Skip to main content

Faberon brain

The brain of Faberon, an autonomous ML research harness.

Give Faberon a research plan and it proposes experiments, submits training jobs (Slurm cluster or local machine), waits for results, judges them against your expectations, and decides what to try next. Every decision lands in an append-only Postgres ledger, and you can steer a running campaign at any time.

This package provides the brain: the durable agent loop (Pydantic AI + DBOS) behind a FastAPI HTTP API, plus the faberon CLI for operating campaigns from a shell. The chat interface ships separately as @faberon/chat.

Install

Requires Python 3.14 and a Postgres database.

uv pip install faberon
faberon serve

Documentation

Install guides, quickstart, runbooks, and design docs live in the repo.

Status

Early beta: expect rough edges and breaking changes.

License

MIT

Metadata

Release files for faberon 0.3.0

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

Source distribution (sdist)

Source distribution for faberon 0.3.0
File Size Uploaded Provenance
faberon-0.3.0.tar.gz 26.2 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for faberon 0.3.0
File Interpreter ABI Platform
faberon-0.3.0-py3-none-any.whl Python 3 none any Details

Total release size: 61.7 kB

Release files / faberon-0.3.0.tar.gz

Download URL faberon-0.3.0.tar.gz
Size 26.2 kB
Tags Source
SHA-256 checksum
How to use checksums
f679202893fc396814a77808dd0c863595be609d6df7a89304f23d200b4f6c4a
BLAKE2b-256 checksum
How to use checksums
ae49553c183ca2ad0d60b09bd1f31440f120bab32b886f6c6416bf95a2667957
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.13 {"installer":{"name":"uv","version":"0.12.13","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Fedora Linux","version":"44","id":"","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / faberon-0.3.0-py3-none-any.whl

Download URL faberon-0.3.0-py3-none-any.whl
Size 35.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
8456197526c91c5e4d477c998d281d0415c52888eeb50e5f67aed17cd723df92
BLAKE2b-256 checksum
How to use checksums
9245b838be2525e754f86d9d2694cfa6292e4b7dca4dca6d617258c2cbe7e9ff
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.13 {"installer":{"name":"uv","version":"0.12.13","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Fedora Linux","version":"44","id":"","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Security for faberon 0.3.0

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.

Release history Release notifications | RSS feed

This release

0.3.0 This release

2 release files No provenance

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