Explore the directory

A Python library that generates Avro schemas from dataclasses, Pydantic models, and Faust records, and serializes or deserializes instances against those schemas.

• Libraries
• Data engineering

A spec-driven autonomous engineering workflow, packaged as a Kiro Power, that walks an AI coding agent through reverse-engineering existing code, planning, test-driven building, adversarial validation and shipping a pull request.

• Agent skills

A command-line tool written in Go that generates direct download links for Ollama models and installs locally downloaded model files and manifests into Ollama.

• Inference
• CLI tools

A structured, human-verified knowledge base of API documentation for over 500 platforms and more than 80,000 tools, built for AI agents to look up parameters, authentication flows and edge cases instead of guessing.

• Agent memory
• APIs

A set of extensions for Visual Studio, VS Code and Claude Code that adds Azure-specific skills and an MCP server so an AI assistant can answer questions about a user's Azure services and help with Azure management and development from inside the IDE.

• MCP servers
• Agent skills

A curated list of guides, courses, prompt libraries, tools, research papers and communities for prompt engineering with large language models and generative AI.

• Curated lists

A Raycast extension that connects to a local or remote Ollama server for chat, quick writing-assistance commands, image understanding and model management, directly from Raycast's launcher.

• Inference
• Desktop utilities

A build system that cross-compiles the OpenCode terminal AI coding assistant, along with the Bun runtime and WebKit's JavaScriptCore engine it depends on, to run natively on Android devices through Termux.

• Coding agents
• Mobile

A learning project that implements a local knowledge base and retrieval-augmented question answering system with Streamlit, LangChain and Chroma, letting a user upload text files and then chat with answers grounded in that uploaded content.

• RAG
• Tutorials

AI assistant tooling for the Godot Engine that gives MCP-capable apps such as Claude, Codex or Cursor a live connection to an open Godot project, plus an optional in-editor chat dock for talking to a model directly.

• MCP servers

An open-source template repository for building an LLM-maintained knowledge base: raw sources go in one folder, and an LLM ingests them into cross-linked wiki pages, answers questions by citing those pages, and audits the wiki for problems on request.

• Agent memory

An open-source framework, no longer maintained, for production deployment of large language, embedding, reranking, speech, and image and video generation models behind a single OpenAI-compatible API port.

• Inference

A C# editor addon for Godot that exposes editor operations, such as creating nodes, editing scenes, managing resources and scripts, and capturing screenshots, as MCP tools so an AI coding assistant can inspect and drive a Godot project directly.

• MCP servers

A Go framework for building AI agents with pluggable model providers, short and long-term memory, input and output guardrails, and multi-agent coordination patterns such as using one agent as a tool for another.

• Agent frameworks

A tutorial project that builds a multi-agent research assistant: a main agent delegates a task to web search, database and private knowledge base sub-agents, then merges their findings into a Markdown or PDF report streamed over WebSocket.

• RAG
• Tutorials

An experimental vLLM plugin that adds Attention-FFN Disaggregation, splitting attention and feed-forward computation across separate GPU or Ascend NPU workers without modifying vLLM itself.

• Inference

A repository combining a custom experimental machine learning algorithm for tabular data with a hand-curated, machine-readable knowledge base of roughly 900 university courses, research papers and explainers, each normalized into Markdown with full provenance.

• Models
• Curated lists

A tool that networks computers a user already owns into a single OpenAI-compatible endpoint, routing each inference or training request to whichever machine runs the right model, with no account or relay required.

• Inference
• LLM gateways

An open-source, agentic security operations center with specialized AI agents for tasks such as triage, plain-text playbooks for multi-agent workflows, and over 7,000 community detection rules, running against a locally hosted or remote LLM of the user's choice.

• Security
• Monitoring

A community-maintained collection of agent skills that teach AI coding assistants how to use Apify Actors for specific tasks, such as ad intelligence research, AI search visibility tracking or app store data, installable into Claude Code, Cursor, Codex and dozens of other agents.

• Agent skills
• Curated lists

A coding agent that drives an existing AI coding CLI, such as Claude Code, Codex or OpenCode, and adds role-based team orchestration on top, assigning depth-appropriate work to advisory product, architecture, frontend, backend, QA, security and DevOps roles under one coordinator.

• Coding agents

An extension for the Pi coding agent that renders tool calls more compactly, with richer diff views for file edits and adjustable presets, to keep the terminal UI readable during long sessions.

• Coding agents

A TypeScript framework for building MCP servers that enforces security at the architecture level, filtering all data through a typed egress layer before it reaches the model and removing tools from the agent's namespace when workflow state forbids them.

• MCP servers
• Security

A desktop app that proxies MCP tool call traffic between AI apps such as Cursor, Claude, VS Code and Windsurf and their MCP servers, checking each request and response against a set of signatures and asking the user before allowing anything it flags as harmful.

• AI evals
• Security