Explore the directory

A self-hosted, Kubernetes-based control plane, built on Crossplane, that provisions and schedules AI inference across any GPU infrastructure and exposes each deployed model behind one OpenAI-compatible endpoint.

• Inference
• Hosting

An MCP server that integrates AgentQL's structured web-data extraction into Claude, VS Code, and Cursor, pulling described fields out of a page from a URL and a prompt.

• MCP servers
• Browser automation

A pack of practical ComfyUI custom nodes for loading and resizing images, comparing generated video results, and building image and video generation workflows, plus standalone browser tools.

• Generative media

A research framework for retrieval-augmented generation across text, image, video, and mixed-granularity corpora, using a learned or training-free router to pick the right corpus per query.

• RAG

A persistent memory extension for the Pi coding agent, keeping durable facts, a daily log, and a scratchpad as plain Markdown files, with optional semantic search across everything remembered.

• Agent memory

A plugin for the NoneBot chatbot framework that adds DeepSeek-powered conversation and question answering to a bot, with multi-turn context and Markdown-to-image rendering.

• Inference

A research library for probabilistic programming with language models, letting a user write programs that combine LLM calls, ordinary code, and probabilistic conditioning, solved by sequential Monte Carlo.

• Agent frameworks

A free, open-source Mac app for AI safety and interpretability research, letting a user inspect a model's internal activations, run probes and sparse autoencoders, and test a hypothesis interactively.

• AI evals

A GitHub Skills exercise that walks an intermediate developer through building a multi-tier fitness application using GitHub Copilot's agent mode.

• Tutorials

A self-hosted, no-code MCP gateway that turns any REST, SOAP, GraphQL, OData, or SQL API into MCP tools for Claude, ChatGPT, and Copilot, with more than 260 ready-made connectors.

• MCP servers

A free graphical modeling tool for designing hierarchical UML state machines and generating the real-time embedded code that implements them with the QP frameworks.

• Design tools

A collection of developer samples showing how to use the KDB.AI vector database, from getting-started guides to industry-specific retrieval-augmented generation use cases.

• Databases
• Tutorials

A minimal Rust crate providing the agent loop, streaming, and tool execution needed to build an LLM agent, working with local models out of the box and seven hosted or local protocols by configuration.

• Agent frameworks

A Terraform module that deploys an end-to-end pipeline for extracting question-and-answer pairs from documents and fine-tuning a large language model on them using Google Cloud Vertex AI.

• Models
• Hosting

An enterprise multi-agent and ChatBI platform combining multi-agent collaboration, retrieval-augmented knowledge, direct database connections, and sandboxed code execution behind role-based access control.

• Agent frameworks

A coding agent implemented in under 200 lines of dependency-free Python, arguing that current models make elaborate agent frameworks unnecessary.

• Coding agents

A set of composable AI skills, organized into small guardrails, multi-step workflows, and guided interviews, that push a coding assistant toward design-first, standards-aware development.

• Agent skills

An Emacs package for AI pair programming that runs Claude Code, Codex, Gemini, or other terminal AI coding tools inside Emacs sessions, deliberately without its own MCP or IDE layer.

• Coding agents
• Editors

A structured, MCP-accessible catalog of authoritative external data sources, government, international-organization, and academic, meant to ground AI agents' answers in verifiable primary evidence.

• MCP servers
• RAG

A native macOS app that turns a user's starred GitHub repositories into an organized, locally searchable, AI-assisted knowledge base instead of an unmanageable bookmark list.

• Desktop utilities

A locally hosted dashboard that coordinates three separate coding and research agents behind one memory layer, scheduler, and skill hub, with cost tracking across providers.

• Agent frameworks

A high-performance serving implementation of Qwen3-TTS that streams speech over HTTP and WebSocket with under 50 milliseconds to first audio at 10 requests per second on a single H100.

• Speech

A local MCP gateway that lets a developer set up MCP servers once and share them, with credentials and permission controls, across Claude, Cursor, Codex, VS Code, and other clients.

• MCP servers

An open-source, Rust-based autonomous coding agent with a native GUI, a terminal mode, and MCP and ACP integrations, that shows exactly which tools it ran and what each one returned.

• Coding agents