Explore Projects

Sherlock is a CLI OSINT tool that searches for a given username across 400+ social media sites simultaneously using concurrent HTTP requests. It checks each site using one of three detection method...

People interested in OSINT, web scraping reliability challenges, and maintaining large data-driven site manifests — specifically the cat-and-mouse game of keeping detection heuristics accurate against WAFs, site redesigns, and anti-bot measures

OpenSpec is a CLI tool that generates and manages spec-driven development (SDD) artifacts — proposal.md, design.md, specs/, tasks.md — inside your project's openspec/ directory, then injects corres...

Great for people interested in formalizing AI-assisted development workflows — specifically the problem of AI coding assistants generating code that drifts from intent because requirements only exist in ephemeral chat history.

GSD is a meta-prompting and workflow orchestration system for AI coding assistants (Claude Code, Gemini CLI, OpenCode, Codex). It installs a set of slash commands, agent definitions, and Node.js ho...

people interested in prompt engineering and AI workflow orchestration — specifically building structured development pipelines that keep LLM agents on-task across long coding sessions with real state management

gstack is a collection of Claude Code slash-command 'skills' (Markdown prompt templates) plus a compiled headless browser CLI built on Playwright. The browser binary (browse) is a TypeScript/Bun CL...

building and extending opinionated AI-driven dev workflows on top of Claude Code, particularly the browser automation layer that connects headless Playwright to an LLM agent loop

rtk (Rust Token Killer) is a CLI proxy that intercepts shell commands run by LLM coding agents (primarily Claude Code) and compresses their output before it reaches the LLM context window. It does ...

Great for people interested in LLM context optimization, building tools that sit between shell environments and AI coding agents, or Rust systems programming involving process spawning, output parsing, and structured filtering pipelines.

CloudCLI (formerly Claude Code UI) is a web-based GUI that wraps multiple AI coding agents (Claude Code, Cursor CLI, OpenAI Codex, Gemini CLI) so you can interact with them from a browser or mobile...

Great for people interested in building browser-based interfaces for terminal-driven AI agents, or exploring how to wrap PTY sessions and streaming CLI output into a real-time web UI

Claude Squad is a terminal multiplexer for AI coding agents (Claude Code, Codex, Gemini, Aider) that runs each agent in an isolated tmux session backed by a git worktree, so multiple tasks can run ...

Great for people interested in building terminal UIs around AI agent orchestration, specifically the intersection of tmux session management, git worktree isolation, and multi-agent workflow automation

dev-browser is a CLI tool that lets AI agents (primarily Claude Code) control a web browser by executing sandboxed JavaScript scripts against a full Playwright API. It works by running a Node.js da...

building or extending AI-driven browser automation tools, especially those that need sandboxed script execution or want to give LLM agents safe web interaction without full host access

Context Mode is an MCP server that acts as a sandboxed execution and indexing layer between AI coding assistants (Claude Code, Gemini CLI, VS Code Copilot, etc.) and their context windows. It inter...

people interested in building protocol-level infrastructure for AI coding assistants — specifically context management, sandboxed code execution, and session continuity across LLM conversation compaction

InsForge is a self-hostable Backend-as-a-Service platform (similar to Supabase) that exposes PostgreSQL, auth, S3-compatible storage, edge functions (via Deno), and site deployment through both a R...

building AI-agent-friendly backend infrastructure and tooling, particularly for developers exploring how MCP servers can bridge AI coding agents to live backend systems like Postgres, auth, and storage

A clean-room Rust reimplementation of Anthropic's Claude Code CLI, reverse-engineered from a source map leak in the official npm package. The project includes behavioral specs derived from the Type...

Rust developers interested in building terminal AI coding agents — specifically the architecture of multi-turn agentic loops, TUI design with ratatui, MCP (Model Context Protocol) client integration, and permission/tool orchestration systems.

yamllint is a Python command-line linter for YAML files that checks both syntax validity and style/cosmetic issues (indentation, line length, trailing spaces, key duplicates, quoting style, etc.). ...

people interested in static analysis tooling, specifically building or extending rule-based linters that operate on structured text formats using token-stream traversal