Explore the directory

A day-by-day tutorial series covering Python from basic syntax through object-oriented programming, exception handling, multithreading and data analysis with NumPy and Pandas, in a structured, beginner-friendly path.

• Tutorials

A Dart-based data engine that combines relational tables with vector and unstructured data, offering ACID transactions, joins, aggregations and hybrid vector retrieval for mobile, desktop, server and edge deployments.

• Databases

A Linux file picker, file searcher and image viewer that works with any desktop environment through an xdg-desktop-portal backend, adding thumbnail browsing, semantic image search and configurable per-file commands.

• Desktop utilities

A privacy-first browser extension that adds a sidepanel chat workspace for local and remote language models, including Ollama, LM Studio and llama.cpp, with local retrieval-augmented generation and browser-context tools.

• RAG
• Inference

A Rust-based terminal and web control plane that runs Codex, Claude Code, Muse Code, Kimi Code and Grok Build sessions side by side, on a laptop, in a container, over SSH or on EC2, and keeps them running after the terminal closes.

• Coding agents

An MCP server that connects Claude Code to the BountyLens bug-bounty hunt tracker, pushing findings, leads, tested endpoints and report drafts from the terminal to a web dashboard in real time.

• MCP servers
• Security

A set of educational Jupyter notebooks that teach the core patterns behind tools like Claude Code and Cursor's agent mode by having the learner build an agentic harness, a small language model and an MCP server from first principles.

• Tutorials

An MCP toolset that lets an AI agent operate Kali Linux penetration-testing tools, such as Nmap, sqlmap, Metasploit, Aircrack-ng and John the Ripper, through natural-language requests.

• MCP servers
• Security

A serving runtime that takes an existing file-defined agent directory and runs it as a live service, embedded in a web app, deployed as a Telegram, Slack or Feishu bot, or exposed as an API endpoint.

• Agent frameworks
• Backend

An open-source Python library that parses Excel workbooks into citation-ready, token-counted JSON chunks for language models, retrieval-augmented-generation pipelines and AI agent frameworks, preserving cells, formulas, merged regions, tables and charts.

• RAG

A multi-agent orchestration and communication layer built on the Beads task tracker, with a live dashboard, a command-line orchestrator host, and a built-in runtime that can spawn and manage agent workers directly.

• Agent frameworks

A distributed hyperparameter-optimization framework for tuning a vLLM language-model serving deployment, using Ray for distributed execution and Optuna for the search.

• Inference

A benchmark for evaluating whether an AI agent or memory system can answer personal, evidence-grounded questions about roughly four years of a person's own multimodal history, including images, videos and emails.

• Agent memory
• AI evals

A multi-agent framework written in Go that follows the design of the Python Agno project, providing agents, teams and workflows with multi-provider model support and an HTTP server for running them as a service.

• Agent frameworks

The official monorepo of client libraries, a command-line tool and MCP servers for the Sendmux email API, covering sending, mailbox and account-management endpoints across TypeScript, Python, Go, PHP, Rust and Ruby.

• MCP servers
• APIs

An open-source, local-first personal AI agent whose identity, memory and workspace stay under the user's control, usable with GPT, Claude, Gemini, DeepSeek or local models without losing continuity when switching between them.

• Agent frameworks

An automated machine-learning engineering stack in which large-language-model agents take a problem description, produce a plan, generate and run code locally, and iteratively refine a solution, aimed today at Kaggle-style competitions.

• Agent frameworks

An independent, open-source terminal coding-agent harness built specifically around the Motif-3 language model's measured behavior, rather than a general harness pointed at a different API endpoint.

• Coding agents

A semantic search tool for text columns in spreadsheets, letting journalists, researchers and anyone working with survey responses or similar data search a CSV by meaning instead of exact keywords.

• RAG
• Data engineering

A Model Context Protocol server that connects AI assistants to the Miro whiteboard platform, letting them read and manage boards, cards, connectors and other items through a standardized interface.

• MCP servers
• Design tools

A Model Context Protocol client that connects Claude, Cursor, Codex and other MCP-compatible AI tools to AutoMem, a graph-and-vector memory service that keeps decisions and context available across separate conversations and devices.

• MCP servers
• Agent memory

A single-binary command-line tool that turns any Model Context Protocol server's tools into ordinary terminal commands, without writing wrapper code or installing a software development kit.

• MCP servers
• CLI tools

An autonomous software-factory agent orchestrator that polls GitHub or Linear for candidate tickets and dispatches parallel coding-agent sessions to work them from backlog through pull-request creation, review and merge.

• Coding agents
• CI/CD

An AI debugger and verification toolkit for local browser development that streams console logs, network failures, exceptions and recordings from a browser extension into any Model Context Protocol-compatible coding assistant.

• MCP servers
• Debugging