Principia  by pzqpzq

AI research system for traceable, evidence-grounded ideas

Created 2 months ago
416 stars

Top 70.0% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

Principia is a local-first research system transforming literature into reusable principles and composing them into traceable research ideas, with tools to inspect their validity. It targets AI researchers and students seeking enhanced idea provenance and a structured, evidence-grounded ideation workflow.

How It Works

Principia employs a "principle-first" workflow: research goals -> literature retrieval -> structured feature extraction (ideas, principles, takeaways) -> evidence selection -> idea generation. It offers a Python framework (principia-ai) for programmatic integration and a local browser-based Visual Workbench. Key is Principia Calculus, a symbolic generation mode building intermediate structures, making ideation inspectable, editable, and reusable, surpassing typical black-box brainstorming.

Quick Start & Requirements

  • V1.3 Framework (PyPI): Install via pip install principia-ai. Requires Python 3.10+ and LLM API keys (e.g., OpenAI, SiliconFlow). Notebook integration needs ipykernel.
  • Visual Workbench: Clone repo, pip install -r requirements.txt, configure LLM keys in .env, run python3.12 principia.py serve. Access at http://127.0.0.1:8795/. Python 3.12 recommended.
  • Source Development: Clone repo, cd Principia/Principia-v1.3, pip install -e ".[dev]".
  • Links: Framework Tutorial: Principia-v1.3/examples/principia_v13_tutorial.ipynb.

Highlighted Details

  • Principia Calculus: Symbolic generation mode for inspectable, editable, and reusable idea construction.
  • Cloud Library: Optional GitHub-native shared memory for caching research artifacts, reducing redundant LLM calls.
  • Evidence-Aware Generation: Explicit user selection of source evidence grounds idea generation.
  • Local-First Design: Prioritizes privacy; research state remains local unless explicitly synced.
  • Research Memory Compounding: Workspaces build a reusable knowledge base over time.

Maintenance & Community

Collaboration noted with the Institute of Computing Technology, CAS, and Beijing Chipflow Technology Co., Ltd. Contact details provided for collaboration. No explicit community channels or contributor details are listed.

Licensing & Compatibility

The repository's README does not specify a software license. This omission requires clarification for adoption, especially concerning commercial use.

Limitations & Caveats

Core functionality relies on configured external LLMs via API keys. V1.3 focuses on framework capabilities. The absence of a stated license is a significant adoption blocker.

Health Check
Last Commit

2 days ago

Responsiveness

Inactive

Pull Requests (30d)
1
Issues (30d)
0
Star History
4 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.