Explore the directory

A Python library of extension and helper tools for everyday data-science and machine-learning tasks, including ensemble methods, feature selection and frequent pattern mining.

• Libraries

Observability and policy enforcement for AI agent harnesses, hooking coding CLIs and chat gateways to capture every run and block dangerous tool calls before they execute.

• AI evals
• Security

An MCP server that connects a user's Zotero research library to Claude, ChatGPT and other AI assistants so they can search, read, annotate and organize papers.

• MCP servers

A framework and no-code GUI for fine-tuning large language models, with a command-line interface for the same workflows.

• Models

A tool that parses a multi-language codebase with Tree-sitter, builds a knowledge graph of its structure in Memgraph, and lets a developer query, edit and optimize the code in plain English.

• Agent memory
• RAG

An AI-powered bug-bounty toolkit that runs reconnaissance, tests for vulnerabilities, validates findings against a strict gate, and writes a submission-ready report for platforms such as HackerOne, Bugcrowd, Intigriti or Immunefi.

• Security

A GitHub CLI extension that lets developers define AI-powered repository automation in Markdown with YAML frontmatter and run it securely as GitHub Actions.

• CI/CD

An open-source machine learning platform that unifies training, fine-tuning, chat and evaluation of models into one interface, running locally or scaled to GPU clusters.

• Models
• AI evals

A self-hosted, open-source AI video production workspace that turns a novel, finished script or product material into characters, storyboards, video clips and an editable draft.

• Generative media

A macOS CLI and menu-bar app that captures screenshots, inspects accessibility elements and drives native UI automation, exposing the same tools to MCP clients.

• MCP servers
• Desktop utilities

A curated list of references for 'vibe coding', collaborating with AI to write code, spanning browser-based tools, IDEs, mobile apps, plugins, local apps and command-line tools.

• Curated lists

A self-hosted, multi-user, multi-agent AI assistant that runs entirely on a user's own machine, aiming to give teams, families and individuals an independent, collaborative agent environment.

• Agent frameworks

An open-source Python library of more than 500 financial analysis methods, written to be fully transparent about their calculations, with an optional MCP server for querying them without code.

• Libraries

An open-source inference engine that profiles a user's own hardware, recommends the best open models for it, and tunes them for that exact machine, running on Apple Silicon, NVIDIA, AMD or CPU-only setups.

• Inference

A red-team adversary-simulation platform covering the phases of the MITRE ATT&CK framework, with a built-in LLM agent for automated processing and decision support.

• Security

A plugin for the Serverless Framework that emulates AWS Lambda and API Gateway on a local machine, so a serverless project's handlers can be tested without deploying to AWS.

• Testing
• Hosting

An application that transforms unstructured data such as PDFs, documents, text files, YouTube videos and web pages into a structured knowledge graph stored in Neo4j using large language models.

• RAG
• Databases

An open-source personal cloud operating system, built on Kubernetes, for running AI agents and LLMs on hardware a person owns and controls in plain language.

• Containers
• Hosting

A PHP-based, self-hosted URL shortener that serves shortened links under your own domain, with a REST API and official Docker image.

• APIs
• Networking

A model router that sits in front of Anthropic, OpenAI and Gemini APIs and picks the best available model for each request using a small on-device embedder rather than a prompt-based heuristic.

• LLM gateways

A cross-platform desktop AI assistant and MCP client that connects to major model providers, supports a local knowledge base, and lets a user install tools built as MCP servers.

• MCP servers
• Inference

An open-source, agentic platform for building and deploying full-stack applications on Cloudflare by describing what to build to an AI coding agent.

• Coding agents
• Hosting

A filesystem-first framework for building durable AI agents, keeping an agent's instructions, tools and configuration in conventional project files so it is easy to inspect, extend and operate.

• Agent frameworks

A visual, canvas-based editor for designing AI-agent workflows that exports Claude Code agents and commands, GitHub Copilot prompts and skills, Codex skills, and similar formats for other agent hosts.

• Agent skills
• Workflow automation