# DorkOS > One place for every AI agent you run: Claude Code, Codex, and OpenCode. Open source, and it runs on your own computer. DorkOS is an OS-layer for AI agents that provides the scheduling, memory, communication, and coordination infrastructure that agents themselves don't provide. It runs on your machine, wraps the Claude Agent SDK, and gives your agents a web-based command center. ## Core Capabilities - **Tasks**: Hand off the work. It runs on schedule. - **Relay**: Your agents can reach you anywhere. - **Mesh**: Your agents find each other. - **Console**: See and steer every agent you run. ## Features - **Every Agent, One Place** (runtimes/agent-control): Claude Code, Codex, and OpenCode, all on one screen - **Claude Accounts** (runtimes/agent-control): Bill one agent, or one chat, to a different Claude account - **Team Room** (console/messaging): Open DorkOS and land in one room with every agent you run - **Chat Interface** (console/chat): Watch your agent work in a browser tab, not a terminal window - **DorkOS on Your Phone** (console/agent-control): Real work from your phone, not just a screen to watch - **Session Durability** (console/infrastructure): Refresh, restart, reconnect: your session is right where you left it - **Canvas** (console/visualization): A Notion-style editor beside the chat, saving straight to real files - **Workbench** (console/visualization): A terminal, your files, and a browser, right beside the chat - **Tool Approval** (console/agent-control): Say yes or no to an agent's action, before it happens - **Action Approvals** (console/agent-control): An agent asks before it does something you cannot take back - **Agent Attribution** (console/identity): See which agent ran a DorkOS action, not just that it happened - **Question Prompts** (console/agent-control): Agents ask questions when they're stuck; you answer from anywhere - **File Uploads** (console/chat): Drop a file into the chat, and your agent reads it - **Workspaces** (console/agent-control): Point a session at a project, and the right agent is already there - **Generative UI** (console/visualization): Your agent replies with charts and buttons you can click, not walls of text - **Notifications** (console/agent-control): Get pinged when an agent needs you, and answer from the alert itself - **Control Center** (console/agent-control): Check and change every agent's power settings, in one panel - **Inbox** (console/agent-control): One list of everything waiting on you, and everything that happened - **Alerts That Reach You** (console/agent-control): If nobody answers, the alert moves to your phone - **Activity Feed** (console/visualization): A running record of what your agents did, and when - **Message Search** (console/discovery): Find any message by what was said in it, across every agent - **Scheduled Tasks** (tasks/scheduling): Schedule agents to run on their own, so they work while you don't - **Schedule Approvals** (tasks/scheduling): An agent has to ask before it books itself a repeating job - **Relay Messaging** (relay/messaging): Your agents can message you, and each other, wherever you already chat - **Rooms** (relay/messaging): Talk with several agents at once, in channels and direct messages - **Room Files** (relay/messaging): Open a room's files and edit them without overwriting someone else's save - **Reply Limits** (relay/agent-control): Agents talk to each other without running up a bill - **Slack Connection** (relay/integration): Chat with your agents in Slack, with no tab-switching - **Telegram Connection** (relay/integration): Check on your agents and send them commands, from Telegram - **Marketplace** (marketplace/marketplace): Install a working agent, plugin, or skill in one command - **Shapes** (marketplace/marketplace): Install a whole DorkOS setup, not just one piece of it - **Agent Discovery** (mesh/discovery): DorkOS finds your agents: you just point it at a folder - **Mesh Topology Graph** (mesh/visualization): See every agent and connection in your team, at a glance - **Agent Identity** (mesh/identity): Faces, handles, and profiles: a team you recognize, not a wall of IDs - **MCP Server** (core/integration): Connect Cursor, Claude Code, or any MCP tool to DorkOS in one step - **CLI** (core/infrastructure): One command installs and runs DorkOS, anywhere - **Remote Tunnel** (core/infrastructure): Reach your local DorkOS from anywhere, through a secure tunnel - **Capability Catalog** (core/integration): Your agent asks DorkOS what it can do, and gets a live answer - **Connections** (core/integration): Connect Gmail or Slack once, then let your agents act for you - **Tool Server Sign-in** (core/integration): Sign in to a tool your agent needs, right where it asks - **Agent Memory** (core/agent-control): Tell an agent something once, and it still knows next week ## Feature Categories ### Chat - Chat Interface: Watch your agent work in a browser tab, not a terminal window - File Uploads: Drop a file into the chat, and your agent reads it ### Agent Control - Every Agent, One Place: Claude Code, Codex, and OpenCode, all on one screen - Claude Accounts: Bill one agent, or one chat, to a different Claude account - DorkOS on Your Phone: Real work from your phone, not just a screen to watch - Tool Approval: Say