Explore the directory

A terminal-first coding agent that lets you bring your own API key or point at a local model, with transparent multi-model routing, per-turn cost display, session branching, and a separate critic agent that grades work against a rubric.

• Coding agents

A desktop-wallpaper visualization that renders your running Claude Code agents as pixel-art office workers, walking to desks, asking permission before risky actions, and holding meetings that can turn into proposals you approve or reject.

• Coding agents
• Desktop utilities

A multi-agent development stack spanning a Python SDK and CLI, a Studio server, and a desktop workspace, with meta-agent orchestration, connections to many LLM providers, an MCP hub, and layered agent memory.

• Agent frameworks
• MCP servers

A terminal AI coding assistant compatible with Claude Code's configuration and skills, built to switch between multiple LLM providers within one session through its own router integration.

• Coding agents
• LLM gateways

A lightweight, open-source vision-language model, about 1.2 billion parameters, for unified document parsing across both digital documents and camera-captured photos of documents.

• RAG
• Models

A Claude Code setup that gives one session a supervisor role over a planner, plan reviewer, coder, and tester, so a single build plan becomes the shared contract the whole team works from instead of copy-pasting between separate chats.

• Coding agents

A vendor-neutral guide to designing, governing, and scaling multi-agent systems, covering building blocks, memory, inter-agent communication, observability, evaluation, security, and governance.

• Agent frameworks
• Books

A benchmark suite that measures the runtime of Apple MLX operations and layers across Apple Silicon chips and select CUDA GPUs, compared against equivalent PyTorch operations.

• AI evals

An MCP server that combines Semantic Scholar and arXiv into one literature-search toolset, giving Claude, Cursor, and other MCP clients parallel search, citation and author graphs, recommendations, and arXiv source downloads.

• MCP servers

A JSON-first SDK, CLI, and MCP server that lets AI agents publish short-form video to TikTok, Instagram Reels, YouTube Shorts, X, and Facebook through one API, without building each platform's integration separately.

• MCP servers
• APIs

An MCP server that exposes Actual Budget's accounts, transactions, and reporting data as tools and resources so LLM assistants like Claude can query and manage a personal budget through natural language.

• MCP servers
• APIs

A memory-optimized ROCm build of Qwen 3.8 27B for AMD Strix Halo APUs, combining 4-bit block quantization, speculative decoding, and a KV-cache scheme to raise inference throughput on unified-memory hardware.

• Models
• Inference

A platform-neutral browser automation layer for AI agents that pairs a Chrome extension with a CLI, JavaScript, Python, and Go SDKs, and an MCP server for driving real Chrome sessions.

• MCP servers
• Browser automation

A Python agent that edits and mutates its own source code in a continuous loop, using AST-level transformations rather than model-generated diffs, to add error handling, optimizations, and new capabilities.

• Coding agents

A packaging and distribution repository for GRACE, a contract-first AI coding methodology built around semantic markup, XML project artifacts, and knowledge-graph navigation, plus an optional CLI.

• Agent skills

A research project exploring autonomous AI agent collaboration for generating a web application from scratch, where a user assembles a team of AI agent roles and states what to build, and the agents plan and carry out each development step together.

• Coding agents
• Agent frameworks

A self-evolving general-purpose AI assistant built on a microkernel architecture, that learns from its own successes and failures through a Bayesian bandit decision loop and can be extended at runtime by describing a new component in natural language.

• Agent frameworks

A semantic search engine for files and code that builds a reusable index and lets a developer or an AI coding assistant find a file by describing what it does, through a CLI, a Python API or an MCP server.

• RAG
• CLI tools

An MCP server and CLI that lets an LLM agent browse DataForSEO's API documentation and make authenticated calls against DataForSEO's SEO data APIs, over stdio by default or over HTTP with OAuth 2.0.

• MCP servers
• APIs

An open-source framework for quickly building, evaluating and reproducing retrieval-augmented generation systems, covering text-based, multimodal and web-accessible scenarios with an end-to-end pipeline from data preparation to evaluation.

• RAG
• AI evals

A community-maintained catalog of real-world use cases for Hermes Agent, the self-improving AI agent from Nous Research, where every entry must link to a primary source such as official documentation, a companion repository or a first-person write-up.

• Agent frameworks
• Curated lists

A local-first runtime that puts Claude Code or Codex to work on an open-ended research problem for hours, running competing families of ideas against a compute budget and a scoreboard.

• Agent frameworks

A community-maintained directory of resources for Google's Agent2Agent (A2A) protocol, including documentation, official and community samples, tools, and compatible services.

• Agent frameworks
• Curated lists

A curated showcase of original student projects, including MCP servers, AI agents, web apps, and automation tools, built for a postgraduate Applied AI Engineering course.

• Curated lists