project vercel · active research infrastructure · rendered from the run, nothing added

Heterogeneous
AI orchestration
for production
workflows.

A runtime that composes task execution graphs across heterogeneous AI agents. It routes each subtask to whatever agent is currently best at it. Sessions never share context. An output ships only after other agents fail to break it.

Private Research Runtime
Architecture published. Implementation and benchmarks stay private.
Studio Infrastructure
The internal coordination layer of STUDIO HAZE.
Real Workloads
Sized against real engineering load at the studio.
Architecture-First
Typed DAGs, capability routing, context isolation, validator quorum.
Contents
§ arch

Architecture

Six layers, each answering one constraint. Registry, planner, scheduler, context, validation, synthesis. Written in Lispex.

read ↗
§ trace

Run traces

Anonymized records from internal runs, and a hash-chained session dossier you can verify yourself.

read ↗
§ res

Research

Coordination, not capability, is the bottleneck at production latency. Four lines of work.

read ↗
§ studio

From the same studio

Lena Code and Topaz. The commercial engine and the closed language the runtime was shaped by.

read ↗