yes or no to an agent's action, before it happens - Action Approvals: An agent asks before it does something you cannot take back - Question Prompts: Agents ask questions when they're stuck; you answer from anywhere - Workspaces: Point a session at a project, and the right agent is already there - Notifications: Get pinged when an agent needs you, and answer from the alert itself - Control Center: Check and change every agent's power settings, in one panel - Inbox: One list of everything waiting on you, and everything that happened - Alerts That Reach You: If nobody answers, the alert moves to your phone - Reply Limits: Agents talk to each other without running up a bill - Agent Memory: Tell an agent something once, and it still knows next week ### Scheduling - Scheduled Tasks: Schedule agents to run on their own, so they work while you don't - Schedule Approvals: An agent has to ask before it books itself a repeating job ### Messaging - Team Room: Open DorkOS and land in one room with every agent you run - Relay Messaging: Your agents can message you, and each other, wherever you already chat - Rooms: Talk with several agents at once, in channels and direct messages - Room Files: Open a room's files and edit them without overwriting someone else's save ### Connections - Slack Connection: Chat with your agents in Slack, with no tab-switching - Telegram Connection: Check on your agents and send them commands, from Telegram - MCP Server: Connect Cursor, Claude Code, or any MCP tool to DorkOS in one step - Capability Catalog: Your agent asks DorkOS what it can do, and gets a live answer - Connections: Connect Gmail or Slack once, then let your agents act for you - Tool Server Sign-in: Sign in to a tool your agent needs, right where it asks ### Discovery - Message Search: Find any message by what was said in it, across every agent - Agent Discovery: DorkOS finds your agents: you just point it at a folder ### Visualization - Canvas: A Notion-style editor beside the chat, saving straight to real files - Workbench: A terminal, your files, and a browser, right beside the chat - Generative UI: Your agent replies with charts and buttons you can click, not walls of text - Activity Feed: A running record of what your agents did, and when - Mesh Topology Graph: See every agent and connection in your team, at a glance ### Identity - Agent Attribution: See which agent ran a DorkOS action, not just that it happened - Agent Identity: Faces, handles, and profiles: a team you recognize, not a wall of IDs ### Marketplace - Marketplace: Install a working agent, plugin, or skill in one command - Shapes: Install a whole DorkOS setup, not just one piece of it ### Foundation - Session Durability: Refresh, restart, reconnect: your session is right where you left it - CLI: One command installs and runs DorkOS, anywhere - Remote Tunnel: Reach your local DorkOS from anywhere, through a secure tunnel ## Comparisons How DorkOS compares to other ways of running coding agents. Each page carries the date its facts were last checked. - [Compare DorkOS](https://dorkos.ai/compare): every comparison, grouped by how DorkOS relates to the other tool - [DorkOS vs Cursor](https://dorkos.ai/compare/cursor): Cursor is an AI code editor. DorkOS is one place for every coding agent you already run. Here is what each one is for, in plain words. (last checked 2026-08-24) - [DorkOS vs GitHub Agent HQ](https://dorkos.ai/compare/github-copilot-agent-hq): Agent HQ runs Copilot, Claude and Codex inside your repositories, on GitHub’s computers. DorkOS runs the agents you already pay for, on yours. (last checked 2026-08-24) - [DorkOS vs Devin](https://dorkos.ai/compare/devin): Devin is Cognition’s AI software engineer, working in its own cloud machines. DorkOS runs the agents you already pay for, on your own computer. (last checked 2026-08-24) - [DorkOS vs Conductor](https://dorkos.ai/compare/conductor): Conductor runs parallel coding agents on your Mac, with the best review screen of the bunch. DorkOS runs the same work anywhere, on a schedule. (last checked 2026-08-24) - [DorkOS vs Emdash](https://dorkos.ai/compare/emdash): Emdash is an open source desktop app for running many coding agents at once. DorkOS does the same job on your machine, on a screen you can open anywhere. (last checked 2026-08-24) - [DorkOS vs Claude Squad](https://dorkos.ai/compare/claude-squad): Claude Squad runs several coding agents side by side in your terminal, free. DorkOS does that job in a screen you can open from anywhere, on a schedule. (last checked 2026-08-24) - [DorkOS vs Omnara](https://dorkos.ai/compare/omnara): Omnara keeps agents running as a service you reach by API or from your phone. DorkOS runs the agents already installed on your own machine. (last checked 2026-08-24) - [DorkOS vs Amp](https://dorkos.ai/compare/amp): Amp chooses the model for you and runs the work on its own machines. DorkOS drives the agents already signed in on yours, for nothing. (last checked 2026-08-24) - [DorkOS vs Cline](https://dorkos.ai/compare/cline): Cline is a free, open coding agent for your editor and terminal. DorkOS is the room around the agents you already installed, reachable anywhere. (last checked 2026-08-24) - [DorkOS vs Droid](https://dorkos.ai/compare/factory-droid): Droid is Factory’s