Loading...
BentoBox is a kernel-level sandbox for coding agents and commands, designed to isolate execution with deny-by-default compartments on Linux and macOS. It helps developers run builds, tests, and agent-driven workflows while keeping sensitive files and other ungranted access paths blocked.
Murmell is a browser-based canvas for running multiple AI coding agents in one shared project directory. It is designed for live collaboration, with file reservations that help prevent agents from overwriting one another.
AgentSky is a managed agent service for launching long-running AI agents in the cloud with one click. It supports multiple harnesses, persistent history, managed recovery, and access through chat channels, CLI, and API.
Termexo is a Windows desktop workspace for running and monitoring Claude Code, Codex CLI, and shell sessions in one project-based window. It helps developers track agent status, resume prior sessions, arrange terminals, and switch Claude Code model profiles locally without an account.
Tempest is a local-first desktop app for running AI coding agents in parallel on isolated git worktrees and branches. It helps developers coordinate tools like Claude Code, Aider, and OpenCode from one interface without requiring an account.
Exmergo Dex is an open-source, agent-native analytics engineering toolkit for exploring data warehouses, authoring dbt and semantic models, and maintaining them when schemas drift. It is designed to run through coding agents such as Claude Code rather than as a separate analytics UI.
Terminal Candy is a native macOS terminal app that lets you run a real shell inside custom visual skins. It supports community skins, custom skin creation from images, and a one-time license after a free trial.
Mubert AI Music API is a developer-facing service for generating royalty-free music for apps, AI agents, streams, and content platforms. It supports text-to-music, image-to-music, realtime streaming, and library-based workflows.
MiniMax is an AI platform for multimodal models, developer APIs, and AI-native products. Its highlighted model, MiniMax M3, focuses on coding, agentic workflows, and long-context multimodal tasks.
SKI is a desktop app for Mac and Windows that lets developers talk to AI coding agents and hear responses aloud. It keeps the main voice loop local and offline, with optional meeting transcription and agent-assisted call features.
Tablo is a tiny floating desktop widget that monitors Claude Code and OpenAI Codex sessions from a corner of your screen. It shows live context usage, approval prompts, and session status so you can keep track of agent work without opening each session.
Memmy is a local-first AI agent that helps people who use multiple AI tools keep shared long-term context on their own device. It scans authorized local conversation history, organizes it into memory, and can pass that context between tools.
Tastemaker is a workflow skill for coding agents that helps them turn brief-driven UI work into a consistent visual system with files, assets, contrast checks, and local project memory. It is aimed at developers using agents such as Claude Code, Windsurf, and Gemini CLI.
ClariLayer is a context layer for AI data agents that connects to Claude Code, Cursor, Codex, or claude.ai. It keeps data definitions durable across sessions and reconciles them against source evidence instead of leaving them as unverified notes.
Medley is a Claude Code plugin that turns prompts into coordinated multi-agent missions. It helps people using Claude Code structure and monitor research, outreach, ops, and other multi-step work.
Task Monki is a macOS desktop app for managing coding-agent tasks from request to pull request. It combines agent runs, local previews, independent reviews, and draft pull request publishing in one task view.
BlackFlare is a macOS menu bar app for Claude Code and Codex that keeps the Mac awake during long runs, sends finish or attention alerts, and shows usage. It also lets users switch defaults and route notifications to Mac, Telegram, or Slack.
MemoryCustodian is a repo-native memory system for coding agents. It stores decisions, constraints, and rejected ideas in plain Markdown so agents can load just the context needed for the current task.
Prelint reviews pull requests against product specifications to catch drift, inconsistencies, and misalignment before changes ship. It uses repo-based specs and prepaid, usage-based billing with $10 in free credits to start.
qsa.sh runs an external security scan of the public IP your request comes from, using terminal-streamed results and no local installation. It helps people inspect their own exposed ports and vulnerability signals from the internet-facing side.