Show HN: OpenWeavr – Run AI workflows on your own machines to automate tasks (github.com)
I’m building OpenWeavr, an open-source platform that lets you run AI agents on your own machines (Mac minis, laptops, or spare computers) to automate real-world tasks.
The idea is simple: many workflows still require manual steps across apps, browsers, and tools. Instead of relying only on cloud SaaS automation, OpenWeavr lets you run agents locally so they can:
• Automate workflows across apps and websites • Run long-lived agents on always-on machines • Orchestrate tasks across multiple devices • Keep data local and private via self-hosting
A lot of people have idle Macs or spare computers at home or work — OpenWeavr turns them into automation workers.
Current focus: • Simple self-host setup • Agent workflows & task automation • Developer-friendly APIs • Privacy-first architecture
The project is still early, and I’d love feedback from the HN community on:
• What tasks would you automate first? • What’s missing from current automation tools? • What would make you run something like this at home or work?
Repo & docs: https://openweavr.ai
Happy to answer questions and would love contributors or feedback!
1 comment
[ 3.1 ms ] story [ 14.5 ms ] threadTo your question about what tasks to automate: one bottleneck I keep hitting is the "teaching" step. Even with a great runtime like this, you still need to define what the agent should do. Writing detailed workflow specs is tedious and error-prone.
We've been tackling this from the input side with SkillForge (https://skillforge.expert) — you record your screen doing a workflow, and AI extracts a SKILL.md that agents can execute. Think of it as "show, don't tell" for agent automation.
A platform like OpenWeavr + a recording-based skill creator could be really complementary. The recording handles the "what to do" part, and OpenWeavr handles the "where to run it" part.
What's the workflow definition format you're using?