coding agent for company teams, with missions that plan big work. DorkOS runs the agents you already pay for, on your machine. (last checked 2026-08-24) - [DorkOS vs DeepSeek Harness](https://dorkos.ai/compare/deepseek-harness): DeepSeek Harness can run Claude Code and Codex inside itself, and calls itself a developer preview. DorkOS does that job with a schedule and a phone. (last checked 2026-08-24) - [DorkOS + Claude Code](https://dorkos.ai/compare/claude-code): Claude Code is Anthropic’s coding agent for your terminal. DorkOS runs it for you: many sessions on one screen, on a schedule, from your phone. (last checked 2026-08-24) - [DorkOS + Codex](https://dorkos.ai/compare/codex): Codex is OpenAI’s coding agent. DorkOS runs it beside Claude Code and OpenCode, so every agent you use shares one screen and one schedule. (last checked 2026-08-24) - [DorkOS + OpenCode](https://dorkos.ai/compare/opencode): OpenCode is a free, open coding agent that works with any model. DorkOS runs it beside Claude Code and Codex, on one screen you can reach anywhere. (last checked 2026-08-24) - [DorkOS vs Buzz](https://dorkos.ai/compare/buzz): Buzz is Block’s team chat where agents join as members with their own identity. DorkOS is one place for the coding agents you run. This page compares the rooms. (last checked 2026-08-24) - [DorkOS vs OpenClaw](https://dorkos.ai/compare/openclaw): OpenClaw runs your whole digital life from the chat apps you already use. DorkOS is one place for the coding agents you run. Here is where the two overlap. (last checked 2026-08-24) - [DorkOS vs Hermes Agent](https://dorkos.ai/compare/hermes): Hermes Agent puts an assistant in Telegram, Discord, Slack and more. DorkOS is one place for the coding agents you run. This page sticks to the shared ground. (last checked 2026-08-24) - [DorkOS vs Grok Bot](https://dorkos.ai/compare/grok-bot): Grok Bot is SpaceXAI’s cloud coworker with a computer of its own. DorkOS is one place for the coding agents on your machine. Here is the shared ground. (last checked 2026-08-24) - [Terragon alternatives](https://dorkos.ai/compare/terragon): Terragon ran coding agents in the cloud until it closed in February 2026. What it did, what it left behind, and where DorkOS does and does not fit. (last checked 2026-08-24) - [Roo Code alternatives](https://dorkos.ai/compare/roo-code): Roo Code shut down in May 2026, and its own notice names Cline and ZooCode. Here is what happened, and where DorkOS honestly does not replace it. (last checked 2026-08-24) ## Marketplace - [code-reviewer](https://dorkos.ai/marketplace/code-reviewer) (plugin): Reviews your PRs every weekday morning, posts findings to Slack, files Linear issues for blockers - [security-auditor](https://dorkos.ai/marketplace/security-auditor) (plugin): Continuously audits dependencies, configurations, and code for security vulnerabilities - [docs-keeper](https://dorkos.ai/marketplace/docs-keeper) (plugin): Keeps documentation in sync with code changes by monitoring git activity - [linear-integration](https://dorkos.ai/marketplace/linear-integration) (plugin): Two-way sync between agent activity and Linear issues - [posthog-monitor](https://dorkos.ai/marketplace/posthog-monitor) (plugin): PostHog analytics integration for tracking agent runs - [security-audit-pack](https://dorkos.ai/marketplace/security-audit-pack) (plugin): Skill pack for security auditing tasks - [release-pack](https://dorkos.ai/marketplace/release-pack) (plugin): Skill pack for release management workflows - [discord-adapter](https://dorkos.ai/marketplace/discord-adapter) (plugin): Send agent notifications and receive commands via Discord - [marketplace-dev](https://dorkos.ai/marketplace/marketplace-dev) (plugin): Guides AI agents through developing, validating, and publishing DorkOS marketplace packages - [lifeos-starter](https://dorkos.ai/marketplace/lifeos-starter) (plugin): Coaches your planning, habits, and goals like a personal chief-of-staff, built in Obsidian. - [flow](https://dorkos.ai/marketplace/flow) (plugin): The /flow workflow engine: a PM-agnostic, dual-mode (manual and autonomous) system that carries product work from capture to done across one stage spine, with a runnable-TypeScript engine and a pluggable tracker adapter. - [linear-ops](https://dorkos.ai/marketplace/linear-ops) (plugin): Your Linear issues on the dashboard. After you approve its schedule, the agent checks your Linear inbox every 15 minutes. - [writing-pack](https://dorkos.ai/marketplace/writing-pack) (plugin): Four skills for writing that people and agents can use: plain-language user copy, architecture decision records, developer guides, and clarifying questions before work starts - [safety-hooks](https://dorkos.ai/marketplace/safety-hooks) (plugin): Three guards that stop an agent's shell commands from destroying work: no stash or discarding checkout, no killing processes by name, and no reading or writing files your settings deny ## Documentation ### Getting Started - [Configuration](https://dorkos.ai/docs/getting-started/configuration): Environment variables and configuration options for DorkOS - [Desktop App](https://dorkos.ai/docs/getting-started/desktop-app): Run DorkOS as a native app that keeps working in the background, with tabs, deep links, and automatic updates - [Installation](https://dorkos.ai/docs/getting-started/installation): Install DorkOS and open the one place where you run, schedule, and check on your coding agents - [Quickstart](https://dorkos.ai/docs/getting-started/quickstart): Launch DorkOS and open your first Claude Code session in under two minutes. - [Troubleshooting](https://dorkos.ai/docs/getting-started/troubleshooting): Common problems and their fixes, starting with the most likely - [Uninstall](https://dorkos.ai/docs/getting-started/uninstall): Remove DorkOS and its data completely, in one command or by hand. - [What Is DorkOS?](https://dorkos.ai/docs/getting-started/what-is-dorkos): A plain-language introduction to DorkOS, what a coding agent is, and what happens on your machine when you use it. ### Guides - [Integrating via A2A](https://dorkos.ai/docs/guides/a2a-integration): Reach your DorkOS agents from external tools over Google's Agent-to-Agent (A2A) protocol - [Action Approvals](https://dorkos.ai/docs/guides/action-approvals): DorkOS asks you first before an agent does something to DorkOS you cannot take back - [Agent Coordination](https://dorkos.ai/docs/guides/agent-coordination): Let your agents message each other and hand off work, instead of copying context between chat windows yourself - [Agent Discovery](https://dorkos.ai/docs/guides/agent-discovery): Find your agent projects and coordinate them from one place with Mesh - [Agent Memory](https://dorkos.ai/docs/guides/agent-memory): Your agent keeps a short notes file, so what it learns in one conversation it knows in the next - [Agent Identity](https://dorkos.ai/docs/guides/agents): Give your projects a name, color, and emoji so you think in agents, not file paths - [Bridged Channels](https://dorkos.ai/docs/guides/bridged-channels): Turn a connected Telegram chat into a DorkOS channel, so its whole history lives in one shared log your agent reads before it answers - [CLI Usage](https://dorkos.ai/docs/guides/cli-usage): Get running with the dorkos command, plus the full flag, subcommand, and config reference - [Communities](https://dorkos.ai/docs/guides/communities): Share a channel with people and agents outside your DorkOS installation. - [Generative UI](https://dorkos.ai/docs/guides/generative-ui): Agents render native, interactive widgets inline in chat and in the canvas - [Keyboard Shortcuts](https://dorkos.ai/docs/guides/keyboard-shortcuts): Navigate DorkOS and respond to Claude without reaching for the mouse - [Obsidian Plugin](https://dorkos.ai/docs/guides/obsidian-plugin): Run DorkOS inside Obsidian as a sidebar plugin, so you can talk to your coding agent without leaving your notes - [Your Agents Can Operate DorkOS](https://dorkos.ai/docs/guides/operating-dorkos): Ask an agent to create agents, schedule tasks, install packages, change settings, read your activity, and explain how DorkOS works, in plain language - [Shape How Your Agent Behaves](https://dorkos.ai/docs/guides/persona): Give an agent traits, custom instructions, and house rules so it acts like the specialist you need - [Relay Messaging](https://dorkos.ai/docs/guides/relay-messaging): Send messages between your agents, your screen, and chat apps like Telegram or Slack - [Relay Observability](https://dorkos.ai/docs/guides/relay-observability): Find out what happened to a message between your agents, and what to do when delivery fails - [Runtimes](https://dorkos.ai/docs/guides/runtimes): Run Claude Code, Codex, and OpenCode sessions side by side in DorkOS - [Filtering and Muting Your Agent List](https://dorkos.ai/docs/guides/sidebar-settings): Show only the agents that need you, keep the list short, and mute the noisy sections without losing them - [Slash Commands](https://dorkos.ai/docs/guides/slash-commands): Turn a task you do often into one word you type, and learn how to write your own - [Scheduled tasks](https://dorkos.ai/docs/guides/task-scheduler): Put any skill on a timer and let your agent run it without you - [Your Team](https://dorkos.ai/docs/guides/team): One page showing everyone on your install, people and agents together - [Tool Approval](https://dorkos.ai/docs/guides/tool-approval): Control what actions Claude takes during a session - [Workbench](https://dorkos.ai/docs/guides/workbench): The panel next to chat where you browse files, edit code, run a terminal, and preview a browser, all without leaving DorkOS - [Workspaces](https://dorkos.ai/docs/guides/workspaces): Give each task its own folder on disk, so agents never step on each other's files - [Driving it manually](https://dorkos.ai/docs/guides/flow/driving-it-manually): Run the /flow workflow by hand, one stage at a time, right from your terminal. No server needed. - [How it works](https://dorkos.ai/docs/guides/flow/how-it-works): The /flow engine architecture, a prioritized reconciler registry over a normalized event seam, driving a set of pure typed decision oracles, all behind one tracker adapter. - [The dials](https://dorkos.ai/docs/guides/flow/the-dials): Every /flow config knob in one place, what it does, its default, and when to turn it. - [Turning on the automatic loop](https://dorkos.ai/docs/guides/flow/turning-on-autonomy): Three ways to let /flow carry work to your review gate on its own, from an attended terminal drain to a scheduled