Open-Cowork: open-source alternative to Claude Cowork with BYOK

Open-Cowork, an open-source alternative to Claude Cowork, launches as a cross-platform agentic coworker that automates computer tasks via screen observation and action. The tool supports bring-your-own-LLM (BYOK) with providers like OpenRouter, OpenAI, and local models, and offers live streaming, approval pauses, and cost controls. It runs on the Coasty Computer Use API by default but allows users to switch models, aiming to democratize AI desktop automation.

Hand off computer tasks to an AI coworker — watch it work, approve from anywhere. An open-source, cross-platform agentic coworker that sees a screen and acts on it — your own desktop, a cloud VM, or a browser. It streams every step live, pauses for your approval, and keeps spend visible and capped. Runs on the Coasty Computer Use API https://coasty.ai/docs out of the box — or bring your own LLM OpenRouter · OpenAI · a local model . Your call. Quickstart quickstart · · bring-your-own-llm-byok Bring your own LLM · /coasty-ai/open-cowork/blob/main/RUN LOCALLY.md Automate your PC · what-you-can-do Features How it works how-it-works · Docs docs Prereqs:Node ≥ 22.5 we use 24 · pnpm 10 corepack enable . git clone https://github.com/coasty-ai/open-cowork.git && cd open-cowork pnpm install one install for the whole monorepo pnpm desktop ← runs the desktop app: starts backend + web, opens the window That's it — one command, zero config. pnpm desktop starts the backend and web UI, then opens the desktop app the build that can drive your own screen . With no key set it runs in demo mode : a bundled mock server and a throwaway sandbox key — no account, no network, no billing. Then, in the window: - Sign in with any email. - On Delegate , pick “This computer local screen .” - Type a task → confirm the cost → watch it work. Tip: put NEEDS HUMAN in a task to see the approval flow pause and resume. 🧠 Bring your own LLM BYOK .Want it to run onyourmodel instead of Coasty? OpenSettings → Model providerand add OpenRouter, OpenAI, or a local model Ollama / LM Studio . Coasty stays the default until you switch. Jump to BYOK ↓ ⚠️ Local control moves yourrealmouse and keyboard. Stop withCancel or close the window , and start small — full safety notes in. RUN LOCALLY.md | Goal | How | Model | Cost | |---|---|---|---| Automate your own PC | pnpm desktop | Coasty or your own LLM | demo $0 · BYOK = your provider's rate | Web app only | pnpm dev → | Coasty | $0 | Your Coasty account | add COASTY API KEY to .env | Coasty real model | sandbox key = $0 | Bring your own LLM BYOK | Settings → Model provider | OpenRouter · OpenAI · Ollama | your provider's rate · local = $0 | The only thing you ever have to set is COASTY API KEY — and even that's optional in demo mode. Everything else has a working default. Prefer your own model? That's BYOK — pick a provider in Settings and local runs use it. Full local-automation guide: RUN LOCALLY.md . Using your own Coasty account, webhooks & the cost warning echo "COASTY API KEY=sk-coasty-test-…" .env sandbox key — never bills pnpm dev now talks to the real Coasty API With a key set, pnpm dev does not start the mock and points the backend at the real Coasty API. Start with a sandbox key sk-coasty-test-… — it exercises the full real model and never bills. Switch to a live key only when you're ready to spend. Webhooks instant status without polling require an https COWORK PUBLIC URL — Coasty only accepts HTTPS webhook URLs. open-cowork detects this: over a non-https URL it simply doesn't register a webhook so run creation never fails and state still syncs live via SSE + read-time reconcile. Set an https COWORK PUBLIC URL a tunnel or your deployment — see DEPLOYMENT.md /coasty-ai/open-cowork/blob/main/DEPLOYMENT.md to turn webhooks on. ⚠ Cost warning.With alivekey sk-coasty-live-… : runs bill$0.05/step, machines$0.05–0.09/hourrunning $0.01 stopped , predict/session calls a few cents each. open-cowork always shows an estimate, requires explicit confirmation, enforces per-run budget caps server-side, and supports machine auto-terminate TTLs — but a live key is real money. All automated tests use the mock/sandbox path and never spend anything. pnpm desktop full stack + the desktop app local screen control — one command pnpm dev full stack, open the web app yourself at :5173 pnpm dev --no-web API only mock + backend pnpm dev:mobile Expo / React Native or: pnpm --filter @open-cowork/mobile web Run the Electron app against an already-running stack advanced With pnpm dev already running in another terminal: pnpm dev:desktop builds the Electron bundles and opens the window only pnpm desktop does both for you — start the stack and open the window — and shuts it all down when you close the window. - 💬 Delegate in chat — "rename these files and email the report" — and watch the agent execute it step by step with a live screen view. - 🧠 Bring your own LLM BYOK — run local screen control on your model: OpenRouter, OpenAI, or a local model Ollama / LM Studio / vLLM . Coasty is just the default. Details ↓ bring-your-own-llm-byok - 📺 Supervise runs — dashboard, durable event timeline SSE with replay , cancel / resume / human-takeover from web, desktop, or phone. - 🔁 Build workflows — a versioned JSON DSL task · assert · if · loop · parallel · retry · human approval with instant validation, cost estimates, and hard server-side budget caps. - 🖥️ Manage machines — provision Coasty cloud VMs, snapshot, stop, terminate, with live cost rates at every step. - 📱 Stay in the loop across devices — start a run on your laptop; when it pauses for approval, the banner pops on your phone. Approve there. - 💸 See cost at all times — wallet balance, per-run worst-case estimates, and an explicit confirm-the-cost handshake before anything billable starts. | Capability | 🖥️ Desktop | 🌐 Web | 📱 Mobile | |---|---|---|---| | Local screen control | ✅ first-class | → cloud machine | → cloud machine | | Cloud-machine control + live view | ✅ | ✅ | ✅ | | Task chat + run dashboard | ✅ | ✅ | ✅ | | Workflow builder | ✅ full | ✅ full | view + approve | | Approvals / human takeover | ✅ | ✅ | ✅ | | Cost / wallet view | ✅ | ✅ | ✅ | Bring your own key, bring your own model. Local screen control defaults to Coasty's computer-use model — but you can point it at any OpenAI-dialect LLM instead. In the desktop app, open Settings → Model provider , pick a provider, choose a vision-capable model, and local runs use it. Coasty stays the default; switch back any time with one click. Nothing else in the app changes. | Provider | API key | Covers | |---|---|---| OpenRouter | required | hundreds of models; vision read from OpenRouter's own modality metadata | OpenAI | required | gpt-4o , gpt-4.1 , … | OpenAI-compatible | optional | Ollama, LM Studio, vLLM, Together, Groq — any …/v1 base URL | - 👁️ Vision is required. Computer use is screenshot-driven, so a model that can't see images is flagged and blocked with a clear message — never a blind, wasted run. - 🏠 Local-first. A local model e.g. Ollama at http://localhost:11434/v1 runs entirely on your machine — no key, no cloud, no spend. - 🔑 Your key stays yours. BYO keys are encrypted with your OS keychain Electron safeStorage — DPAPI / Keychain / libsecret , live only in the desktop process, are scrubbed from every error message, and never reach the web or mobile bundle. - 👀 No surprise data egress. With a third-party model, your screenshots and prompts go to that provider — the app says so right in the confirm-the-cost dialog before a run starts. - ☁️ Cloud-machine runs always use Coasty. BYO drives local desktop runs today; cloud BYO is a documented follow-up. Built on the Vercel AI SDK : rate-limit 429 and transient errors retry with backoff, and if a model ignores structured output the response is recovered with a defensive JSON parse — so even smaller local models can drive the loop. You ──► open-cowork backend ──► Coasty API ──► a screen the agent drives │ the ONLY place ├─ your own desktop desktop app │ the API key lives ├─ a Coasty cloud VM any client └──► web / desktop / mobile └─ a browser page Playwright live events, approvals, costs One shared agent loop screenshot → predict → act → repeat drives any screen through a single Executor interface — LocalExecutor your desktop , RemoteMachineExecutor a cloud VM , or BrowserExecutor . The predict step is its own seam @open-cowork/llm : Coasty is the default implementation, and a bring your own LLM bring-your-own-llm-byok is just another one behind the same contract, so the loop, executors, and UI don't care which is behind it. Clients never hold the Coasty key: they talk to the backend with short-lived session tokens, and the backend proxies to Coasty, verifies HMAC-signed webhooks, persists runs, and fans events out over SSE. Full design in ARCHITECTURE.md . COASTY API KEY exists only in the backend's environment. Browsers, Electron renderers, and the mobile app authenticate with short-lived session tokens and never see the key — enforced by tests that scan every client bundle and a runtime E2E assertion that watches every browser request for secret material. Bring-your-own-LLM keys follow the same rule: encrypted with the OS keychain safeStorage , held only in the desktop process, scrubbed from every error, and kept out of the web/mobile bundles the AI SDK is desktop-only . Coasty webhooks are verified with per-run HMAC secrets constant-time compare, ±5-minute replay window before they can touch any state. Threat notes in SECURITY.md . | Guide | What's inside | |---|---| | Automate your own PC with the desktop app — step by step | | SECURITY.md /coasty-ai/open-cowork/blob/main/SECURITY.md DEPLOYMENT.md /coasty-ai/open-cowork/blob/main/DEPLOYMENT.md COOKBOOK.md /coasty-ai/open-cowork/blob/main/COOKBOOK.md DECISIONS.md /coasty-ai/open-cowork/blob/main/DECISIONS.md · CONTRIBUTING.md /coasty-ai/open-cowork/blob/main/CONTRIBUTING.md · SUMMARY.md /coasty-ai/open-cowork/blob/main/SUMMARY.md packages/core Coasty client, agent loop, workflow DSL, cost estimator, HMAC — isomorphic, zero deps packages/executor Executor abstraction: LocalExecutor native , RemoteMachineExecutor VM , BrowserExecutor packages/llm BYO LLM provider seam: Coasty + OpenAI/OpenRouter/Ollama via the Vercel AI SDK desktop-only packages/ui Shared React design system + domain components apps/backend Fastify: auth, Coasty proxy sole key holder , webhooks, SQLite, SSE fan-out, budgets apps/web Vite + React SPA also hosted by the desktop shell apps/desktop Electron shell + LocalRunManager local screen control apps/mobile Expo / React Native companion monitor + approve tools/mock-coasty Full offline mock of the Coasty API REST + SSE + signed webhooks e2e Playwright end-to-end flows web + desktop | Command | What | |---|---| pnpm dev | mock + backend + web, wired together --no-web for API only | pnpm doctor | preflight: Node, deps, key shape | pnpm test | every unit + integration suite offline, no spend | pnpm typecheck · pnpm lint · pnpm format | strict static checks | pnpm e2e | Playwright: web + desktop journeys vs the mock | pnpm security:scan | assert no secret material in client code/bundles | pnpm dev:mock|backend|web|desktop|mobile | run any single piece | Repository: https://github.com/coasty-ai/open-cowork https://github.com/coasty-ai/open-cowork Issues & feature requests: https://github.com/coasty-ai/open-cowork/issues https://github.com/coasty-ai/open-cowork/issues Report a vulnerability: Security Advisories https://github.com/coasty-ai/open-cowork/security/advisories see SECURITY.md /coasty-ai/open-cowork/blob/main/SECURITY.md Coasty: docs https://coasty.ai/docs · API keys https://coasty.ai/developers/keys MIT /coasty-ai/open-cowork/blob/main/LICENSE © Coasty / open-cowork contributors