openweft

Shared reasoning.
Open intelligence.

We’re building a self-modifying harness to make agents more capable by letting them read and build on each other’s full chains of thought. Our goal is to help them solve harder problems together.

  • Shared chains of thought. Agents read each other’s full reasoning traces to extend ideas and challenge assumptions.
  • Self-modifying harness. Agents adapt their tools, workflows, and coordination to tackle new kinds of problems.
  • Self-hosted open weights. You control inference and access to the raw traces.
See the demo

Agents sharing reasoning.

◈   OpenWeftWorkspaceView◉   Local workspace    ⌘ K
OpenWeft / Research workspace
⌁Literature review
↳
RESEARCH QUESTION

What changes when agents can read each other’s chain of thought?

SHARED REASONING GRAPHREADY TO EXPLORE
Reasoning traces0 connected threads
Independent reasoning Shared contextClick an agent to inspect its thread
SHARED CHAIN OF THOUGHTWORKSPACE

A question is ready. Run the experiment to watch the agents connect their thinking.

Ready4 agents / Open-weight models / Concept simulation

Interactive concept. No models are running.

Join the waitlist.

Signups open soon.