Clark
An AI coworker with its own cloud computer
783 followers
An AI coworker with its own cloud computer
783 followers
Clark is an AI coworker with its own cloud computer - browser, terminal, files, and code. Hand it a real task, close the tab, and come back to finished work: wide, sourced research; websites; spreadsheets; decks; audits; or tested code. It can fan work out to parallel specialists, run on a schedule, and return artifacts with the evidence behind them. Use Clark on web or mobile, work in real repositories with Clark Code, or embed the agent through an OpenAI-compatible API.
Free Options
Launch Team / Built With
Clark
@stanislav_kirdey To be honest , I am actually waiting for something that can own an entire workflow instead of just helping with one prompt at a time. The cloud computer+ parallel specialists approach is a really interesting direction. Excited to give it a try.
Clark
@james_anderson77 thanks!
share your feedback here or on the app 💜
@stanislav_kirdey Seriously the ability to walk away from a task and come back to finished work is exactly the kind of experience I've been hoping AI would evolve toward . Excited to try this out.
@stanislav_kirdey What’s one real task you’d hand Clark right now and why; and what would you need to see in the returned files or logs to feel confident you could rely on it again?
Clark
@swati_paliwal i handle it a lot of prototype app building, very wide research, git repo analysis, anything where agent with browser can be great like filling out forms etc, and it manages my calendar too!
@stanislav_kirdey the returned artifact bit is what i'd test first. say Clark gives me a sourced research deck, i send it to a client, and they flag one claim on slide 7. can that note come back with the exact file/section/version attached, or am i back to pasting a screenshot into chat? if there's a public sample deck/report, happy to run that handoff once.
Clark
@eason_zhou makes sense!
The 'own cloud computer' framing is what separates this from a chat wrapper for me — but it lives or dies on state. Between tasks, is each job a fresh ephemeral VM wiped clean every time, or a durable workspace that keeps files and context so a scheduled monitor run actually builds on the last one? And with Clark Code in a real repo, does it work on a clone in its own env and hand back a PR/diff I can inspect, or does it need direct write access to the repo?
Clark
@noctis06 clark code it will work in the repo and do the changes just like codex or claude
the sandboxing/state questions above cover the trust side well. curious about the fan-out mechanic specifically - when Clark splits a task across parallel specialists, do they each get an isolated environment that gets merged into the final artifact, or do they share the same cloud computer/workspace while running concurrently? asking because shared-state parallelism is where I'd expect the weird bugs to show up first
Clark
@galdayan full isolated clarks with full browser and filesystem work in parallel and merge into final artifact
@stanislav_kirdey Full isolation makes sense - avoids exactly the shared-state race conditions I was worried about, at the cost of a merge step at the end. Is that merge automatic (Clark reconciling the artifacts itself) or does it flag conflicts for the user to resolve manually?
Fedica
Clark
@hamza_afzal_butt yes it can!
OpenMarkdown
Congrats on the launch! How does Clark compare to Hermes Agent deployed on a cloud computer? Does the workflow / tool-chain is built to be more complete towards problem-solving?
Clark
@xueyanzhang good question! Clark is optimized on doing complex workflows on its own computers with its own browser, and be extremely token efficient
what hermes does with opus 4.8 clark can do with gemini 3.1 flash life (20x cheaper!)
OpenMarkdown
@stanislav_kirdey Impressive harness! Will give it a try. What types of task fit the best for Clark.
Clark
@xueyanzhang
clark cloud is great to draft documents, do very deep and wide research, or prototype toy projects
clark code ide for serious software development as alternative to codex
an AI coworker with its own cloud computer is a wild framing. curious how you handle the case where it needs to install something or hit a paywall/captcha mid-task - does it just stall out and ping you, or does it have some way to work around that on its own?
Clark
@omri_ben_shoham1 it will try to solve it, and if it needs to login somewhere it willl ask you to take over browser and provide credentials
Moving from “answer my prompt” to “complete the work and return evidence” is the interesting shift here. For long-running tasks, how does Clark preserve the reasoning and context behind intermediate decisions so users can inspect more than just the final artifact?
Clark
@amir_mehrabi it shows full proof of work in chat