Skip to main content

dfm — Developer Foundation Model

CI License: MIT Platform: macOS on Apple Silicon Python 3.12+

A coding agent that runs entirely on your Mac. DFM edits, builds, tests, repairs and verifies code using on-device models: Apple FM for routing and short text, and a local MLX model for code. Repository knowledge comes from RepoCanon, RepoKG and, optionally, Reflex.

DFM sends no code or prompts to hosted models. Other network access (GitHub, package registries) is off or requires approval, per policy.

Status: early (0.0.1). Commands and configuration may change.

Requirements

  • macOS on Apple Silicon, Python 3.12+, uv, Git.
  • Memory for the local model: the recommended 27B model (4-bit) needs about 18.5 GB at its default context, so 32 GB or more is recommended. dfm setup picks a model that fits.
  • Optional: Apple Intelligence, for Apple FM.

Quick start

Install dfm as a command (the package is dfm-agent; the command is dfm):

uv tool install "dfm-agent[mlx]"           # from PyPI, once released
uv tool install "git+https://github.com/NehharShah/dfm[mlx]"   # or straight from GitHub
dfm doctor                                 # check this machine
dfm setup                                  # choose a local model
dfm implement "fix the failing test"

Omit [mlx] to install without the local coder. Upgrade with uv tool upgrade dfm-agent. To run from a checkout instead, see CONTRIBUTING.md.

How it works

  • The model proposes one action at a time (read, search, patch, run, test). DFM executes it, reruns the tests after every edit, and reports only what a command verified.
  • Every command is classified and checked against policy, then runs in a per-command macOS sandbox. Destructive, production and mainnet actions require a typed confirmation. DFM does not commit, push or rewrite history.
  • Repository files, issues and CI logs reach the model as untrusted data, with secrets redacted.
  • Memory checks, thermal pacing, reasoning budgets and a persistent prompt cache keep the model usable alongside other apps.

Modes: ask, plan, implement, review, security-review, ci, fix-pr, implement-issue, benchmark. Full list: command reference.

Documentation

Guide · Architecture · Commands · Configuration · Policy · Threat model · Troubleshooting · Design decisions

Contributing and security

See CONTRIBUTING.md and AGENTS.md. Report vulnerabilities privately as described in SECURITY.md. Changes: CHANGELOG.md.

License and notices

DFM is released under the MIT License and is provided "as is", without warranty of any kind. DFM runs commands and changes files on your machine. Its safeguards reduce risk but do not eliminate it. Review its changes before you commit them.

Models are third-party software under their own licenses, and you are responsible for complying with the license of any model you download. RepoCanon, RepoKG and Reflex are separate projects under their own licenses.

Apple, Apple Intelligence, Apple Silicon and macOS are trademarks of Apple Inc. DFM is an independent project and is not affiliated with or endorsed by Apple.

Metadata

Release files for dfm-agent 0.0.1

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

Source distribution (sdist)

Source distribution for dfm-agent 0.0.1
File Size Uploaded Provenance Actions
dfm_agent-0.0.1.tar.gz 271.3 kB With provenance Details for dfm_agent-0.0.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for dfm-agent 0.0.1
File Interpreter ABI Platform Actions
dfm_agent-0.0.1-py3-none-any.whl Python 3 none any Details for dfm_agent-0.0.1-py3-none-any.whl

Total release size: 617.5 kB

Release files / dfm_agent-0.0.1.tar.gz

Download URL dfm_agent-0.0.1.tar.gz
Size 271.3 kB
Tags Source
SHA-256 checksum
How to use checksums
95c83de75985ad233acdd03d660eacdadddb6b2ddd2386f2beec76df820bf331
BLAKE2b-256 checksum
How to use checksums
15f0b13ae558a9bf9ad0eea0c06eee4643914a95a2e6496ffbc8c2337638c919
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 31, 2026.

Transparency log

Release files / dfm_agent-0.0.1-py3-none-any.whl

Download URL dfm_agent-0.0.1-py3-none-any.whl
Size 346.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
de22c43e3506a157851827266ab78a4abcff0cc1f0f0ac59792de68b94ade4fa
BLAKE2b-256 checksum
How to use checksums
277d3fe8ce3cb2f231b0892bd6f47ec1b0444be34fac95cc86004991203d20df
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 31, 2026.

Transparency log

Security for dfm-agent 0.0.1

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.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for dfm_agent-0.0.1.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 31, 2026.

Transparency log

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