Agent Desktop

Agent Deck is an open-source terminal UI and desktop application for running, orchestrating and monitoring multiple AI coding agents in parallel. A background daemon runs the agents independently of either client, allowing the terminal UI and desktop app to show the same sessions; the desktop app can display agents from multiple local or remote daemons, while the terminal UI attaches to one daemon and supports remote hosts over SSH. It can start individual agents, scheduled tasks, dispatcher jobs in isolated repository copies, or multi-role orchestrations in which an orchestrator delegates work to roles such as coders, reviewers and release agents. Each agent is displayed with its live status, current tool, directory and last prompt. The system supports Claude Code, Pi, OpenCode, Codex and Devin, while adapters for Gemini CLI and Aider are described as planned rather than shipped. The terminal client runs on macOS and Linux and through WSL on Windows. The native desktop app is alpha software for macOS on Apple Silicon and Linux amd64; it connects to an existing daemon and does not start its own. Agents continue running when the terminal UI is detached or the desktop app is closed.

Agent S is an open-source computer-use agent framework from Simular. It accepts natural-language tasks, observes a real desktop through screen and accessibility signals, and operates ordinary applications by clicking, typing, scrolling, and executing optional local code rather than relying on per-application APIs or scripts. The project has progressed through three generations: accessibility-tree grounding with an LLM, a vision-based manager-worker architecture using multiple foundation models, and Agent S3, which scales computer-use attempts through parallel rollouts and selection. Its workflow can combine model-driven exploration with reusable automation code, replay saved skills, and recover when the interface changes. The framework supports macOS, Windows, and Linux, works with models from OpenAI, Anthropic, Gemini, OpenRouter, vLLM, and open-weight providers, and is distributed through the `gui-agents` Python package. An optional local coding environment can execute Python and Bash with the current user's permissions, so the repository warns that this capability should be used only in trusted environments.

agent-browser is a native Rust browser-automation CLI for AI agents, developed by Vercel Labs. It lets agents open pages, read accessibility-tree snapshots containing element references such as @e1, and interact with those references through shell commands including click, fill, press, and scroll. The browser remains open between commands so an agent can repeat a snapshot-act-check loop, while a background daemon controls the browser through the Chrome DevTools Protocol and maintains separate sessions and browser state. It supports Chrome for Testing by default, CDP connections to existing browsers, alternative engines, iOS Simulator Mobile Safari, cloud browser providers, an MCP server, agent skills, screenshots, PDFs, recordings, downloads, network and storage controls, and debugging tools. It is distributed through npm, Homebrew, npx, and native binaries for macOS, Linux, and Windows, and is licensed under Apache-2.0.

Agency Agents is a collection of specialized AI-agent instruction files and a native desktop app for macOS, Linux, and Windows. Its agents define domain-specific identities, workflows, rules, deliverables, code examples, and success metrics across engineering, design, marketing, sales, testing, security, finance, game development, GIS, healthcare, and other divisions. The repository provides scripts that convert and install the agents into tools including Claude Code, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Aider, Windsurf, Qwen Code, Kimi Code, Codex, Osaurus, and others; the app browses the roster, installs selected agents, and keeps them updated. The repository is distributed under the MIT License.

PI-Desktop is a local-first desktop workspace for AI coding agents, built with Electron, a Rust host core, and the pi Agent Harness. It lets users open local projects, connect cloud or local models through providers such as OpenAI-compatible APIs, manage projects and long-running sessions, and review file changes and command output. Its architecture separates the React renderer, Electron desktop orchestration, Rust-managed permissions, filesystem access, SQLite persistence and secrets, and a pi Agent sidecar responsible for the agent loop, model interaction, and streaming. Agent, Plan, and Goal modes provide different approval boundaries; agents can read and edit files, run commands, and delegate exploration, implementation, research, testing, or review to background Subagents. The workspace supports MCP servers, Skills, installable Plugins, model and provider switching, session imports, notifications, context checkpoints, and a plugin marketplace. Conversations are stored locally as JSONL with a SQLite index, settings and logs remain on the machine, credentials use the operating-system keychain, and model requests go directly to the configured provider or endpoint. Plugin processes are permission-gated and isolated from the renderer, but plugins remain user-trusted code rather than a complete operating-system sandbox. It is an early-preview cross-platform application distributed for macOS, Windows, and Linux under the GNU Lesser General Public License v3.0.