Hard problems need new tools.

Explore AI Performance Discover the research

The Numaro approach

From mathematical discovery
to faster computation.

We build AI that explores ideas, creates tools, and checks its own work. From mathematical discovery to faster AI and computation.

Meet the research engine

From the labA 22-year mathematical record, broken.

AI Performance

Make your hardware go further.

Explore the work

AI workloads & kernels

Make your model run faster and use less memory.

Compilers & runtimes

Optimize MLIR/IREE, TVM, and LLVM toolchains for GPUs and custom accelerators, with hardware or simulator evaluation.

Specialized languages & toolchains

Build a software foundation around your particular workload.

One workload. An agreed baseline. A measurable next step.

Discuss a pilot

Research in the open

Ideas with evidence.

All research

01 / Mathematical discovery

22 years

A mathematical record, broken.

A new rigorous lower bound for square-lattice self-avoiding walks, improving the 2004 record.

Explore the result

02 / AI performance

2–4.5×

Faster kernels for AI.

Selected batched matrix multiplications on NVIDIA L40S, measured against torch.bmm / cuBLAS.

See the benchmarks

0.93663An AI-discovered chip-placement algorithmmean placement proxy · Chip design 11,000+Spherical-code record campaignverified records · Discrete geometry 45Matrix-multiplication schemesrecords · Algebraic complexity

The research engine

Every experiment
informs the next.

Agents explore hypotheses, build tools, and test results. Shared memory carries the evidence and working methods into the next campaign.

How autoresearch works

Work with Numaro

Put research to work.

Start with your workload and a clear performance target.