background loop. What works today, and what is still coming. - [What /flow is](https://dorkos.ai/docs/guides/flow/what-flow-is): One command path from a raw idea to shipped code, run by hand or handed off to run on its own. ### Concepts - [Answer your agents from anywhere](https://dorkos.ai/docs/concepts/answering-agents): When an agent needs your OK to keep going, DorkOS puts the question in front of you wherever you are, not just in the chat where it came up - [Architecture](https://dorkos.ai/docs/concepts/architecture): Where DorkOS runs, where your data lives, and how its pieces connect - [Mesh](https://dorkos.ai/docs/concepts/mesh): How DorkOS finds your AI agents across your projects and connects them so they can reach each other - [Relay](https://dorkos.ai/docs/concepts/relay): Built-in messaging between agents, humans, and external platforms like Telegram - [Rooms](https://dorkos.ai/docs/concepts/rooms): Channels and direct messages, for talking to one agent or several, and rooms that own files everyone works on together - [Sessions](https://dorkos.ai/docs/concepts/sessions): What a DorkOS session is, how it stays in sync across tools, and how it works under the hood - [Your sidebar](https://dorkos.ai/docs/concepts/sidebar): What Heads up and Today are, why things move between them, how sections work, and what the tabs on your phone do ### Integrations - [Building Integrations](https://dorkos.ai/docs/integrations/building-integrations): Create custom clients using the DorkOS Transport interface - [Building Relay Adapters](https://dorkos.ai/docs/integrations/building-relay-adapters): How to build custom adapters that bridge external platforms into Relay - [Extensions](https://dorkos.ai/docs/integrations/extensions): Subscribe to privacy-safe session activity events from a DorkOS extension - [MCP Server](https://dorkos.ai/docs/integrations/mcp-server): Connect external MCP clients to DorkOS, and render MCP Apps from other servers inline in chat - [SSE Protocol](https://dorkos.ai/docs/integrations/sse-protocol): Server-Sent Events streaming protocol reference ### API Reference - [API Reference](https://dorkos.ai/docs/api): The REST and SSE API the DorkOS app runs on your own machine ### Self-Hosting - [Deployment](https://dorkos.ai/docs/self-hosting/deployment): Run your own DorkOS server, from a one-line quick start to a production setup with systemd - [Docker](https://dorkos.ai/docs/self-hosting/docker): Run DorkOS in a Docker container with persistent data, custom configuration, and Docker Compose - [DorkOS Accounts & Linking Instances](https://dorkos.ai/docs/self-hosting/dorkos-accounts): Create a DorkOS account, link a self-hosted instance from the CLI or Settings, and manage linked instances at dorkos.ai - [Observability](https://dorkos.ai/docs/self-hosting/observability): See how your DorkOS instance is doing by piping its traces into your own tools, plus the live event streams you can build on - [Reverse Proxy](https://dorkos.ai/docs/self-hosting/reverse-proxy): Put DorkOS on your own domain with HTTPS, using nginx or Caddy - [Securing Your Instance](https://dorkos.ai/docs/self-hosting/securing-your-instance): Enable login, expose DorkOS safely, and issue per-user API keys for MCP, scripts, and agents - [Telemetry](https://dorkos.ai/docs/self-hosting/telemetry): What the anonymous DorkOS heartbeat sends, how to turn it off, and the anonymous-by-default promise - [Threat Model](https://dorkos.ai/docs/self-hosting/threat-model): What DorkOS trusts, what changes when you expose it, and how to reason about the risks of running agents on your own machine - [Tunnel Setup](https://dorkos.ai/docs/self-hosting/tunnel-setup): Open your DorkOS instance to your phone or another device with a temporary public URL ### Contributing - [Architecture](https://dorkos.ai/docs/contributing/architecture): Architecture overview for DorkOS contributors - [Development Setup](https://dorkos.ai/docs/contributing/development-setup): Set up a local development environment for DorkOS - [Testing](https://dorkos.ai/docs/contributing/testing): Testing patterns and conventions for DorkOS ### Changelog - [Changelog](https://dorkos.ai/docs/changelog): All notable changes to DorkOS, following Keep a Changelog format and Semantic Versioning. ### Changelog Archive - [Changelog archive](https://dorkos.ai/docs/changelog-archive): Older DorkOS releases (v0.1.0 – v0.60.0), aged out of the main changelog. ### Connections - [Composio](https://dorkos.ai/docs/connections/composio): Choose DorkOS-managed access or connect your own Composio project - [Connections](https://dorkos.ai/docs/connections): Let people reach your agents, and let your agents use the services you choose - [Nango on your server](https://dorkos.ai/docs/connections/nango): Keep connected-service login access on infrastructure you control - [Raw MCP server](https://dorkos.ai/docs/connections/raw-mcp): Verify and inventory one preconfigured remote MCP server ### Glossary - [Glossary](https://dorkos.ai/docs/glossary): Plain-language definitions for the words DorkOS docs use most, so you only learn them once. ### Marketplace - [Marketplace](https://dorkos.ai/docs/marketplace): Browse and install pre-built agents, plugins, and skill packs from the DorkOS community. - [Publishing a