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.
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.
npx skills add UnicomAI/wanwu --skill evo2git clone --depth 1 https://github.com/UnicomAI/wanwuWrote 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.
[](https://agentmods.dev/skills/unicomai/wanwu/evo2)<a href="https://agentmods.dev/skills/unicomai/wanwu/evo2"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/evo2/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.
<a href="https://agentmods.dev/skills/unicomai/wanwu/evo2"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/evo2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00083 | $0.01482 |
| Opus 5.5 | $0.00033 | $0.00593 |
| Sonnet 5.5 | $0.00017 | $0.00296 |
| Haiku 4.5 | $0.00008 | $0.00148 |
Grade A, and why
evo2 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 1mo 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.
This is a copy
98% identical to evo2 — 68 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.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evo 2 — DNA Language Model
Prerequisites
| Requirement | Minimum | Recommended |
|---|---|---|
| Python | 3.11 | 3.12 (<3.13) |
| CUDA | 12.1+ | 12.4+ |
| GPU VRAM | 24 GB (7B bf16) | 80 GB (40B) |
| RAM | 32 GB | 128 GB |
How to run
Installation
pip install evo2
# Weights pulled from Hugging Face on first model load.
Loading and scoring
from evo2 import Evo2
model = Evo2("evo2_7b") # or "evo2_40b" — see model table
seqs = ["ATCG" * 50, "GGGCTTAA" * 25]
ll = model.score_sequences(seqs) # → list[float], mean per-token log-likelihood
print(ll)
Generation
out = model.generate(
prompt_seqs=["ATGAAAGCT"],
n_tokens=256,
temperature=0.7,
)
print(out.sequences[0])
Models
| Name | Params | Context | VRAM (bf16) | Notes |
|---|---|---|---|---|
evo2_7b |
7 B | 1 M nt | ~22 GB | Default; fits on a single 24 GB+ GPU |
evo2_40b |
40 B | 1 M nt | ~78 GB | H100 80 GB or multi-GPU |
evo2_1b_base |
1 B | 8 K nt | ~6 GB | FP8 path requires sm_89+ (H100) |
Output format
score_sequences returns a list[float] (or np.ndarray) of mean log-likelihoods,
one per input sequence. More negative ⇒ less likely under the model. For variant
effect, compute Δll = ll_alt - ll_ref over a fixed window.
generate returns a GenerationOutput with .sequences (list[str]), .logits
(list[Tensor]), and .logprobs_mean (list[float]) — always populated, no flag required.
Decision tree
Need a DNA model?
│
├─ Per-base/per-sequence likelihood, generation → Evo 2 ✓
├─ Predict experimental tracks (expression, accessibility) → borzoi
└─ Protein, not DNA → fair-esm2 / esmfold2
Remote compute
7B/40B inference is GPU-bound (≥24 GB / 80 GB VRAM). Read
compute_details({provider, mode:'read'}) for an environment with evo2 +
flash-attn and a pre-cached HF weight mount, then submit:
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.
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.
- 1mo ago First seen · 154 lines · 83 tokens per session scan A fe8268806919
evo2 is a skill published in the GitHub repository UnicomAI/wanwu (2,375 stars, last pushed 4d ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,482 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to evo2, differing in 68 lines, and is treated as a copy.
Other skills, from other repositories
molecular-rag
Retrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. Based on MolRAG (Xian 2025, ACL).
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.
video_action_recognition
Technical guidance for recognizing human actions in video without training a new machine-learning model or using an LLM. It describes a pipeline that samples video frames, estimates body poses, measures movement, and assigns labels with rules.
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 14 skills: Dify, LangChain, LlamaIndex, Ollama, Transformers, Hermes Agent, OpenClaw, OpenCode, Pi, DocuTranslate, DeepSeek Harness and more.
ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.
ai-ml
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.