Menu

Individual skill

setup-mosaic-remote-tool

0upvotes

Set up, launch, validate, and troubleshoot the mosaic (Boltz-2 binder hallucination) ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

skills/setup-mosaic-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.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
1,781
Repository last updated
Nov 9, 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 mosaic (Boltz-2 binder design) as a remote tool

> Validation status (2026-10-02): mosaic (escalante-bio/mosaic through the joltz JAX port of Boltz-2) designed binders on the NVIDIA GB10 (aarch64, cc 12.1, driver 580.173.02) under the optimization kit's `off` mode. **mosaic DESIGNS a binder; it does not fold a sequence you give it.** One request is one design: a target sequence and a binder length in, a binder sequence plus the predicted complex and its ipTM / pLDDT / PAE out. Every one of the 125 optimiser steps is a full Boltz-2 forward and backward pass. Acceptance in one held worker: ladder 169 / 256 / 384 tokens (pool peak 8.0 / 16.0 / 32.0 GiB, in-use 4.85 / 8.13 / 15.67), mixed shapes 4/4, four identical requests 4/4 (23.6 / 23.4 / 23.3 / 23.2 s), every request writing a complex PDB. **Declared budget 32.0 GiB at the 384-token ceiling.** 512 tokens was measured and is not offered: about 120 s per step, so one design is hours. **Residency gain depends heavily on request size**: 11.5x for a 5-step request at 169 tokens (269.5 s cold, 23.5 s held) but only ~1.5x at 169 tokens and ~1.08x at 384 for the full 125-step recipe, because the compile it saves (a few minutes per shape) is small against the work. A new SHAPE (target residues x copies + binder length) pays a compilation; a seed or step change does not; an epitope or a second target copy costs a smaller recompile. Designs are not bit-reproducible across requests (boltz re-draws reference coordinates). The kit's `fast` mode engages here but was not adopted: see provider.toml. Wall times were taken on a shared card; peaks reproduce, times do not. Public publication, cross-user isolation, concurrency, recovery and scientific quality (a high ipTM is the model's opinion of a design optimised against it) 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. The model is JAX; its torch is CPU-only on purpose (it only reads the checkpoint).
- 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.
- The host's memory is one pool shared with the GPU: before starting the worker run `python scripts/remote_validation/wait_for_memory.py --need 42`.

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