Skip to main content

FermiLink logo

Docs PyPI License Python arXiv:2604.03460

Write a goal.md for scientific simulations and more!

FermiLink reads a simple markdown file describing your scientific goal,
then autonomously runs multi-job multi-day simulations on your laptop or HPC clusters.


Key Features

Package Knowledge Base Manager

Use FermiLink to conveniently load package knowledge base to your local workspace; and then apply any local agent for interactive research.

fermilink install <pkg-id>
cd /path/to/workspace/
fermilink init <pkg-id>
# then try any agent 
codex 

Autonomous Scientific Simulations

Beyond interactive use, FermiLink can also sustain multi-task multi-day simulations on either your laptop or HPC.

fermilink loop goal.md          # long-running simulations on workstations or HPC
fermilink reproduce paper.tex   # reproduction of a full research paper
fermilink research goal.md      # full research-paper-scale, multi-task campaigns

Autonomous Code Optimization (beta)

Apply FermiLink to your existing scientific code with a performance goal. It iteratively modifies hot paths and runs deterministic benchmarks.

At the end of the day, it provides optimized scientific code with improved speed while preserving computational accuracy.

fermilink optimize goal.md      # iterative code with correctness guarantees

Quickstart

# 1. Install
pip install fermilink

# 2. Set up an AI agent (pick one)
fermilink agent codex        # or: claude, gemini, opencode

# 3. Install a scientific package knowledge base
fermilink install meep       # 150+ packages available

# 4. (Optional) Configure the default SLURM HPC profile
fermilink hpc

# 5. Write your goal.md (see example above), then run
fermilink loop goal.md

First time? Just run fermilink with no arguments. Then, an interactive setup wizard will walk you through everything.


Design principles

The key design principle of FermiLink is the segregation of package knowledge bases and simulation workflows.

design


Supported Workflows

FermiLink supports the following seven major commands for various simulation workflows:

Command Best for Duration Recommended Environment
exec Quick one-off simulations Minutes Laptop / workstation
chat Interactive conversation with agents Hours Laptop / workstation
loop Iterative jobs with PID/SLURM monitoring Hours -> days Workstation / HPC
reproduce Multi-task, paper-scale reproducation of papers Days -> weeks HPC clusters
research Multi-task, paper-scale research Days -> weeks HPC clusters
optimize Code performance tuning (beta) Hours Any
exploop Iterative experimental jobs with PID monitoring Hours -> days Workstation

Built-in Scientific Packages

FermiLink ships with 150+ knowledge bases for packages spanning multiple scientific domains. Install any of them with a single command:

fermilink install <package>       # e.g., meep, lammps, pyscf, openfoam
fermilink list                    # see all installed packages

Don't see your package? Compile your own local knowledge base:

fermilink compile /path/to/your/code

Browse the full package list →


Interaction surfaces

FermiLink isn't just a CLI tool. Pick the interface that fits you:

  • Command line — fermilink exec/loop/reproduce/research/optimize goal.md for headless, scriptable autonomy
  • Web UI — fermilink start launches a ChatGPT-style browser interface for interactive sessions
  • Telegram bot — fermilink gateway connects to Telegram so you can run and monitor HPC jobs from your phone

Documentation

Resource Link
Full documentation fermilink.org
Installation guide fermilink.org/installation
Laptop tutorial fermilink.org/tutorial_laptop
HPC tutorial fermilink.org/tutorial_hpc

Citation

If FermiLink is useful in your research, please cite:

  • Gang Meng†, Andres Felipe Bocanegra Vargas†, Xinwei Ji†, Federico Garcia-Gaitan, Felipe Reyes-Osorio, Jalil Varela-Manjarres, Yafei Ren, Mohammadhasan Dinpajooh, Branislav K. Nikolić, Tao E. Li. FermiLink: A Unified Agent Framework for Multidomain Autonomous Scientific Simulations. arXiv:2604.03460 (2026).

Contributing

We welcome contributions, from bug reports to new package knowledge bases. See CONTRIBUTING →


License

AGPL-3.0

Metadata

Release files for fermilink 0.3.10

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for fermilink 0.3.10
File Size Uploaded Provenance
fermilink-0.3.10.tar.gz 1.2 MB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for fermilink 0.3.10
File Interpreter ABI Platform
fermilink-0.3.10-py3-none-any.whl Python 3 none any Details

Total release size: 3.7 MB

Security for fermilink 0.3.10

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page