cards that lack DP4A support.

• Inference

A self-hosted, AI-native issue tracker and wiki that runs as one Cloudflare Worker and exposes 121 tools over MCP, so a coding agent can file, move and update tickets and write wiki pages.

• MCP servers
• Backend

An LLM skill that teaches an AI coding agent how to design with OpenPencil, covering its command-line tool, a batch design DSL, MCP design tools and general design conventions.

• Agent skills
• Design tools

A from-scratch training framework for Llama 3 architecture language models, covering data preparation, pretraining, LoRA personality fine-tuning, GGUF export and a small standalone Go inference engine.

• Models

A Claude Code plugin that turns research, ideas and decisions captured while working into an interlinked personal wiki with search, automatic research on a missed lookup, and a browsable web interface.

• Agent skills
• Agent memory

A collection of Ubuntu snap packages that install a locally optimized runtime and model weights for a chosen open language model in one command, tuned automatically for the host hardware.

• Inference

A set of structured AI coding-assistant skills that teach an agent the Frappe framework's DocTypes, REST and RPC API patterns, Desk customization, frontend development and testing conventions.

• Agent skills

A native C/C++ inference engine, built on ggml, for running diffusion transformer image and video generation models locally on resource-constrained and edge devices.

• Inference
• Generative media

A self-hosted personal AI assistant that indexes conversations into facts, rewrites its own system prompt based on what worked, and follows the user across messaging apps.

• Agent frameworks

A curated, terminal-first comparison table of command-line coding agents similar to Claude Code, listing each tool's supported model back-ends, license and implementation language.

• Coding agents
• Curated lists

A browser-based, installable web interface for Claude Code that adds chat, workflow and agent orchestration, MCP server management and cost tracking, launched with a single command.

• Coding agents

A zero-dependency Python module that parses coding-agent session files from Claude Code, Codex and Pi and flattens each tool's own JSONL format into the plain messages list Transformers expects.

• Coding agents
• Libraries

A private desktop app for chatting with, and building with, open models that run entirely on the user's own machine, combining chat, a coding agent, image and music generation, and document Q&A.

• Coding agents
• Inference

A free, openly licensed engineering book and companion course on building and running large language model systems, covering tokenization, serving and fine-tuning models rather than only calling a hosted API.

• Tutorials
• Books

A community-maintained vLLM plugin that serves large language models on AWS Trainium and Inferentia through a Neuron backend, using the same vLLM APIs and configuration as other backends.

• Inference

A research benchmark and training project for small vision-language models that spot factory procedure errors in first-person video by identifying exactly when a step starts and ends, aimed at real-time deviation warnings before an incident happens.

• Models
• AI evals

An embeddable Rust memory engine for AI agents that manages what is remembered instead of only storing it, applying temporal decay, contradiction detection, consolidation and a knowledge graph.

• Agent memory
• Databases

An open source desktop app, written in Go, for working with a bring-your-own-key AI coding agent on local projects, reviewing its file changes and test results inside the app.

• Coding agents