Stars
Interactive error analysis skill for AI agents. Studies LLM trace datasets, builds a review UI, monitors annotations, categorizes failure modes, proposes new samples.
Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.
An Obsidian plugin that embeds Claude Code/Codex as an AI collaborator in your vault
AI agents running research on single-GPU nanochat training automatically
Microsoft 365 Agents channel for OpenClaw with integrated Graph API tools (alpha)
🥧 HTTPie CLI — modern, user-friendly command-line HTTP client for the API era. JSON support, colors, sessions, downloads, plugins & more.
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
Maven Lightning Lesson on Product Thinking for Agentic Development - Specflow framework, patterns, and live tnyOffice demo
Python package for estimating a CIs for metrics evaluated by LLM-as-Judges.
Official community-driven Azure AI Examples
The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.
Main reference implementation for NLWeb, implemented in Python.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
Anthropic's educational courses
For the Takeoff Cursor course.
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
OpenAI Sora videos turned into Spatial 3D videos for the Apple Vision Pro