Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.

🩺 Errors that are worth reading

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. A local Wispr Flow alternative. ⭐ helps a ton :) Windows & iOS waitlist open. Linux soon.

Find vulnerabilities, misconfigurations, secrets, SBOM in containers, Kubernetes, code repositories, clouds and more

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Find secrets with Gitleaks 🔑

Automated Penetration Testing Agentic Framework Powered by Large Language Models

LLM-powered PermissionRequest hook for coding agents (e.g. Claude Code)

Turn your Claude subscription into a browser test agent

A TUI sidebar to orchestrate VS Code windows and track Claude Code agents.

💅🏻 ⚒ A collection of awesome design systems

Your Neovim AI sidekick

Give agents an operating system as a library. Runs in your existing backend – no sandboxes, VMs, or SaaS. Powered by WebAssembly & V8 isolates.

Expect tests your agent's code in a real browser

Your personal intelligence agent. Watches the world from multiple data sources and pings you when something changes.

A CLI for Twitter/X — feed, bookmarks, and user timeline in terminal

The distributed app store for vibe-coded projects. Federated, AI-curated, fully static on GitHub Pages.

An AI Hedge Fund Team

Replace port numbers with stable, named local URLs. For humans and agents.

Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Anti…

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

🟣 : An Amazon Cognito Emulator for local development

Personal memory across agents

An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and interact with your apps, and to proxy xcodebuild to save token wastage - LLMs directly calling xcb have …

Autonomous AI development loop for Claude Code with intelligent exit detection

The open source coding agent.