Explore the directory

A deployable template that runs Claude Code, Codex CLI, GitHub Copilot CLI, Cursor CLI, Gemini CLI or opencode inside Vercel Sandbox to execute coding tasks on a user's repositories through a web UI.

• Coding agents

A local-first control panel for running and managing self-hosted LLM backends such as vLLM, SGLang, llama.cpp and ExLlamaV3, with GPU monitoring, an OpenAI-compatible chat proxy, and agent sessions against local or remote controllers.

• Inference

An open-source, self-hostable runtime for serverless AI workloads that gives a Pythonic interface for fast-starting GPU containers, autoscaling inference endpoints, sandboxed code execution and background task queues.

• Containers
• Hosting

A local-first, self-hostable AI chat workspace that brings multi-model chat, an agent mode for multi-step tool workflows, and deep research with reviewable plans into one app, keeping conversation history in the browser by default.

• Agent frameworks
• Inference

A low-memory IntelliJ IDEA alternative for Java and Spring Boot development, built to review, run and debug code that an AI coding tool has already written.

• Editors

An open-source agent that runs continuously on your own machines to keep applications running, generate infrastructure code, debug Kubernetes and automate deployments, only pinging a human when it needs one.

• CI/CD
• Containers

Kubb is a plugin-based code generation framework that reads an OpenAPI schema and generates TypeScript types, typed clients, TanStack Query or SWR hooks, Zod validators and mock handlers from it.

• Libraries
• APIs

An open-source, cloud-native AI and API gateway and developer portal that connects more than 100 AI models behind one standardized API, alongside general API management, monitoring and a team developer portal.

• LLM gateways
• APIs

An Android GUI agent framework that lets an AI agent see, plan and operate real Android app interfaces on a physical device, returning structured results for each action.

• Agent frameworks
• Mobile

A hand-picked, weekly-updated collection of AI agent research papers published in 2026, sourced from arXiv and organized by topics such as multi-agent coordination, memory and RAG, tooling, evaluation and security.

• Curated lists
• Papers

An offline, Git-native API workspace that stores requests, tests, notes, and documentation together as plain-text files, instead of in a proprietary collection format.

• Testing
• APIs

A from-scratch Rust port of Pi Agent, a native terminal AI coding agent CLI, built to start faster and use fewer resources than managed-runtime or Electron-based alternatives.

• Coding agents
• Terminals

A multi-agent AI platform for data analysis and research that automates hypothesis generation, data cleaning, visualization and report writing using LangChain, OpenAI models and LangGraph.

• Agent frameworks
• Data engineering

A cross-platform client app for Ollama that connects to an existing Ollama server over its API, without hosting a model server on the device itself.

• Inference

A high-performance, cross-language inference engine that runs AI models directly inside an app with low latency, full data privacy and no per-inference API cost, using unified memory on Apple devices.

• Inference

A DeepSeek Harness plugin that turns the current session into a captain able to assemble durable sub-agents, split a goal into dependency-aware tasks, and coordinate them through direct messages and a live web UI.

• Agent frameworks

A collection of fake Blender Python API modules that gives IDEs working code completion and type hints for Blender add-on development, without needing Blender itself installed.

• Libraries

CLM-8B is a System One model trained with contrastive learning to score candidate actions against a state, matching a larger reference model's accuracy on computer-use, gaming and tool-calling tasks at up to 9x lower latency.

• Models

A Vue implementation of Ant Design X, a component library for building AI chat and conversational-interface (LUI) applications compatible with OpenAI-standard model APIs.

• UI kits

A free, in-progress hands-on course of Jupyter notebooks that is the unofficial companion repository to a book on applying large language models, covering techniques, projects and enterprise-scale solutions.

• Tutorials

A Go framework for building production agent systems, providing LLM agents, graph-based workflows, tool calling, session and memory state, knowledge retrieval, evaluation and OpenTelemetry observability in one Go-native stack.

• Agent frameworks

An open-source MCP host desktop app that connects any LLM supporting function calling, such as ChatGPT, Anthropic or Ollama models, to MCP tool servers over stdio or SSE.

• MCP servers

An open-source desktop app where a developer and their coding agent share a canvas: the agent draws diagrams and traces of its work, and clicking a diagram element jumps to the underlying code.

• Coding agents
• Design tools

A single-binary management console with an embedded web UI for installing, configuring, monitoring and updating components of the NullClaw AI-agent ecosystem, including process supervision and health checks.

• Agent frameworks
• Monitoring