🧬 MoleCode

An LLM-native, graph-explicit molecular language

Official repository for MoleCode unlocks structural intelligence in large language models.

Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly. Instead of making language models reconstruct molecular structure from cryptic strings, MoleCode lets them read, write, and edit directly on the structures.

English | 中文

Try our latest products on the official website!

Please visit the AtomFlow website.

What is MoleCode?

A molecule is a graph: atoms are nodes, bonds are edges, and chemistry emerges from the topology. Yet large language models are almost always fed molecules as linear strings like SMILES, where the graph is implicit — connectivity is positional, branches are syntactic, and rings hide inside index digits. Before an LLM can do any chemistry, it must first reconstruct the graph from the syntax, spending reasoning budget on structural bookkeeping.

MoleCode makes the structure the language. Every atom and bond is written as a typed declaration with a persistent identifier, serialized as a Mermaid graph. Topology becomes directly readable, editable, and auditable inside the context window — and the format is deterministically and losslessly inter-convertible with SMILES / MOL via RDKit (no learned model, no information loss).

graph TB
    subgraph chlorophenol["para-chlorophenol"]
        chlorophenol_C_1[C]
        chlorophenol_O_1[OH]
        chlorophenol_C_2[CH]
        chlorophenol_C_3[CH]
        chlorophenol_C_4[C]
        chlorophenol_Cl_1[Cl]
        chlorophenol_C_5[CH]
        chlorophenol_C_6[CH]
        chlorophenol_C_1 === chlorophenol_C_2
        chlorophenol_C_2 --- chlorophenol_C_3
        chlorophenol_C_3 === chlorophenol_C_4
        chlorophenol_C_4 --- chlorophenol_C_5
        chlorophenol_C_5 === chlorophenol_C_6
        chlorophenol_C_6 --- chlorophenol_C_1
        chlorophenol_C_1 --- chlorophenol_O_1
        chlorophenol_C_4 --- chlorophenol_Cl_1
    end

The same Subgraph → Node → Edge grammar covers small molecules, polymers, and Markush structures — and extends to reaction mechanisms and multimodal document parsing.

Why it matters

Empirically (see the MoleCode paper and docs/06-why-it-works.md):

• Generalization, not memorization. SMILES accuracy collapses from ~42% on familiar molecules to ~20% on novel ones; MoleCode holds ~76–80% across all familiarity tiers.
• Cheaper reasoning. MoleCode has longer input but its chain-of-thought grows sub-linearly with molecule size (~C^0.52) versus SMILES' super-linear ~C^1.65 — about a 5× lower total token cost per query.
• Scales to big, repetitive objects. Full-chain SMILES accuracy falls toward 0% as polymer chains grow; MoleCode stays flat.
• Markush understanding jumps from 38.1% → 84.0%.

Install

pip install molecode          # from PyPI — pulls in rdkit + networkx

Or from source (for the examples, the Agent Skill, and development):

git clone https://github.com/AtomFlow-AI/MoleCode.git
cd MoleCode
pip install -e .

pip install molecode gives you the library (molecode.molecule, molecode.polymer, molecode.markush, molecode.prompts, molecode.llm). The runnable examples/ and the Agent Skill live in the repository. Full API reference → docs/api.md.

Quick start

from rdkit import Chem
from molecode import mol_to_mermaid, mermaid_to_mol, mol_to_smiles

# SMILES  ->  MoleCode graph
graph = mol_to_mermaid(Chem.MolFromSmiles("CC(=O)Oc1ccccc1C(=O)O"), name="Aspirin")
print(graph)

# MoleCode graph  ->  SMILES  (lossless round-trip)
assert mol_to_smiles(mermaid_to_mol(graph)) == Chem.CanonSmiles("CC(=O)Oc1ccccc1C(=O)O")

Works with your coding agent (Claude Code · Codex)

MoleCode ships as a ready-to-use Agent Skill, so coding agents can clone this repo and immediately reason over and edit molecules at the explicit-graph level — no extra setup, no MCP server required.

Instead of asking the model to hand-write SMILES — error-prone for anything non-trivial — the skill has it convert → inspect the named atoms/bonds → edit the graph → validate, all through one stable CLI:

python .claude/skills/molecode/scripts/molecode_convert.py doctor
python .claude/skills/molecode/scripts/molecode_convert.py smiles-to-molecode "CCO" --name Ethanol
python .claude/skills/molecode/scripts/molecode_convert.py validate --input edited.mmd     # formula, counts, round-trip
python .claude/skills/molecode/scripts/molecode_convert.py molecode-to-smiles --input edited.mmd

The skill bundles the six conversion forms (SMILES / PSMILES / Markush ↔ MoleCode) plus validate, compare (Markush-aware isomorphism) and doctor, a syntax reference for hand-editing graphs, and a file-based edit workflow built for large molecules. See .claude/skills/molecode/SKILL.md.

Three domains, one grammar

🧪 Small molecules — molecode.molecule

Atoms are prefix_Element_Number[Label] nodes; bonds are --- (single), === (double), -.- (triple), with ===|E|/===|Z| and _R/_S for stereochemistry. → syntax reference

🔗 Polymers — molecode.polymer

The repeat unit stays explicit as a subgraph carrying a symbolic ×n count, with TL/TR terminus markers — so the graph does not blow up with chain length. → polymer docs

from molecode.polymer import polymer_to_mermaid, mermaid_to_psmiles

graph = polymer_to_mermaid("*NCCCCCC(=O)*", n=8, name="Nylon-6")   # PSMILES -> graph
mermaid_to_psmiles(graph)                                          # -> '*NCCCCCC(=O)*'

🧩 Markush structures — molecode.markush

Variable R-groups and named substituents become abbreviation nodes in curly braces — {R1}, {Boc}, {Ar} — something plain SMILES cannot express. A built-in graph-isomorphism comparator scores predictions up to abbreviation expansion. → Markush docs

graph TB
    subgraph Mol["molecule name"]
        Mol_C_1[C]
        Mol_O_1[OH]
        Mol_X_1{Boc}
        Mol_X_2{R1}
        Mol_C_1 --- Mol_O_1
        Mol_C_1 --- Mol_X_1
    end

Run the tasks: understand · generate · edit · reason

MoleCode is a drop-in representation for any LLM — feed the grammar as a system prompt, hand the model a graph, and validate its output deterministically. The examples/ folder has runnable scripts for all four task families (they run offline by default, printing the exact prompt; set MOLECODE_API_KEY to call a model):

python examples/01_molecule_roundtrip.py   # SMILES <-> graph (lossless)
python examples/02_polymer_roundtrip.py    # polymers with ×n
python examples/03_markush_roundtrip.py    # abbreviation nodes & isomorphism
python examples/04_understanding.py        # count atoms / formula / rings ...
python examples/05_generation.py           # de novo design under constraints
python examples/06_editing.py              # local graph edits (add/del/substitute)
python examples/07_reasoning.py            # reaction-product prediction
python examples/08_image_to_molecode.py    # OCSR: molecule image -> MoleCode (vision model)

The reusable ingredients: