Explore the directory

An open-source book that derives LLM inference and training system design from hardware constraints and model architecture, with quantitative worked estimates and companion calculation tools.

• Books

A local-first web-intelligence toolkit for AI coding agents, providing search, fetch, crawl, extract, cache and research tools over MCP with no API keys or per-query cost.

• MCP servers
• Browser automation

A starter stack combining LangChain, Neo4j and Ollama with Docker, meant as a template and set of demo applications for building a GenAI application.

• Agent frameworks
• RAG

An ecosystem of code generators that turn OpenAPI specifications into production-ready TypeScript or Python SDKs, along with validators, mocks, and other client code.

• APIs

The .NET team's curated set of portable Agent Skills and host-specific custom agents that help AI coding agents perform .NET and C# development tasks.

• Agent skills

A CLI tool and visualization dashboard that tracks token usage and cost across many AI coding agents from the terminal, with an optional public leaderboard.

• CLI tools
• Monitoring

A curated list of LLM and VLM inference research papers with accompanying code, covering Flash-Attention, Paged-Attention, quantization, parallelism and related inference-optimization techniques.

• Curated lists
• Papers

An open-source framework that generates production-ready Lottie animations through Claude Code, Codex, or any other coding agent that supports skills, from a plain-language prompt.

• Agent skills
• Generative media

A Go REPL with line editing, multi-line input, package-import completion, and automatic printing of declared values, evaluating each entered expression by running it as a Go program.

• Languages

An AI-powered custom node for ComfyUI that assists with building, debugging and rewriting image-generation workflows.

• Generative media

A package for running inference and fine-tuning Vision Language Models, including omni models with audio and video support, on Apple Silicon Macs using MLX.

• Models
• Inference

A 3D interactive visualization of a GPT-style large language model network running inference, showing a small trained model sorting letters and rendering larger networks such as GPT-2.

• Tutorials

A prompt gallery, image-prompt library, and two agent skills plus a CLI for generating and editing images with OpenAI's GPT Image 2 and 2.5 models.

• Agent skills
• Generative media

An autonomous red-team agent platform, orchestrated with LangGraph, that runs reconnaissance, exploitation and reporting for authorized penetration-testing engagements.

• Security

A template for self-hosted AI coworkers, each given its own browser, files and tools, with every action decided before it happens and recorded after, built on the AG-UI protocol.

• Agent frameworks

A framework from the creators of Terminal-Bench for evaluating and optimizing coding agents and language models across thousands of parallel sandboxed environments.

• AI evals

An inference library for Recursive Language Models, a task-agnostic paradigm that lets a language model programmatically examine, decompose and recursively call itself over near-infinite-length contexts.

• Models
• Inference

An enterprise-grade AI agent platform offering multi-provider LLM management, RAG-backed knowledge bases, visual workflow orchestration and multi-agent coordination.

• Agent frameworks
• RAG

A framework for building persistent, stateful AI agents on Cloudflare using Durable Objects, so each agent has its own state, storage and lifecycle and hibernates when idle.

• Agent frameworks

A self-hostable personal AI assistant combining an LLM, a user's own knowledge base and autonomous agent loops, so agents can browse the web, run code and call MCP-compatible tools.

• Agent frameworks

An Apache incubator project for a high-performance agent workspace that records every action it takes as an append-only event log, so the log itself drives its UI, prompts and crash recovery.

• Coding agents

A collection of training recipes for aligning language models with human and AI preferences, spanning supervised fine-tuning, DPO, RLHF and related post-training techniques.

• Models

A CLI tool that turns a codebase's structure, decisions, history and team knowledge into a context graph, so AI coding agents can answer questions, plan changes, debug failures and write code with project-specific context.

• Agent memory

An embedded scripting language and evaluation engine for Rust, with a JavaScript-and-Rust-like syntax, dynamic typing, and tight integration with native Rust functions and types.

• Languages