AI Client2025
Source code for the GitHub Copilot Chat extension in VS Code: inline chat, an agent mode that plans and edits files autonomously, next-edit suggestions, and MCP integration. Open-sourced so developers can study how Copilot connects to an editor.
AI Agent2025
Collaborates on web tasks in real time: edit its plan before it runs, pause and grab the browser mid-task, and approve irreversible clicks before they happen. A research prototype for studying human-in-the-loop oversight instead of full autonomy.
AI Audio2025
Synthesizes up to 90 minutes of multi-speaker speech in one pass, with as many as four voices in a single conversation. Pairs continuous acoustic and semantic tokenizers at a 7.5 Hz frame rate with a next-token diffusion head on an LLM backbone.
AI Agent2025
Declares and installs agent dependencies from an apm.yml manifest—skills, prompts, agents, plugins and MCP servers—with transitive resolution, security auditing, plugin packaging, and cross-host registries so agents are reproducible across repos.
AI Agent2025
Automates multi-step web tasks by perceiving webpages as pixels and issuing low-level mouse, keyboard and scroll actions. A 7B-parameter multimodal agent trained on 145K synthetic trajectories (FaraGen), designed for on-device deployment and efficient task completion (~16 steps/task).
AI Agent2025
Packages reusable GitHub Copilot building blocks — agents, prompts, instructions, and skills — to make AI-assisted coding repeatable and standards-aligned for a team. Built around an RPI (Research, Plan, Implement) workflow in VS Code.
AI Model2025
Converts images (and other conditions) into high-fidelity, fully textured 3D assets using a 4B-parameter generative model and a field‑free sparse voxel format (O‑Voxel). Handles arbitrary topology, PBR materials, and near real-time mesh/voxel conversions; requires Linux and an NVIDIA GPU with >=24GB memory.
AI Client2026
Command-line tool for browser automation: record and generate Playwright scripts, inspect selectors, capture screenshots. Writes snapshots and screenshots to disk rather than into an LLM's context, cutting token use ~4x versus Playwright MCP.
AI Agent2026
A curated collection of reusable 'skills' that let LLM-driven coding agents perform common .NET/C# tasks — build diagnosis, debugging, testing, data access, upgrades, MAUI, and AI/ML workflows. Implements the Agent Skills standard and is published for agent marketplaces (Copilot CLI, Claude Code, Cursor).
AI Infra2026
Runs untrusted code (LLM outputs, plugins, and third‑party tools) inside cross‑platform, policy‑driven sandboxes. Provides a unified JSON schema and a TypeScript SDK that sit on multiple containment backends (process sandboxes, LXC/Bubblewrap, microVMs). Early preview with known permissive profiles — not yet a security boundary.
MLOps2026
Runs durable, checkpointed SQL workflows inside PostgreSQL so long-running data and AI pipelines can resume after crashes without external orchestrators. Provides a SQL DSL, in-process background worker, and Postgres-backed state—useful for embeddings, ETL, scheduling, and fan-out jobs when you can install extensions.
AI Client2026
Browser-based visual editor and learning hub for RDF/OWL ontologies (targeted at Microsoft Fabric IQ): interactive graph exploration, a searchable catalogue, an embeddable viewer, RDF/XML import/export, and a natural-language→ontology preview — all as a zero-backend static site.