Explore the directory

A self-hostable OSINT tool for investigating email addresses across breach databases, social networks, DNS records and the open web, producing an exposure score and structured findings.

• Security

A Core ML and Apple Neural Engine port of the Laya typed-decision model, which answers structured choice, ordinal-score and yes/no questions in a few milliseconds without generating text tokens.

• Models
• Inference

A VS Code extension that adds local, LLM-assisted code completion, chat and an agentic coding assistant backed by llama.cpp.

• Inference
• Editors

A zero-authentication toolkit of US stock market data endpoints, including CBOE options Greeks, FINRA short volume and SEC EDGAR filings, packaged as a single Skill file for AI coding assistants.

• Agent skills
• APIs

An open-source, multi-agent financial-news analysis platform that monitors Chinese financial news sources in real time and uses LLM-based sentiment analysis and a knowledge graph to surface potential trading signals.

• Agent frameworks

A Java library that embeds the CPython interpreter through JNI, letting Java programs call native Python modules and extensions directly.

• Libraries

An open-source, no-code tool that generates REST, GraphQL, and MCP endpoints for a database, running in a container on Azure, another cloud, or on-premises.

• APIs
• Databases

A collection of AI agent control tools that operate WPS/Microsoft Office, Zotero and Adobe Illustrator through COM automation, giving an agent office CLI commands, academic-research skills and vector-graphic editing commands.

• Workflow automation

A hard fork of GNU Emacs with its roughly 300,000-line C core rewritten in Rust and a GPU-based display engine, aiming for full compatibility with existing Emacs configs and packages alongside modern rendering and performance.

• Editors

A framework that installs into a legacy project and coordinates a team of AI agents to analyze the existing code and produce traceable, executable specifications that coding agents can use to evolve the system safely.

• Agent frameworks

An open-source Windows app, from Microsoft, with more than 25 interactive samples showing developers how to add local AI models and APIs to Windows apps, with exportable C# source.

• Tutorials

An independent toolkit that lets an AI coding agent browse, edit, validate and deploy n8n workflows from VS Code, Cursor or the terminal, with Git-based version control and TypeScript workflow files.

• Coding agents
• Workflow automation

A Model Context Protocol server that gives an LLM web search and page-fetching capability through DuckDuckGo, with rate limiting and results formatted for language-model consumption.

• MCP servers

A macOS menu bar app that tracks how much of your AI coding quota remains across many providers, including Claude, Codex, Gemini, Copilot and Cursor, with reset countdowns and low-quota alerts.

• Desktop utilities

An open-source, browser-based AI agent that runs penetration testing tools autonomously against a connected Kali attack box, reading results and deciding its own next steps.

• Security

An open-source enterprise AI platform that unifies multi-provider model routing, multimodal chat, file and RAG retrieval, MCP tools, usage billing, identity and audit logs into one deployable product.

• RAG
• LLM gateways

A Python library of primitives for building multimodal LLM agents, including personas, tool-using agents and knowledge graphs, that works with local backends such as Ollama and llama.cpp as well as cloud providers.

• Agent frameworks

A plugin that connects instant-messaging bots on nine chat platforms, including Feishu, WeChat, DingTalk, Slack, Telegram, Discord and WhatsApp, to DeepSeek Harness, so a local AI harness can chat through them.

• Coding agents

A Burp Suite extension that integrates AI into a security testing workflow, adding built-in MCP tooling, AI-assisted analysis, and AI-driven passive and active vulnerability scanning alongside manual testing.

• Security

A hands-on Rust course that builds a small, type-safe, auto-vectorized database expression engine across five modules and ten cumulative, independently testable checkpoints.

• Tutorials

A local-first desktop AI assistant that combines chat, durable memory, tool use and multi-agent orchestration to plan a task, delegate parts of it to child agents, and work inside your files and channels.

• Agent frameworks

A system that gives a text-based LLM a voice by wrapping it with low-latency speech-to-text and text-to-speech models, so a user can talk to it out loud.

• Speech

An unofficial Rust reimplementation of Apache RocketMQ, a distributed message queue, aiming for memory safety and high throughput while staying compatible with the RocketMQ protocol.

• Backend

Coffee watches a React codebase for placeholder components and uses the OpenAI chat completions API to generate or update their code each time the source file is saved, inside an isolated Docker container.

• Design tools