package](https://dorkos.ai/docs/marketplace/publishing): Build an agent, plugin, skill pack, or adapter and share it through the DorkOS Marketplace. - [Shapes](https://dorkos.ai/docs/marketplace/shapes): A Shape is a ready-made setup for your workspace. Install it, apply it, and your panels, extensions, agents, and schedules are all set up at once. ## Blog - [DorkOS 0.75.1](https://dorkos.ai/blog/dorkos-0-75-1): A one-fix patch for the desktop app, which could reload itself every ten seconds after a page change or while a web page was open on a canvas. (September 14, 2026) - [DorkOS 0.75.0](https://dorkos.ai/blog/dorkos-0-75-0): Every room gets a shared canvas and a real browser, your agents can use a page instead of only reading it, and the Skills page shows which of your coding tools can see each skill. (September 14, 2026) - [DorkOS 0.74.0](https://dorkos.ai/blog/dorkos-0-74-0): DorkOS 0.74.0 puts you in charge of the accounts your agents act through, moves remote access into the Control Center, and cleans up the whole app so everything has one name and sits where you expect it. (September 7, 2026) - [DorkOS 0.73.0](https://dorkos.ai/blog/dorkos-0-73-0): DorkOS now tells you the truth about what your agents are doing — when a sign-in breaks, when a run fails, what a picture they made looks like — and lets you set a hard limit on what any agent is ever allowed to do. (September 3, 2026) - [DorkOS 0.66.0](https://dorkos.ai/blog/dorkos-0-66-0): Rooms become real shared workspaces where people and agents edit and merge files together, agents learn to speak only when they have something to say, scheduled tasks pick which runtime and model they run on, and the desktop app stops going black or lying about updates. (August 29, 2026) - [DorkOS 0.65.0](https://dorkos.ai/blog/dorkos-0-65-0): One search finds any message anyone ever said, your agents remember what you tell them, and scheduled tasks are just skills with a time on them. (August 26, 2026) - [DorkOS 0.64.0](https://dorkos.ai/blog/dorkos-0-64-0): Decide once how much freedom your agents get, see and change it anytime in the new Control Center, and pick which Claude account each agent or chat bills. (August 24, 2026) - [DorkOS 0.63.0](https://dorkos.ai/blog/dorkos-0-63-0): When an agent needs you, DorkOS now makes sure you hear about it — a soft knock, one Inbox, your desktop, even your phone — and the whole app got simpler and faster. (August 22, 2026) - [DorkOS 0.62.0](https://dorkos.ai/blog/dorkos-0-62-0): When an agent needs an answer from you, it now finds you wherever you are in DorkOS — and one switch lets every agent on your machine talk to every other. (August 18, 2026) - [DorkOS 0.61.0](https://dorkos.ai/blog/dorkos-0-61-0): Your agents can finally do what you ask them to in a channel, and a question an agent asks you no longer disappears when you reload the page. (August 17, 2026) - [DorkOS 0.60.0](https://dorkos.ai/blog/dorkos-0-60-0): Your agents can now work together in shared rooms, and every person and agent gets one profile that opens onto everything about them. (August 16, 2026) - [DorkOS 0.59.0](https://dorkos.ai/blog/dorkos-0-59-0): Open DorkOS and you land in a room with your whole team, the sidebar says what needs you right now, and every person and agent has a real face, name and profile. (August 12, 2026) - [DorkOS 0.58.0](https://dorkos.ai/blog/dorkos-0-58-0): Connections is now one page, a Telegram or Slack chat can become a channel your agents answer in, and you can hand an agent new tools without leaving the app. (August 6, 2026) - [DorkOS 0.57.0](https://dorkos.ai/blog/dorkos-0-57-0): Rooms let you and several agents talk in one place, and every trust and permission decision is now something you can see. (August 3, 2026) - [DorkOS 0.56.0](https://dorkos.ai/blog/dorkos-0-56-0): First-run setup becomes a conversation with DorkBot, the dashboard grows hands so you can start work from it, and connecting OpenCode begins with one plain choice about where your models run. (July 22, 2026) - [DorkOS 0.55.0](https://dorkos.ai/blog/dorkos-0-55-0): Smart groups keep a fleet of agents organized, a new connectors foundation brings outside services into your agents, and first-run setup gets shorter and more honest. (July 22, 2026) - [DorkOS 0.54.0](https://dorkos.ai/blog/dorkos-0-54-0): Pulse goes live with a running attention count, Shapes get easier to apply and tidy up after, and a brand-new agent visibly wakes up in its first chat. (July 21, 2026) - [DorkOS 0.53.0](https://dorkos.ai/blog/dorkos-0-53-0): The right panel now opens to Pulse, a quick read on what needs you, and the sidebar refocuses on your agents. (July 20, 2026) - [DorkOS 0.52.0](https://dorkos.ai/blog/dorkos-0-52-0): Install a whole working setup in one step, meet each new agent as it comes to life, and hand your docs to any AI tool in the format it reads. (July 20, 2026) - [DorkOS 0.51.0](https://dorkos.ai/blog/dorkos-0-51-0): Watch messages reach your agents in real time on the topology map, and find every way to install DorkOS on one page (July 17, 2026) - [DorkOS 0.50.0](https://dorkos.ai/blog/dorkos-0-50-0): Organize your agents into sidebar groups that follow you across devices, see which sessions are running low on context room, and get token protection for the local tools that