Open source. Open possibilities.

HermesMade provides six CLI tools addressing common AI user pain points: censorship risk analysis, model quality monitoring, API cost optimization, local LLM deployment, code inspection, and task cost estimation.

Self-hosted web toolkit with client-side processing for images, PDFs, text, math, and data tools. Lightweight Docker image, no tracking, open-source under MIT.

JSON Hero is an open-source web-based JSON explorer that lets you browse, search, and navigate JSON files through multiple view modes with content previews and related value scanning.

Reel generates always-current demo films for web apps and CLIs from a YAML spec. It drives a real browser or terminal, records the actual flow, and renders GIF, MP4, WebM, storyboards, and interactive HTML compositions. Works via CLI, Studio UI, or Claude Code plugin. Fails CI when demos break.

A local-first web UI for running Claude Code and Codex sessions in browser tabs with real PTY terminals, persistent history, and agent coordination via MCP. Sessions run in tmux for durability, with token-authenticated localhost security.

webpack-dashboard is a CLI dashboard for webpack dev server. It replaces noisy build output with a terminal UI showing build progress, asset sizes, errors, and warnings. Install as a dev dependency, add the DashboardPlugin to webpack config, and wrap your dev command with webpack-dashboard.

SurrealDB is a multi-model database built in Rust, unifying document, graph, relational, time-series, geospatial, and key-value data with real-time and vector search capabilities.

Orca is an open-source desktop app for orchestrating AI coding agents like Claude Code, Codex, and OpenCode side-by-side, each in its own git worktree. It includes a mobile companion, terminal splits, design mode, GitHub/Linear integration, SSH worktrees, and an Orca CLI.

WebdriverIO is a next-gen browser and mobile automation test framework for Node.js, supporting WebDriver, WebDriver BiDi, and Appium protocols for end-to-end, unit, and component testing.

Herdr is a terminal runtime that keeps coding agents running in the background across local and remote machines, with agent-driven control via CLI and socket API.

E2B is an open-source infrastructure for running AI-generated code within secure, isolated cloud sandboxes.

A tool to apply changes across multiple repositories simultaneously by running scripts or programs in their context.

A Claude Code plugin that equips a solo developer with an AI agile team: 13 specialist agents, 30 slash commands, QA-gated multi-agent code review, sprint ceremonies and persistent project memory.

Vtx is a minimalist coding agent harness featuring a Textual TUI and headless CLI. It offers a lean ~2,600-token system prompt, supports 50+ LLM providers, and includes modular skills, session trees, and safe permission controls.

A local-first AI agent debugger that reveals why an agent behaves a certain way. It combines visual replay, behavior diff comparisons between good and bad runs, and full visibility into prompts, context, memory, retrieval, and tool calls. Designed for AI agent development with LangChain support, running entirely locally with SQLite storage.

MCP server that lets AI coding agents inspect and control a live Chrome browser via Chrome DevTools, supporting performance traces, network inspection, screenshots, console logs, and Puppeteer-based automation.