Loading...
Boltbar is a native macOS chat bar for GPT and Claude that opens over any app with Option-Space. It also provides a Claude Code and Codex agent mode for working in selected project folders with configurable permissions.
Mudroom runs coding agents in an isolated Linux VM or Docker/Podman environment on a clone of a project, then shows their changes as a diff for selective review and application. It supports several coding agents and command-line workflows across macOS, Linux, and Windows.
Yardlet is a free, open-source native Mac app that runs coding-agent CLIs such as Codex and Claude Code side by side. It adds shared task management, cross-agent coordination, approvals, code review, browser automation, MCP connectors, and account-limit visibility while using the agents' existing sign-ins.
PulseDev is a macOS desktop tool that lets developers select elements on a running local website, describe UI changes, and send the contextual task to an existing coding agent. It shows the resulting source diff for review and requires approval before writing changes to project files.
VibeiDE is a desktop workspace that queues and orchestrates Codex, Claude Code, and OpenCode tasks across projects. It helps developers run agents in parallel, preserve sessions, and review completed work from one place.
AI Bridge is a macOS app for running Claude Code, Codex, Grok and OpenCode side by side in organized projects and workspaces. It helps developers and technical teams monitor agent state, review actions, and work with Kubernetes, databases and selected Slack channels from one interface.
tabsh is a local browser-based workspace for shells and command-line agents, organizing projects as status-based cards beside the rest of a developer's web tools. It supports configurable CLI providers, persistent shell sessions, and terminal or chat interfaces on macOS and Linux.
MiniMax M3.1 Flash is a language model for multi-step agents, coding, computer use, enterprise workflow automation, and cybersecurity. Developers can access it through the MiniMax API, M Plan, and MiniMax Code, with token-based pricing for input, output, and cached input.
Inyon is an open-source tool for watching, answering, and steering coding agents running in tmux on your own computers. Developers can use its Android app, or an optional self-hosted hub for browser access, to manage supported CLI agents remotely.
Ovren is an AI coding tool for making changes to existing products from natural-language requests. It plans and writes the code, opens a pull request for team review, and provides live previews for frontend changes.
Praex is an AI copartner for browser chat, terminal-based coding work, and desktop use. It helps individuals ask questions, work with code repositories, and continue agent sessions across supported devices.
ESP-Mosaico 是一款基于 ESP32-S31 的模块化 AIoT 与嵌入式开发板，结合设备端 Agent、触控界面和可扩展外设。它面向希望通过自然语言或 PC 端 AI 编程 Agent 构建、测试和部署实体设备应用的创作者与开发者。
Pairon is a shared AI coding workspace for teams using Claude Code, Codex, and OpenCode. It connects local computers and project folders so teammates can direct agents, review changes, and preserve project decisions together.
Step 5 Preview is StepFun’s flagship AI model for agentic software engineering, professional knowledge work, and finance-oriented tasks. It supports vision input and a 1M-token context window, and is available through StepFun products and API.
Helicon is a free, MIT-licensed desktop, web, and editor interface for the Muse Code CLI. It helps developers manage projects and sessions, review diffs and approvals, and inspect usage while using their existing muse login and Muse Code access.
tetriz-harness is an open-source developer tool that scans and improves the rules, skills, hooks, agents, and other configuration used by AI coding tools. It helps engineering teams review harness recommendations and distribute approved changes to selected developers or teams, including manually managed test/control rollouts.
BOSS Console is a desktop workspace for running always-on AI agents with browser, terminal, editor, notebook, and plugin access. It helps developers and teams connect agents, control their available tools, and inspect work locally or through supported web and shared-session services.
Parallax is Conifer’s tool for coordinating multiple AI coding agents and reviewing their work against the original task, not just the final diff. It helps developers run agents in parallel, verify findings with tests, and receive eligible fixes as pull requests.
Acyclic Labs runs software-development tasks across parallel coding agents in isolated sandboxes, then combines the results into a reviewable patch or pull request. It is aimed at teams handling large codebases or multiple agent sessions through the CLI, dashboard, or MCP.
Reason is an autonomous AI software engineer and cloud coding agent for teams that want to assign GitHub issues and receive tested, evidence-backed pull requests. It can investigate bugs, implement features, run validation, and support selected dashboard and reporting workflows.