Cloud-side autonomous work
Clark Agent runs in Clark’s cloud on its own computer, so it can keep working for hours after you close the tab.
Clark Labs
Clark Labs offers two AI agents: Clark Agent for autonomous browser-based work in the cloud, and Clark Code for coding tasks on your own machine. It also provides an OpenAI-compatible Clark Platform API for developers.
Two AI agents from Clark Labs
Clark Labs builds two related products: Clark Agent, an autonomous computer-use agent that runs in Clark’s cloud, and Clark Code, an AI coding agent that runs on your machine. Together they cover two common workflows: delegating browser-based tasks to a cloud computer, or pairing with a repository on a local or remote development environment.
Clark Agent is designed for jobs that can run while you are offline, including research, bookings, documents, forms, and recurring workflows. Clark Code is aimed at software work on a real codebase, with support for reading, editing, running tests, and carrying project memory across sessions. The site also offers the Clark Platform, an OpenAI-compatible API gateway for teams and developers who want to use Clark models or route frontier models through a single interface.
Core capabilities
Browser, terminal, and file access
It can use a real browser, terminal, and files to research, build websites and documents, fill forms, and handle recurring workflows.
Citable, reviewable results
The product returns work as inspectable artifacts with cited sources, so you can review findings instead of treating the output as a black box.
Local or remote repo execution
Clark Code reads, edits, and runs code in your real repository on your machine or over SSH, rather than in a cloud sandbox you do not control.
Repository memory
It keeps a persistent memory of project architecture, conventions, and prior decisions, which reduces repeated setup across sessions.
API gateway and SDK support
The Clark Platform exposes an OpenAI-compatible API gateway, letting apps call Clark Agent or route to frontier models through the same interface.
Common workflows
Delegate web tasks to a cloud computer
Use Clark Agent for research, comparison shopping, form filling, bookings, and other browser-based errands that can continue while you are away from the screen.
Work directly inside a codebase
Use Clark Code when you need an assistant that can read a repository, make edits, run tests, and keep track of project decisions across sessions.
Integrate agent or model access into software
Use the Clark Platform when you want one OpenAI-compatible API to call Clark Agent or route requests to frontier models in your application.
Adopt the workflow in a team setting
Use Clark Labs engagements when your organization wants an on-site team to install the same loop-based approach for product development, research, testing, or recurring operations.
Automate repeatable operational workflows
Use Clark Agent for recurring monitoring or reporting jobs that should run on a schedule and return results for human review.
Pros and Cons
Pros
- Clark Agent can keep working in the cloud after you close the tab, which suits long-running tasks.
- Clark Code works on your actual repository on a local machine or remote host over SSH.
- The products are split by workflow, making it easier to choose between web tasks and coding tasks.
- Clark Agent output is presented as something you can review, with cited sources for research work.
- The Clark Platform uses an OpenAI-compatible interface and official SDKs in five languages, which lowers integration effort for developers.
Cons
- The source does not provide a full technical specification for browser, terminal, file, or integration boundaries beyond the high-level product descriptions.
- iOS for Clark Agent and Windows/Linux for Clark Code are not yet fully available according to the site.
- Pricing details are clearer for agent plans and platform usage than for every workflow boundary or feature limit.
FAQ
How does Clark Agent work?
Clark Agent runs in Clark’s cloud with its own browser, terminal, and file storage. You give it a task, let it work, and review the finished result when it is done.
How does Clark Code differ from Clark Agent?
Clark Code runs on your own machine, or on a remote host over SSH. It reads, edits, and runs your real repository, and it is available as a native desktop app for macOS, Windows, and Linux.
Does Clark have plans for both individuals and teams?
Yes. The pricing page describes individual plans, focused Coder and BYOK options, and seat-based team plans with shared credits and organization billing controls.
Can developers use Clark through an API?
Yes. The platform page describes Clark as an OpenAI-compatible gateway, with official SDKs in TypeScript, JavaScript, Python, Rust, and Zig.
What platforms are supported?
The source says Clark Agent is available on the web and Android now, with iOS coming soon. Clark Code is available on macOS, Windows, and Linux, with Linux also packaged as .deb and .rpm.
Quick Facts
- Category
- AI Agent / Developer Tool
- Brand
- Clark Labs
- Products
- Clark Agent, Clark Code, Clark Platform
- Platforms
- Web, Android, macOS, Windows, Linux
- Pricing model
- Paid plans and per-token API pricing
- Website
- clarkchat.com
Alternatives à Clark Labs
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
Ghost
Ghost est un assistant IA en terminal pour discuter, générer du code et lancer des tâches en ligne de commande. Modèles gratuits, Linux, macOS, Windows, open source.
Devin
Devin is an AI coding agent and software engineer that helps developers and engineering teams plan and execute complex software tasks. It is available through desktop, cloud, JetBrains, and CLI surfaces, with plans for individuals, teams, and enterprises.
Codex Plugins
Codex Plugins bundle reusable skills, app integrations, and MCP servers into workflows you can install in the Codex app or use from Codex CLI. They help extend Codex with connected-service tasks, reusable instructions, and shared team workflows.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.