Menu

Individual skill

setup-af3_jax-remote-tool

0upvotes

Set up, launch, validate, and troubleshoot the AlphaFold 3 (JAX fork) ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

skills/setup-af3_jax-remote-tool/SKILL.md

Read pinned source

Source commit 5598a9fc97e32964fe9b703818e7d0747142f179

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

Standard SKILL.md format has not been attested at this commit. No installation command is available; inspect the source.

Repository context

Repository stars (not skill ratings)
1,780
Repository last updated
Nov 8, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Set up AlphaFold 3 (JAX fork) as a remote tool

> Validation status (2026-10-01): AF3-JAX (the sokrypton/alphafold3 open fork on public OpenFold3-preview2 weights) folded on the NVIDIA GB10 (aarch64, cc 12.1, driver 580.173.02) under the optimization kit's `off` mode. **It is the first JAX provider on this standard, and the largest residency gain measured here: 24-26x** — four consecutive identical requests ran 170.5 / 8.3 / 7.0 / 7.0 s on an idle card and 179.1 / 6.8 / 6.8 / 6.8 s on a contended one, against RFdiffusion3's 12x. (A contended card gives the *higher* ratio, because it slows the first request far more than the replays; read any residency multiple with that in mind.) **That figure is the smallest input's, which is where it is largest: at the row the budget is declared on — 800 residues — the same worker gives 3.5x**, 755.0 s cold against ~218 s held. Plan with the second number; the first is the best case. Three things residency keeps, and the third is this provider's own: the 1.37 GB zstd weight read, the XLA executables (one per padding bucket), and **tokamax's per-shape autotune, which nothing persists** — upstream's `ModelRunner._load_autotune_cache` reads a file that its `except Exception: pass`-wrapped writer never produces here, so a worker restart pays the first-request price again per bucket. That is why `idle_timeout_s` is 900 and not something shorter. Ladder 2.0 / 4.0 / 4.0 / 8.0 GiB at 100 / 200 / 400 / 800 residues; declared budget 8.0 at the 832-token bucket. Eleven acceptance requests, every one asserted to have produced a structure. Two cautions below are specific to this provider: it does not run at all without one upstream flag (**the shared-memory wall**), and **its VRAM figure is quantised** in a way a torch provider's is not. Public publication, cross-user isolation, concurrency, recovery and scientific quality are untested; keep this deployment private.

## Prerequisites

- Run from the ToolUniverse repository root on Linux with Python 3.12.3.
- A CUDA GPU is required. This provider holds its model resident between requests; CPU is not a target.
- Keep provider data, weights, caches, and credentials outside Git.
- Bind to loopback. A non-loopback bind requires TOOLUNIVERSE_API_TOKEN; never put it in arguments or results.

Run the standard-library contract check before downloading large dependencies:

~~~bash
Back to top