HN Explorer

Show HN: I built an open-source alternative to Claude Cowork (github.com)

1 points by wayneshng ↗ HN
Hey HN,

A few months ago, I tried to automate some of my work with the popular AI agent OpenClaw, and then I quickly realized how difficult it is to get it to work with APIs and third-party services securely, which is essential for a lot of work-related tasks.

Then I realized OpenClaw is more of a personal assistant and it was not designed to get actual work done as a coworker. So I started to build Valmis, an alternative to OpenClaw that works with more than 100 apps and services, with security being the priority.

Valmis addresses the security issue by designing a proxy system: dockerized agent runtime can only request the host machine to make API requests by providing the relevant credential ID. The host then makes the actual request and returns the JSON data to the agent runtime. With this design, you can even turn off the internet access of the agent container while making it work.

Our proxy system now supports 100+ business and productivity integrations, including all Google Workspace apps, Slack, Notion, HubSpot, Salesforce, and Figma.

One of the coolest features of Valmis is the automated workflow. You can automate multi-step workflows using our workflow builder. Each workflow can be triggered by cron, webhooks, app events, and it supports conditions and loops.

I'd be happy to answer any questions in the comment section.

10 comments

[ 3.3 ms ] story [ 551 ms ] thread
wayneshng
Interesting stuff, how does it different from n8n? Also I like how you get to make agents play legit chess in your readme.
wayneshng
Thanks! I'd say the workflow part is inspired by n8n, but overall, the project aims to build an OpenClaw, but for work. So the primary interface is the chat UI where teams and users can interact with the agent. Workflows can be created by the agent via human language, but you can also create workflows on an n8n-style canvas.

For the chess part, yeah, it's an example I created to show how LLMs can actually do rigorous work. We cannot always trust the output generated (or hallucinated most of the time) by LLMs, but if we add a deterministic tool layer and instruct the model to rely only on the tool's output, we can get more accurate results. In this case, the tool used is a lightweight chess engine.

CupofChineseTea
Looks good, I’ll spin up an instance and give it a try. Btw, does it support multiple users? And the chess engine thing is brilliant, I guess you can extend your logic to other fields, can tools be extended by the end user?
wayneshng
It doesn’t current support multiuser, but the system is designed to support multiple users with different roles and permissions. I’m also adding a feature to share credentials between teams, which will be rolled out soon. For the tools call question, yes, this will be a generic mechanism for producing rigorous results from agents. I’m planning to extend it to other fields such as calculation, data analysis and deep research. The basic idea is to give zero trust to any outcome generated through LLMs’ text generation to avoid hallucinations, and only trust results from tool calls.
daanlo
Looks cool. Will check it out :)
wayneshng
Thanks! Let me know if you have any feedback or comments.
cunjieliu
What's the difference between this and n8n
wayneshng
I’d say the workflow feature is inspired by automation tools like n8n, but the workflow execution is “ai native”. For example, for a condition node, we use AI to determine true or false, so that you don’t have to compare fixed values. Also, workflows can also be created from the chat UI by talking to the agent.