nasa-petal/bidara

BIDARA is a GPT-4 chatbot that was instructed to help scientists and engineers understand, learn from, and emulate the strategies used by living things to create sustainable designs and technologies using the Biomimicry Institute's step-by-step design process.

BIDARA – Bio‑Inspired Design and Research Assistant

What it is – BIDARA is a GPT‑4‑powered chatbot that helps scientists, engineers, and designers work through the Biomimicry Institute’s Design Process. It guides users step‑by‑step from defining a problem to abstracting biological strategies and turning them into design concepts.

Why it matters – Biomimicry is a proven way to create sustainable technologies by learning from nature. BIDARA packages the entire design workflow into an interactive AI assistant, making the process accessible to teams that may not have deep expertise in biology or biomimicry.

How it works

  • The bot runs on OpenAI’s GPT‑4 model and is given a long system prompt that defines its role, knowledge domains (biology, engineering, industrial design, etc.) and the exact sequence of steps it must follow.
  • At each step (Define, Biologize, Discover, Abstract, Emulate) it asks the user for input, provides guidance, and cites peer‑reviewed sources.
  • Users can run BIDARA on Discord, on a hosted web interface, or directly in a ChatGPT/OpenAI Playground session by copying the supplied system prompt.

Key features

  • Guided Biomimicry workflow – enforces the six‑step Biomimicry Design Process and forces frequent user check‑ins.
  • Citation of scientific literature – the prompt instructs the model to provide peer‑reviewed references for any biological information.
  • Multi‑modal output – encourages users to sketch biological and design strategies, list keywords, and create abstracted design concepts.
  • Deployment flexibility – available as a Discord bot, a web‑app (hosted at https://nasa-petal.github.io/bidara-deep-chat/), or a reusable system prompt for any OpenAI interface.

Getting started

  1. Discord – clone the repo, add your OPENAI_API_KEY, DISCORD_TOKEN, and optional SEMANTIC_SCHOLAR_API_KEY to a .env file, install the Python requirements, and run python3 bot.py.
  2. Web version – the repository nasa-petal/bidara-deep-chat contains the front‑end; follow its README for deployment.
  3. ChatGPT / Playground – paste the large system prompt (provided in the README) into the “System Prompt” field and start a conversation.

Technical stack

  • Language: Python 3.8+ for the Discord bot.
  • AI model: OpenAI GPT‑4 accessed via the OpenAI API.
  • Optional data source: Semantic Scholar API for literature lookup.
  • Hosting options: Local machine, AWS EC2 (with CloudFormation template provided), or any platform that can run a Python process.

Maintenance / updates

  • The README includes step‑by‑step instructions for updating the bot on an AWS EC2 instance (stop the screen session, pull changes, restart bot.py).
  • A separate repository hosts the web UI, which currently has more features than the Discord version.

Who should use it

  • Researchers and product developers interested in biomimetic solutions.
  • Educators teaching the Biomimicry Design Process.
  • Anyone with access to OpenAI’s API who wants a structured, AI‑driven facilitator for sustainable design.

All information above is taken directly from the project's README; no additional features have been inferred.

Related

  • Project
    HangYu8123/HarnessFlow

    HarnessFlow is a portable set of Markdown instruction files that turn Claude Code, Codex CLI, or GitHub Copilot into a multi‑step, self‑reviewing coding assistant. It provides request templates, parallel analysis agents, a devil’s‑advocate challenge, QA validation, and persistent repo memory. Install by copying the pack into `.github/HarnessFlow/` of your repo and running the provided `setup.sh` or `cli_setup.sh`. Choose a request template (code, refactor, debug, etc.), fill it in, and paste it to the assistant. The pack supports three workflow modes—`general`, `fast`, and `skill`—and reports benchmark gains (up to 76 % fewer generated lines while staying 100 % correct).

  • Project
    jim60105/docker-whisperX

    A collection of optimized Docker images for WhisperX, providing pre-bundled ASR models for fast and efficient speech-to-text transcription with word-level timestamps.

  • Project
    jacbz/Lofi

    A machine learning-supported lo-fi music generator that uses a VAE model to represent and generate musical tracks through feature vectors.

  • Project
    xpzouying/x-mcp

    X‑MCP is a Chrome extension that lets AI agents (Claude, Codex, etc.) control your browser to create and publish posts on Xiaohongshu via the Model Context Protocol (MCP). It requires no Python/Docker backend—just a token from aredink.com—making AI‑driven automation reachable for non‑technical creators.