Request early access

Cloud and local AI, working as one.

Forjal is an applied AI lab. We research and build the systems that let the AI you use in the cloud work with the computer you already own.

Read the manifesto

Computing has done this before.

Work moved from the mainframe to the personal computer when personal machines became efficient enough for the job, not when they beat the mainframe. AI is at the same turn.

Two transitions. Then: work moves from the mainframe to the personal computer along a full adoption curve. Now: AI work moves from the data center to your computer along the same curve, solid up to today and dashed after it, fading out.
5.3x

more intelligence per watt from local AI, 2023 to 2025

Stanford

3.5months

for open models to double their capability per parameter

Nature Machine Intelligence

>50%

of new PCs expected to ship with an AI chip in 2026

Counterpoint Research

Your AI and your computer rarely work together.

The AI people rely on every day runs in a data center. The computer in front of them, with a chip built for AI, mostly sits out.

Local AI exists, but it is usually built as a destination: another chat, another runtime, another model to manage. It rewards people who enjoy the setup and own high-end machines, and asks everyone else to change how they work.

NVIDIA researchers argue that small models are powerful enough, better suited and more economical for many of the calls an AI agent makes. Which parts of people’s work belong on their own machine is still an open question. It is the question our research is built around.

Source: Belcak et al., NVIDIA Research, 2025

Local AI should join the AI you use. Not replace it.

We are early. The best questions are still open.

Research and product share one loop: every product we ship is an instrument of the research.

All research →

Where local AI fits.

Which parts of people’s work belong on their own machine.

The hardware people own.

How to get the most from CPUs, GPUs and NPUs.

Capable local agents.

The architecture and harness that make local models work.

LatestProduct

Forjal is coming to Surface Laptop Ultra

Surface Laptop Ultra puts 128 GB of unified memory and an NVIDIA RTX Spark chip on a laptop. We're bringing Forjal to it, so the agent you already use can work with a capable local agent on the same machine.

Read the note
Introducing our first product

Open Hybrid Intelligence

The bridge between your computer and the AI agents you already use.

  • Claude Code
  • Codex
  • OpenClaw
  • Hermes Agent
  • OpenCode
  • Pi
  • Fewer cloud tokens
  • More free context
  • Files stay on your machine

Work with us

Bring it to your team.

Your company already owns the compute. The laptops your team uses carry chips built for AI, and Forjal puts them to work inside the agents your team already uses. We are working with a few teams on what that should look like.

Build with us.

We are a small lab. If you want to work on how cloud and local AI work together, we would like to hear from you.

Make local intelligence a natural part of every AI workflow.

Your hardware, in the loop.