OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Drugclaw

DrugClaw is a Python command-line agent runtime that uses agentic retrieval and reasoning to answer drug-information questions with structured, source-attributed evidence.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Drugclaw — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use DrugClaw for focused drug-information research when a command-line workflow and source-attributed, structured findings are useful.

Who it is for

  • Researchers investigating drug targets, mechanisms, indications, or repurposing evidence
  • Users examining drug safety, adverse reactions, or drug–drug interactions
  • Users researching pharmacogenomics or drug labeling

Documented uses

  • Retrieve evidence about a drug’s targets and mechanisms
  • Investigate indications and drug-repurposing evidence
  • Look up safety risks, serious adverse reactions, and drug interactions
  • Explore pharmacogenomic factors and labeling information
Before you choose

Requirements & limits

The documented primary workflow runs through a CLI and requires an API key, base URL, and model in its configuration.

  • DrugClaw is a Python CLI and agent runtime, not a general chat assistant.
  • Minimal mode supports basic queries with the repository’s minimal resource metadata.
  • The fuller local-resource mode is intended to expand local evidence coverage; the README says its resource bundle will be released upon paper acceptance.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install DrugClaw and run a drug-information query

Set up the documented minimal CLI workflow and submit a drug-focused question.

Before you start

  • Python environment with the project dependencies installed
  • API key, base URL, and model details for the API configuration

Steps

  1. Clone the DrugClaw repository and change into its directory.

  2. Install the project with the command below.

    Documented command
    pip install -e .

  3. Create api_keys.json at the repository root with api_key, base_url, and model fields, or specify another configuration path with --key-file.

  4. Run the command below to check whether the setup looks usable.

    Documented command
    python -m drugclaw doctor

  5. Submit a question with the command below.

    Documented command
    python -m drugclaw run --query "What are the known drug targets of imatinib?"

Expected outcome

A CLI response to a drug-focused question using the minimal setup.

Guide limitations

  • The API configuration requires credentials and provider details.
  • The documented minimal mode uses the tracked minimal resource metadata; broader local evidence coverage depends on the separate full resource bundle.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
QSong-github/DrugClaw · Official homepage title · retained in its source language
How we review sourcesSuggest a correction