A guide for using Meta AI's ESM-2 protein language model through the fair-esm Python package. The model reads amino-acid sequences and produces numerical representations or prediction scores.

Use it to create per-sequence or per-residue embeddings, score possible mutations with masked-language predictions, or predict contacts from protein sequences.

It gives developers a documented way to turn protein sequences into data for machine-learning analysis. It also clarifies which ESM package is meant and lists computing requirements such as Python, CUDA, and GPU memory.

fair-esm2 — Skill for Claude Code and Codex by UnicomAI

About the project

Wanwu is an enterprise platform for building AI agents, workflows, retrieval-augmented applications, and managing models in multi-tenant environments. It is designed for developers and enterprise teams delivering AI applications and integrations. The catalogue entries provide skills and agents for using the platform.

UnicomAI/wanwu · 2,461 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add UnicomAI/wanwu --skill fair-esm2

Clone the repo

git clone --depth 1 https://github.com/UnicomAI/wanwu

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/unicomai/wanwu/fair-esm2/github.svg)](https://agentmods.dev/skills/unicomai/wanwu/fair-esm2)

Your own site

<a href="https://agentmods.dev/skills/unicomai/wanwu/fair-esm2"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/fair-esm2/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/unicomai/wanwu/fair-esm2"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/fair-esm2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,393 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 86% copy Near-identical to another mod in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00066	$0.01393
Opus 5	$0.00033	$0.00696
Sonnet 5	$0.00013	$0.00279
Haiku 4.5	$0.00007	$0.00139

Measured 9d ago against content hash ab851af1124c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

fair-esm2 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

86% identical to fair-esm2 — 36 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

configs/microservice/bff-service/configs/agent-skills/claude-science/fair-esm2/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fair-esm2 — ESM-2 (Meta AI)

ESM-2 code and weights are MIT (Meta AI, github.com/facebookresearch/esm).

Package disambiguation. pip install fair-esm gives you import esm with esm.pretrained.* (ESM-1/2). Biohub's github.com/Biohub/esm fork (MIT) gives you from esm.models.esmfold2 import ESMFold2InputBuilder — see the esmfold2 skill. Both share the esm namespace but are different libraries. This skill covers fair-esm (the Meta package).

Prerequisites

Requirement	Minimum	Recommended
Python	3.8+	3.11
CUDA	11.7+	12.x
GPU VRAM	8 GB (8M), 16 GB (650M)	24 GB+ (650M / 3B)

How to run

Embeddings

import torch, esm

model, alphabet = esm.pretrained.esm2_t33_650M_UR50D()
model = model.eval().cuda()
bc = alphabet.get_batch_converter()

_, _, toks = bc([("ubq", "MQIFVKTLTGKTITLEVEPSDTIENVK")])
with torch.no_grad():
    out = model(toks.cuda(), repr_layers=[33])
emb = out["representations"][33]      # (1, L+2, 1280) — includes BOS/EOS
seq_emb = emb[0, 1:-1].mean(0)        # per-sequence mean

Masked-LM scoring

with torch.no_grad():
    out = model(toks.cuda(), repr_layers=[33])
logits = out["logits"][0, 1:-1]       # (L, |vocab|)
# WT marginal log-likelihood; for mutation scoring, mask the position and
# compare logit[mut] − logit[wt].

Contact prediction

with torch.no_grad():
    out = model(toks.cuda(), repr_layers=[33], return_contacts=True)
contacts = out["contacts"][0]         # (L, L)

Models

Name	Layers	Dim	Params	Use
`esm2_t6_8M_UR50D`	6	320	8 M	Fast smoke / tiny embeddings
`esm2_t33_650M_UR50D`	33	1280	650 M	Default embedding model
`esm2_t36_3B_UR50D`	36	2560	3 B	Best embeddings, 24 GB+

Read the full file on GitHub · 141 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

.catalog_stamp 13 B

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 141 lines · 66 tokens per session scan A ab851af1124c

Subscribe to this mod's changes

fair-esm2 is a skill published in the GitHub repository UnicomAI/wanwu (2,461 stars, last pushed 4d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,393 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to fair-esm2, differing in 36 lines, and is treated as a copy.

Data and AI LLM RAG and vectors Scientific ai biomodels mcp wanwu workflow

molecular-rag

Retrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. Based on MolRAG (Xian 2025, ACL).

synthetic-sciences/openscience · 40 tokens

dify

Use when building LLM applications with visual workflow — RAG knowledge bases, AI agents, chatbots with drag-and-drop orchestration. Dify: open-source LLM app platform supporting 30+ models (OpenAI, Claude, DeepSeek, Ollama, Qwen, GLM) with Docker deployment.

znlgis/opengis-skills · 66 tokens

ai-skills

Use when building LLM applications, RAG knowledge bases, AI agents, terminal coding agents, multi-model orchestration, plugin-based agent harnesses, or file translation. Index of 9 skills: Dify, Hermes Agent, OpenClaw, OpenCode, Pi, DocuTranslate, Oh-My-OpenAgent, Superpowers-zh, DeepSeek Harness.

znlgis/opengis-skills · 79 tokens

fair-esm2