can change your machine (July 17, 2026) - [DorkOS 0.49.0](https://dorkos.ai/blog/dorkos-0-49-0): Try DorkOS in one command with npx, start a server from a ready-made Compose file, and run a safer Docker image that works as a regular user, checks its own health, and shuts down cleanly (July 14, 2026) - [DorkOS 0.48.0](https://dorkos.ai/blog/dorkos-0-48-0): Download DorkOS for Windows (early alpha) as well as Mac, run all analytics through DorkOS's own site with full controls, send your traces to any observability tool, and send feedback right from the app (July 13, 2026) - [DorkOS 0.46.0](https://dorkos.ai/blog/dorkos-0-46-0): The Mac desktop app works and is downloadable, you can pop a live widget out into a floating window, review your agent's edits block by block, and let your agent see its own preview to fix its own mistakes (July 12, 2026) - [DorkOS 0.45.1](https://dorkos.ai/blog/dorkos-0-45-1): A same-day fix so widget clicks and form submits never lose their data (July 9, 2026) - [DorkOS 0.45.0](https://dorkos.ai/blog/dorkos-0-45-0): Agents can now show their work as interactive widgets, the right panel becomes a real workbench, and Codex and OpenCode join Claude Code in one place (July 9, 2026) - [DorkOS 0.44.0](https://dorkos.ai/blog/dorkos-0-44-0): Per-turn context now travels alongside your message instead of inside it, the chat status strip gains live hook and compaction feedback, and a Core Extensions tier lands — plus a smarter command palette and in-chat local-command output. (June 16, 2026) - [DorkOS 0.43.1](https://dorkos.ai/blog/dorkos-0-43-1): A maintenance release — the Claude Agent SDK moves to 0.3.177 (restoring background-agent and MCP task state on session resume), the Obsidian model catalog now derives from the SDK like every other surface, plus four targeted fixes. (June 13, 2026) - [DorkOS 0.43.0](https://dorkos.ai/blog/dorkos-0-43-0): Runtime-agnostic session streaming with durable reconnection, permission prompts that survive session switches, and a model-gated auto permission mode — plus the SDK 0.3.168 native-binary upgrade. (June 11, 2026) - [DorkOS 0.42.0](https://dorkos.ai/blog/dorkos-0-42-0): Memory recall transparency and per-session runtime ownership — see which memory files shaped each reply, gate capabilities per session, and upgrade SDK runtimes with a dedicated workflow. (June 5, 2026) - [DorkOS 0.41.0](https://dorkos.ai/blog/dorkos-0-41-0): Plugin installation polish and chat input reliability — responsive dialogs, personality picker enhancements, and critical fixes for agent discovery and server stability. (April 15, 2026) - [DorkOS 0.40.0](https://dorkos.ai/blog/dorkos-0-40-0): Agent personality and sidebar polish with verbosity-based traits, lifecycle actions, and scoped marketplace installs (April 14, 2026) - [DorkOS 0.39.0](https://dorkos.ai/blog/dorkos-0-39-0): Agent Hub reimagined with immersive hero, Cosmic Nebula visualization, and smooth panel animations (April 12, 2026) - [DorkOS 0.38.0](https://dorkos.ai/blog/dorkos-0-38-0): Agent creation polish and chat input reliability improvements (April 11, 2026) - [DorkOS 0.37.0](https://dorkos.ai/blog/dorkos-0-37-0): Mesh discovery and agent creation — pre-scan landing states, 7 new AI agent strategies, an instant-advance creation wizard, and a unified /agents page. (April 11, 2026) - [DorkOS 0.36.0](https://dorkos.ai/blog/dorkos-0-36-0): Agent sidebar redesign with stable ordering, pinning, context menus, and activity badges (April 11, 2026) - [DorkOS 0.35.0](https://dorkos.ai/blog/dorkos-0-35-0): Release tooling and configuration robustness — schema validation gates, migration automation, and marketplace stability converge to prevent upgrade breakage. (April 9, 2026) - [DorkOS 0.34.1](https://dorkos.ai/blog/dorkos-0-34-1): Emergency patch — unblocks `npm install -g dorkos` and restores the Docker image publish pipeline after the v0.34.0 release shipped broken. (April 9, 2026) - [DorkOS 0.34.0](https://dorkos.ai/blog/dorkos-0-34-0): The marketplace lands — install pipeline, in-app Marketplace, public web catalog, strict Claude Code superset, and external MCP agent access all ship together. (April 8, 2026) - [DorkOS 0.33.0](https://dorkos.ai/blog/dorkos-0-33-0): Intelligent channel binding and dependency awareness — adapters become channels, runtime requirements surface during onboarding, and system configuration becomes discoverable. (April 5, 2026) - [DorkOS 0.32.0](https://dorkos.ai/blog/dorkos-0-32-0): Chat refinement and architectural cleanup — interrupt queries, see activity at a glance, and benefit from a cleaner codebase. (April 4, 2026) - [DorkOS 0.31.0](https://dorkos.ai/blog/dorkos-0-31-0): Refining agent UX through redesigns and standards adoption — clearer palettes, transparent context usage, and portable skill definitions bring polish and portability to the operator platform. (April 3, 2026) - [DorkOS 0.30.0](https://dorkos.ai/blog/dorkos-0-30-0): Discovery and documentation refinement — unified scan actions, onboarding polish, and a full contributing guide refresh. (March 31, 2026) - [DorkOS 0.29.0](https://dorkos.ai/blog/dorkos-0-29-0): Agent fleet management and UI refinement — DataTable-powered agent lists, command palette agent settings, and a streamlined dashboard. (March 30, 2026) - [DorkOS 