Explore the directory

A self-hosted, open-source alternative to Jira, Trello, ClickUp and Monday where AI agents work inside the same Scrum board and sprints as human teammates.

• Workflow automation

A portable AI coding assistant setup that installs Claude Code, Codex and OpenClaw onto a USB drive or a computer with a single script, keeping configuration and API keys stored locally.

• Coding agents

A fast, plug-and-play LSP client for Emacs that offloads language-server communication and analysis to an external multi-threaded process to avoid stalling the editor.

• Editors

An on-device AI inference library for React Native, built on Meta's ExecuTorch runtime, that runs machine learning models on a phone with no network calls.

• Inference
• Mobile

A CLI and MCP server that converts Korean government and office documents (HWP, HWPX, PDF, Office formats and scanned images) into Markdown, with table reconstruction, form filling and document diffing for AI agents to read and act on.

• MCP servers
• RAG

The official WordPress package that exposes WordPress abilities as Model Context Protocol tools, resources and prompts, so MCP-compatible AI agents can discover and call WordPress functionality.

• MCP servers

An MCP server that indexes official documentation from websites, GitHub, npm, PyPI and local files, so an AI coding assistant can query the exact library version a project depends on.

• MCP servers
• Documentation tools

An open-source, continuously updated benchmark research platform that tracks real-world inference performance of popular open-source serving frameworks such as vLLM, SGLang and TensorRT-LLM across current GPU hardware and models.

• Inference
• AI evals

A curated Chinese-language collection of research summaries, papers and resource links on knowledge graphs, natural language processing and dialogue systems, including a survey of open-source question-answering systems.

• Curated lists
• Papers

A bundled desktop client for DeepSeek Harness that packages the official CLI with a native window, system tray, built-in Node.js runtime, ten UI themes and a plugin marketplace, currently undergoing a major rewrite.

• Coding agents

A systematic literature review indexing more than 861 papers on large language models applied to cybersecurity, organized around domain-specific LLMs, defensive and offensive applications, and future research directions.

• Security
• Papers

A free, open-source terminal coding agent that runs entirely on local hardware with a bundled llama.cpp inference server, auto-configuring itself for NVIDIA GPU, CPU or Apple Silicon with no subscription or per-token billing.

• Coding agents
• Terminals

A roughly 1,300-line, fully readable coding-agent engine meant as a teaching reference for how a tool like Claude Code actually works, so a developer can read the whole thing and fork it into something of their own.

• Coding agents
• Tutorials

A community-maintained vLLM hardware plugin that runs high-performance LLM inference on Apple Silicon Macs using MLX as the compute backend.

• Inference

A PostgreSQL extension for scalable, disk-friendly vector search, the successor to pgvecto.rs, that compresses vectors with RaBitQ and autonomous reranking to cut storage cost while preserving search quality.

• RAG
• Databases

An open-source, MIT-licensed visual workspace for running and reviewing multiple coding agents such as Codex, Claude Code and OpenCode in parallel, with WYSIWYG editors, session tracking and an iOS companion.

• Coding agents

Official code samples for the Agent2Agent protocol, demonstrating multi-agent interoperability with example agent servers and clients in Python, Go, .NET, Java and Node.js.

• Agent frameworks
• Tutorials

A GPU-accelerated data curation toolkit that builds repeatable pipelines to load, filter, deduplicate and transform large text, image, video and audio datasets for AI training, running the same pipeline on a laptop or a multi-node Ray cluster.

• Models
• Data engineering

A CLI that manages a pool of reusable, isolated git worktrees per repository, so each coding-agent session gets its own environment instantly, with dependencies and build cache preserved between uses.

• Coding agents
• Git

A terminal multiplexer for running several AI coding agents in parallel, giving each one its own tmux pane and isolated git worktree and branch so they can work at the same time without conflicts.

• Coding agents
• Terminals

A high-performance code-intelligence engine that indexes a codebase into a knowledge graph and exposes it to AI coding agents and IDEs over CLI, MCP or a web UI, aiming to cut the tokens an agent needs per response.

• MCP servers
• Agent memory

A daily-updated collection of Nix packages for AI coding agents and related development tools, letting each one be run or installed reproducibly through Nix without a separate package manager.

• Coding agents

An independent MCP server that connects AI agents to 70 Brazilian public data sources covering the economy, legislation, transparency, the judiciary, elections, health, education, public safety and aviation.

• MCP servers

A KV-cache compression method for LLM inference that quantizes cached keys to 3 bits and values to 2 bits using Triton kernels, integrated with vLLM to cut memory use and raise usable context length.

• Inference