Explore the directory

A hands-on set of tutorials and code samples, in Python and .NET, for building agents with the Microsoft Agent Framework, covering tools, providers, RAG and multi-agent workflows.

• Tutorials

elem-go is a Go library for building HTML views as plain Go functions instead of a separate template language, so every element and attribute is type-checked at compile time and ordinary Go tooling works on views unchanged.

• Libraries

A Next.js project template that pairs a Claude Code skills-driven workflow with an interview-style process for turning an idea into a spec, architecture, implementation and deployment.

• Agent skills
• Web frameworks

SlideRule is a product-rehearsal engine that takes one sentence describing an idea and runs it through a gated pipeline of spec, pages, structure, bind and closure steps to produce a runnable application preview.

• Agent frameworks

An early-stage, in-development open-source repository of AI agent code and templates for n8n and other automation workflows, published alongside the author's YouTube tutorials.

• Workflow automation
• Tutorials

A Rust library and command-line tool that lets an application call OpenAI, Anthropic, Ollama, DeepSeek, Google, Cohere, Mistral, Hugging Face, ElevenLabs and other LLM backends through one unified, builder-style API.

• LLM gateways

A curated collection of papers, benchmarks, and open-source projects on graph engineering for coordinating LLM agents, organized around a survey moving from individual agent intelligence to system-level intelligence.

• Curated lists
• Papers

A pure-PHP SDK implementing the full Model Context Protocol specification, for building MCP clients and servers that run in ordinary PHP, Apache, and cPanel hosting environments.

• MCP servers

A C library and command-line tool for inspecting and manipulating GGUF model files, showing metadata and tensors, comparing two models for similarity, and inspecting raw tensor weights.

• Inference
• CLI tools

A local-first AI desktop assistant, inspired by Claude Code's Cowork mode, that reads files, runs commands, writes documents, and builds reports autonomously on the user's own machine.

• Agent frameworks

A multi-user, browser-based agent platform where a session's execution target is chosen per session, a cloud sandbox, an SSH host, or a machine behind NAT with no public IP, reached through an outbound-only connector daemon.

• Coding agents

A production-ready MCP server that connects AI assistants to a Nextcloud instance, giving them CRUD access to notes, calendars, contacts, files, and other Nextcloud apps through natural language.

• MCP servers

GitHub's official collection of Copilot plugins, bundling MCP servers, skills, and hooks, plus a marketplace of externally hosted plugins for services such as Advanced Security, Azure DevOps, and Power Platform.

• MCP servers
• Agent skills

A correction-first persistent memory system for AI coding agents that stores structured records of user corrections and measures whether an agent actually stops repeating a mistake, rather than only measuring memory retrieval.

• Agent memory

An open-source, self-hostable agentic IDE that runs a team of coding agents such as Claude Code, Codex, and Cursor from desktop, mobile, or a VPS, each in its own git worktree, steerable from a phone.

• Coding agents

A generalized biological foundation model that unifies nucleic acid and protein language modeling in a single architecture, usable for sequence embedding, masked pretraining, and sequence- or token-level classification and regression tasks.

• Models

A local-first, multi-provider coding agent runtime that defaults to DeepSeek V4 Flash but also supports Codex, OpenAI, Anthropic, OpenRouter, and other providers, with parallel agent roles in isolated git worktrees and OS-level sandboxing.

• Coding agents

A working environment for long-running Codex agents that gives each agent a durable domain responsibility, organizes agents into a governed team, and exposes mature capabilities to customers and collaborators through interface agents.

• Agent frameworks

Video-MME-v2 is a benchmark for evaluating video understanding in multimodal large language models, built from more than 3,300 human-annotation hours across a three-level progression from information retrieval to temporal reasoning.

• AI evals

A plugin for Simon Willison's LLM command-line tool that adds access to models running on a local or remote Ollama server, including chat, image attachments, tool calling, and embeddings.

• Inference

A collection of installable AI-agent skills that teach coding assistants like Claude Code, Copilot, Cursor, and Gemini CLI to write and run test automation code against TestMu AI's cloud of real devices and browsers.

• Agent skills
• Testing

framedex is a Claude Code skill and command-line tool that turns a scattered video and photo archive into a portable, plain-text knowledge base, writing a Markdown sidecar next to each file with transcript, location and scene description.

• Agent skills
• CLI tools

A project-memory skill for AI coding assistants that saves session logs, a project wiki, rules, and TODOs between sessions, so Claude Code, Cursor, or Codex can resume a project without re-explaining it.

• Agent memory

An MCP server that lets AI assistants search, create, update, delete, and aggregate records in an Odoo ERP system through natural language, with a YOLO mode for quick testing against any Odoo instance.

• MCP servers