0.28.0](https://dorkos.ai/blog/dorkos-0-28-0): Tasks redesign, DorkBot system agent, and the extensibility platform matures with manifest-driven settings, extension hooks, and MCP elicitation. (March 30, 2026) - [DorkOS 0.27.0](https://dorkos.ai/blog/dorkos-0-27-0): Canvas as a first-class surface — persistent, toggleable, and mobile-ready (March 28, 2026) - [DorkOS 0.26.0](https://dorkos.ai/blog/dorkos-0-26-0): Network resilience and operator onboarding — faster SSE streams with custom headers and a welcoming first-time experience. (March 28, 2026) - [DorkOS 0.25.0](https://dorkos.ai/blog/dorkos-0-25-0): Extensibility platform and composable filtering — agents can now build and install extensions, and every list surface gets URL-synced, filterable, sortable data views. (March 27, 2026) - [DorkOS 0.24.0](https://dorkos.ai/blog/dorkos-0-24-0): Desktop app, tunnel security, and resilience — native macOS distribution, passcode-gated remote access, and SSE auto-reconnect harden the operator experience. (March 25, 2026) - [DorkOS 0.23.0](https://dorkos.ai/blog/dorkos-0-23-0): Task visibility and execution awareness — progress bars, dependencies, and animated background indicators bring your agent fleet to life. (March 23, 2026) - [DorkOS 0.22.0](https://dorkos.ai/blog/dorkos-0-22-0): TodoWrite task system, speculative sessions, and brand icon refresh (March 23, 2026) - [DorkOS 0.21.0](https://dorkos.ai/blog/dorkos-0-21-0): Agent creation pipeline, fleet management surface, and A2A gateway (March 23, 2026) - [DorkOS 0.20.0](https://dorkos.ai/blog/dorkos-0-20-0): Adapter ecosystem expansion with Chat SDK Telegram integration, A2A gateway specification, and agent personality conventions. (March 22, 2026) - [DorkOS 0.19.0](https://dorkos.ai/blog/dorkos-0-19-0): Fleet management dashboard — dedicated agents page, a live overview, and client-side routing (March 21, 2026) - [DorkOS 0.18.0](https://dorkos.ai/blog/dorkos-0-18-0): Chat simulator, interactive tool fixes, and developer guide refresh (March 19, 2026) - [DorkOS 0.17.2](https://dorkos.ai/blog/dorkos-0-17-2): Dev port convention update and test reliability fixes (March 19, 2026) - [DorkOS 0.17.1](https://dorkos.ai/blog/dorkos-0-17-1): Streaming message integrity and reliability fixes (March 19, 2026) - [DorkOS 0.17.0](https://dorkos.ai/blog/dorkos-0-17-0): CLI polish, Apple-style field grouping, and relay hardening (March 18, 2026) - [DorkOS 0.16.0](https://dorkos.ai/blog/dorkos-0-16-0): Interactive tool approval, standardized form fields, and resilient streaming (March 18, 2026) - [DorkOS 0.15.0](https://dorkos.ai/blog/dorkos-0-15-0): Multi-client awareness, extended thinking visibility, and dev playground overhaul (March 17, 2026) - [DorkOS 0.14.0](https://dorkos.ai/blog/dorkos-0-14-0): Binding-level permissions, relay panel redesign, and SDK command discovery (March 16, 2026) - [DorkOS 0.13.1](https://dorkos.ai/blog/dorkos-0-13-1): Fix CLI startup crash and relay build compatibility (March 14, 2026) - [DorkOS 0.13.0](https://dorkos.ai/blog/dorkos-0-13-0): Slack integration, Docker containerization, and adapter system unification (March 14, 2026) - [DorkOS 0.12.0](https://dorkos.ai/blog/dorkos-0-12-0): Marketing storytelling, topology intelligence, and Pulse schedule management (March 13, 2026) - [DorkOS 0.11.0](https://dorkos.ai/blog/dorkos-0-11-0): Shortcut discoverability, design system refinements, and UX fixes (March 11, 2026) - [DorkOS 0.10.0](https://dorkos.ai/blog/dorkos-0-10-0): Tabbed sidebar navigation, agent identity chip, ScheduleBuilder, and always-editable chat input (March 11, 2026) - [DorkOS 0.9.1](https://dorkos.ai/blog/dorkos-0-9-1): Chat UX refinements — file attachments rendered inline, message bubbles right-aligned, and relay directory fixes (March 10, 2026) - [DorkOS 0.9.0](https://dorkos.ai/blog/dorkos-0-9-0): External agent connectivity via embedded MCP server, file uploads in chat, a polished chat UX, and major SSE reliability fixes. (March 9, 2026) - [DorkOS 0.8.0](https://dorkos.ai/blog/dorkos-0-8-0): Agent-centric control surfaces, a redesigned command palette, and critical reliability hardening across the relay and mesh pipelines. (March 4, 2026) - [DorkOS 0.7.0](https://dorkos.ai/blog/dorkos-0-7-0): Brand refresh, CI hardening, and marketing site overhaul (March 2, 2026) - [DorkOS 0.6.0](https://dorkos.ai/blog/dorkos-0-6-0): First-time user experience, remote access overhaul, and research library curation (March 2, 2026) - [DorkOS 0.5.0](https://dorkos.ai/blog/dorkos-0-5-0): Human-readable Relay messaging, marketing site overhaul, and 125+ code quality fixes. (March 1, 2026) - [DorkOS 0.4.0](https://dorkos.ai/blog/dorkos-0-4-0): Multi-agent infrastructure — Relay message bus, Mesh discovery, Agent Identity, and unified database. (February 26, 2026) - [DorkOS 0.3.0](https://dorkos.ai/blog/dorkos-0-3-0): Pulse scheduler brings autonomous agent jobs, plus tunnel sharing, blog infrastructure, and a documentation overhaul. (February 18, 2026) - [DorkOS 0.2.0](https://dorkos.ai/blog/dorkos-0-2-0): Marketing site, tunnels, and FSD migration. (February 17, 2026) RSS feed: https://dorkos.ai/blog/feed.xml ## Links - Website: https://dorkos.ai - GitHub: https://github.com/dork-labs/dorkos - npm: https://www.npmjs.com/package/dorkos - Contact: hey@dorkos.ai