Explore the directory

A free textbook on building an LLM inference stack from scratch in Rust, covering the driver interface, attention kernels, a paged KV cache, a scheduler, multi-GPU collectives and a quantisation pipeline.

• Inference
• Books

A user-owned personalization memory layer for AI agents that models a person's preferences, habits and communication style as a fuzzy graph, with a deterministic zero-LLM core and optional human-approved enrichment.

• Agent memory

A collection of configurations for the Kiro IDE — agents, hooks, steering files, powers and skills — documented against Kiro's current schemas, covering AGENTS.md, permissions and hook triggers.

• Agent skills
• Editors

A browser-based retrieval-augmented generation app that answers questions over YouTube videos, podcasts and PDFs, with every claim in the answer carrying a citation that deep-links back to the source, built with Next.js and Gemini.

• RAG

A self-hosted, Claude-powered autonomous coding agent that plans a project, writes code and tracks its own tickets unattended for hours, with two-way Telegram control from a phone.

• Coding agents

An open-source, self-hostable AI agent that asks several models the same hard question and blends their answers, then plans, uses tools and checks its own work on longer tasks, remembering what works across sessions.

• Coding agents

A self-hosted identity provider for AI agents that gives each agent its own revocable identity, authority that can only narrow when delegated, and a tamper-evident audit trail it cannot write to itself.

• Security
• Auth

A deterministic, read-only static auditor for GGUF model files that flags chat-template backdoors, SSTI risks, and suspicious tokenizer, config or model-card content without ever rendering templates or loading tensor weights.

• Security

The complete sample code for a Japanese book on training and using local LLMs in Python, covering embedding a local model in an app, building a transformer from scratch, fine-tuning, multimodal generation and RAG.

• Tutorials
• Books

A dependency-free WebGPU runtime for running 1-bit, binary-weight large language models directly in the browser, with GPU-resident decoding, streaming output and cross-turn KV-cache reuse.

• Inference

A curated collection of open-source AI agent frameworks, research papers and production deployment guides, organized by what a developer wants to build and by capability.

• Agent frameworks
• Curated lists

A collection of reference implementations of agentic retrieval-augmented generation, evaluation and orchestration workflows, built for Vector Institute's Agent Bootcamp using current Python agent frameworks.

• RAG
• Tutorials

A large-scale dataset and benchmark for detecting errors in multi-agent systems, with systematically generated failure scenarios and verifiable ground-truth labels across several agent frameworks.

• AI evals

An SGLang Docker image, with several out-of-tree patches, for running LLM inference on AMD's consumer Strix Halo APU (Ryzen AI Max+ 395 / Radeon 8060S), a platform AMD's own official images do not target.

• Inference
• Containers

The specification and message definitions for Ping Protocol, Blue Robotics' binary message format for sonar devices, together with tools that generate documentation and implementation source code from those definitions.

• Libraries

A quantization-aware training framework built on Keras 3 that optimizes neural-network bit-widths by gradient, down to a per-weight and per-activation level, for real-time deep learning on FPGAs and other edge devices.

• Models

A command-line tool for setting up and running local AI models on AMD GPUs, shipped as a single prebuilt binary with a full-screen TUI dashboard for GPU telemetry, model serving and chat.

• Inference
• CLI tools

A production-focused guide for AI and machine-learning system design interviews, working through model selection, LLM gateways, caching, streaming, cost control and evaluation with decision tables and architecture diagrams rather than flashcards.

• Books

A structured, topic-by-topic roadmap and resource collection for learning generative and agentic AI, moving from math and Python foundations through machine learning, deep learning, LangChain, RAG, vector databases, LangGraph and the Model Context Protocol.

• Tutorials

A high-performance, in-memory vector database and search engine in Rust for semantic search and document indexing, exposed over binary RPC, REST, gRPC, GraphQL and MCP with native SDKs in five languages.

• RAG
• Databases

A Claude Code skill for multi-model AI coding: Claude writes the task brief and reviews the finished diff, while GPT-6 Sol implements the change through the OpenAI Codex CLI, so the same model never grades its own work.

• Agent skills

A command-line interface and MCP server that gives AI coding agents a local, cited memory layer for a Git repository, built from generated wiki pages, symbol context, git history and dead-code and risk signals.

• MCP servers
• Agent memory

An official MathWorks toolkit that gives AI coding agents an MCP server and companion skills for running Polyspace static analysis on C and C++ code, fixing violations and formally verifying run-time safety.

• MCP servers
• Code quality

A setup guide for running the Pi coding agent inside an isolated Docker Sandbox microVM while it talks to a local llama-server inference backend running on the host GPU.

• Containers
• Tutorials