OpenAI4S

Open AI for Scientist

💸 Replicating Claude Science in two cuts or less

An open-source, Code-as-Action scientific research agent.
_{The model's action space is a Turing-complete kernel — not a fixed tool schema.}

English · 简体中文

[!TIP] Why "two cuts"? No pricey frontier-model key needed — OpenAI4S runs on Doubao (豆包) via the cheapest "Small" plan on Volcengine Ark (火山方舟): ¥9.9 / month (≈ US$1.4). Pick the ark provider in the UI and you get a Claude-Science-class agent for less than a cup of coffee.

_{Volcengine Ark · Agent Plan (Personal) — the entry Small tier is ¥9.9 / month.}

🧬 Code-as-Action, not ReAct

Most "AI agents" are ReAct + tool_use: each step the model emits one tool_use JSON, the host runs that single tool, and the loop repeats — the action space is a fixed menu. OpenAI4S instead emits a cell of real Python/R code that runs in a persistent kernel; every "tool" is a plain function on an in-kernel host object. The action space is a Turing-complete language — one turn can loop, branch, and call libraries while big objects stay resident in kernel memory.

# ReAct: ~14 round-trips (read → … → filter → sort → plot).   OpenAI4S: one code cell.
hits   = [f for f in files if pattern in host.read_file(f)]
top3   = sorted(hits, key=os.path.getsize, reverse=True)[:3]
frames = [pd.read_csv(f) for f in top3]      # a 100k-row DataFrame stays in the kernel...
host.save_artifact(plot(frames))             # ...only "<DataFrame 100000×20>" hits context

📣 News

• 2026-07-06 🎉 Open-sourced — the pure-stdlib Code-as-Action engine, the scientific web app, 24 science Skills, and BYOC remote compute.

😮 Highlights

• 🧬 Code-as-Action engine — a Jupyter-style persistent kernel is the action space. Namespace persists across cells; big objects stay resident, only summaries hit context.
• 🐍 Pure-stdlib core — the engine and the web server are stdlib-only (http.server + hand-rolled WebSocket, no framework, no deps). The LLM client speaks OpenAI / Anthropic / Gemini over urllib alone.
• 🔌 One-line multi-provider — ark (doubao · glm · kimi · deepseek · minimax) plus official chatgpt · claude · gemini, behind a single host.llm; switch from the UI.
• 🖥️ Full scientific web app — live streaming turns, versioned artifacts (with a built-in 3Dmol viewer for .pdb/.cif), a live Notebook sharing the agent's kernel, background & resume.
• 🔬 24 bundled Skills — 14 GPU/model science Skills (AlphaFold2 · ESMFold2 · Boltz · Chai-1 · OpenFold3 · ProteinMPNN · ESM-2 · Evo2 · Borzoi · scGPT · scVI · DiffDock …) + research-workflow Skills. Skills are recipes of code, not JSON schemas.
• ☁️ BYOC remote compute — dispatch GPU jobs to your own machines via ssh:<alias> or the bundled NVIDIA NIM provider; real host.fold (single-sequence Protenix / AF3-class) under a strict no-fabrication policy.

🎬 Demo

Live API workflow — from UniProt / RCSB to a 3D structure & report	Real-data analysis — human insulin INS (P01308): from UniProt / RCSB to a reproducible report
Visual artifact editing — “raise the confidence cutoff to 75” in one line	Annotation-driven chart editing — lasso a region & recolor the legend
Plan-mode research — artemisinin & paclitaxel solubility prediction	Protein engineering — from sequence to ranked mutants & structural rationale

⚡ Quickstart

git clone https://github.com/PKU-YuanGroup/OpenAI4S && cd OpenAI4S
./setup.sh     # one-time: build the environment with uv
./start.sh     # launch the web UI at http://127.0.0.1:8760/

setup.sh creates the .venv with uv; start.sh launches the daemon + web UI from it. No API key is needed to boot — set your model in the UI (Customize → Models). One-shot without the UI: uv run openai4s run "Compute the mean of [4,8,15,16,23,42] and submit it." -v.

📚 Documentation

🗺️ Roadmap

• OS-level sandbox parity (Seatbelt / bubblewrap + seccomp) for the local kernel.
• Keyless web_search beyond DuckDuckGo (rate-limit resilience).
• More BYOC providers (Modal / SLURM) beyond SSH + NVIDIA NIM.
• A public benchmark of end-to-end scientific workflows.
• Local GPU model serving so structure/design Skills run without remote compute.

💡 Contributing

OpenAI4S is a community effort to keep the Code-as-Action paradigm open.

Development setup

Requires Python ≥ 3.10 and uv.

git clone https://github.com/PKU-YuanGroup/OpenAI4S && cd OpenAI4S
./setup.sh                          # uv sync --extra science + pre-commit hook
uv run pytest                       # offline test suite (LLM mocked)
uv run pre-commit run --all-files   # format + lint everything

Style is enforced by pre-commit — black, isort (--profile black), and ruff, pinned in .pre-commit-config.yaml. Runtime deps: the core is zero-dependency (pure stdlib); the optional science extra pins numpy>=1.24 · pandas>=2.0 · matplotlib>=3.7.

What we welcome

• New Skills — a SKILL.md (+ optional kernel.py) under skills/ — recipes of code, not schemas.
• New providers — a wire adapter in openai4s/llm.py, or a BYOC compute provider.
• Engine & UI — the core is pure stdlib and readable; the web app is framework-free.

Keep the core dependency-free, guard optional science imports behind try/except ImportError, and make sure uv run pytest and uv run pre-commit run --all-files pass before opening a PR.

👍 Acknowledgement & related work

• Claude Science (Anthropic) — the closed reference architecture whose Code-as-Action design, persistent kernel, host-RPC protocol, and safety layers OpenAI4S independently reproduces in open source.
• CodeAct — "Executable Code Actions Elicit Better LLM Agents" — code as a unified action interface.
• ReAct — "Synergizing Reasoning and Acting in Language Models" — the tool_use baseline this project departs from.
• The science Skills stand on ColabFold / AlphaFold, ESM, OpenFold, Boltz, Chai, ProteinMPNN, DiffDock, Evo2, Borzoi, scGPT, scVI-tools and open data services (NCBI, UniProt, RCSB PDB, EBI, OpenAlex, Crossref).

🔒 License

Released under the MIT License — see LICENSE.

✨ Star history

✏️ Citing

@software{openai4s2026,
  title  = {OpenAI4S: An Open-Source Code-as-Action Scientific Research Agent},
  author = {OpenAI4S contributors},
  year   = {2026},
  url    = {https://github.com/PKU-YuanGroup/OpenAI4S},
  note   = {Open AI for Scientist — a pure-stdlib reproduction of the Code-as-Action paradigm}
}

🤝 Community contributors