Explore the directory

A GitHub Action that scans pull requests for AI-agent governance gaps, missing audit trails, policy enforcement and human oversight, and posts a compliance report mapped to the EU AI Act, DORA and ISO 42001.

• Security
• CI/CD

An experimental Haskell compiler, written incrementally by AI models, tracked as a percentage of the Stackage package set it can successfully build.

• Languages

An autonomous AI agent that runs a senior-analyst-style forensic investigation loop on top of the SANS SIFT Workstation, restricted to a fixed set of read-only forensic tools, and produces an auditable, traceable incident report.

• Security

An open-source study guide of more than 60 pages covering agentic AI from LLM foundations through production system design, framework walkthroughs and an interview question bank.

• Tutorials

An autonomous coding-agent CLI and Python library that plans, codes, reviews and tests a change, then reports separately whether the run completed and whether anything the agent did not write actually verified the result.

• Coding agents

An SDK and command-line surface for authoring, validating, evaluating and syncing skills for Codex and other AI coding agents, currently being split into a separate Skills SDK and a Skills Foundry.

• Agent skills

A bridge daemon that lets AI coding agents from different tools, including Claude Code, Codex, OpenClaw, Hermes Agent, Gemini CLI, Zed and VS Code, send prompts to and collaborate with each other over a shared A2A and ACP hub.

• Agent frameworks

A Swift package that decomposes an image with Apple's Vision, CoreML, ARKit and LiDAR frameworks, fans it out into several vision-language-model calls, and aggregates typed results.

• Libraries

An experimental local background service that watches a project's repositories and compiles their changing state into a compact context artifact an AI assistant can read directly.

• Agent memory

A Ballerina client library implementing the Agent2Agent (A2A) protocol, letting one AI agent discover another agent's skills and delegate and track work with it.

• Agent frameworks

An unofficial implementation for fine-tuning VGGT-Omega, a feed-forward 3D reconstruction model, on your own data, plus a standalone GPU-free 3D reconstruction viewer.

• Models

A beginner-to-advanced course that teaches the Model Context Protocol by building MCP servers and clients from scratch in Python, and deploying them locally and remotely.

• MCP servers
• Tutorials

A VS Code extension for editing SysML v2 and KerML systems-engineering models as text and diagrams, with validation, diagram views and CI-friendly automation.

• Editors

A Docker image for a self-hosted document-parsing server, powered by IBM Docling, that converts PDF, DOCX, PPTX, HTML and more to Markdown or JSON with optional GPU acceleration.

• RAG
• Containers

An open-source UI component library whose 59 components are copied into your project as editable source files, built on Base UI and StyleX with typed design tokens.

• UI kits

An MCP server for Zitadel identity management that lets AI tools create, provision and manage users, projects, applications, roles and service accounts through natural language.

• MCP servers
• Auth

A fully local, full-duplex voice assistant for Windows that lets a user interrupt it mid-sentence and answers using visual context captured from the desktop the instant the user speaks.

• Speech

A cross-platform desktop application for transcribing audio and video offline using OpenAI's Whisper models on the user's own machine, with an optional OpenAI backend when a user supplies an API key.

• Speech

An open-source voice assistant that runs on your own computer and your own OpenAI key: you talk to it, and a background team of AI bots handles slower work in a real browser, a shell and your files while the voice call keeps talking.

• Agent frameworks
• Speech

A self-hosted AI-text detector that runs 23 independent detection engines on CPU and combines their scores into one calibrated forensic result, with published accuracy figures and its own documented failure modes.

• AI evals

A self-hosted evidence store for coding agents that captures model calls, code changes, developer decisions and check results, so teams can compare models, reuse prior session context, and build training datasets.

• AI evals

A Chrome extension paired with a local Python backend that indexes the pages a user actually reads and lets them search their browsing history in plain English using local retrieval-augmented generation.

• RAG

A reference implementation of production-style retrieval-augmented generation for document question answering, combining hybrid retrieval, citation grounding and a streaming chat API.

• RAG

A step-by-step tutorial notebook for fine-tuning the Qwen2.5-VL-7B vision-language model with Hugging Face TRL for visual question answering on the ChartQA dataset.

• Tutorials