Skip to main content

Faraday research agent

Project description

Faraday Agent

PyPI version License: Apache 2.0

Accelerating science with agentic AI for research and drug design

Faraday is an AI scientist that carries out research workflows end to end:

Install

pip install faradayai

Credentials

Set a model API key before running. Faraday supports OpenAI, OpenRouter, and Azure OpenAI.

OpenAI (default)

export OPENAI_API_KEY=...

OpenRouter

export OPENROUTER_API_KEY=...
# faraday.yaml
llm:
  provider: openrouter
  model: openai/gpt-5
  api_key_env: OPENROUTER_API_KEY

Azure OpenAI

# faraday.yaml
llm:
  provider: azure
  model: gpt-5
  api_key: OPENAI_API_KEY
  base_url: AZURE_OPENAI_BASE_URL
  api_version: preview

Run faraday --check-tools to verify keys and tool availability after setup.


Quickstart

Run a one-shot task:

faraday "Summarize structure–activity relationships across KRAS inhibitors, focusing on motifs that improve binding affinity and selectivity"

Interactive mode:

faraday

With a config file:

faraday --config faraday.example.yaml "Your task here"

Results are written to ./run_outputs/ by default:

run_outputs/
  run_{timestamp}_{chat_id}_{query_id}/
    agent_outputs/       # files, plots, and generated artifacts
    run_artifacts/
      events.jsonl       # timestamped stream of every agent event
      metadata.json      # run parameters (model, steps, config)
      result.json        # final answer and run summary
      trajectory.json    # full trajectory for replay

Useful flags: --model, --max-steps, --debug, --check-tools, --app-mode, --sandbox-backend, --batch-file, --use-docker. See faraday --help for the full list.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

faradayai-0.1.41.tar.gz (161.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

faradayai-0.1.41-py3-none-any.whl (188.2 kB view details)

Uploaded Python 3

File details

Details for the file faradayai-0.1.41.tar.gz.

File metadata

  • Download URL: faradayai-0.1.41.tar.gz
  • Upload date:
  • Size: 161.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for faradayai-0.1.41.tar.gz
Algorithm Hash digest
SHA256 485005416b722ed0743ec8c96492d1174a18eb76c7964e01ef09a01e81eed73a
MD5 f1af5430556a0a7eb5bec4260dc31118
BLAKE2b-256 f9411b88c03a84e769b89d27ec568ab3dcefcf453efe76058b5323b4ccd38b62

See more details on using hashes here.

Provenance

The following attestation bundles were made for faradayai-0.1.41.tar.gz:

Publisher: publish.yml on AscentBio/faraday

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file faradayai-0.1.41-py3-none-any.whl.

File metadata

  • Download URL: faradayai-0.1.41-py3-none-any.whl
  • Upload date:
  • Size: 188.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for faradayai-0.1.41-py3-none-any.whl
Algorithm Hash digest
SHA256 7286fc62f7798713ac779a2c8c39d74cd2a0a502ea5e383c0b3fd07bcfe85bb4
MD5 5a96c8f17fd154a30b222133d33fff4b
BLAKE2b-256 485479a991943de5fc30cf56d08c2b7e0122e81f23b9fce7db332647723c4b92

See more details on using hashes here.

Provenance

The following attestation bundles were made for faradayai-0.1.41-py3-none-any.whl:

Publisher: publish.yml on AscentBio/faraday

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page