get-physics-done — Codex Skill by psi-oss

by psi-oss · Codex Skill · ★ 819

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

About get-physics-done

Get Physics Done (GPD) Built by physicists, for physicists Get Physics Done is an open-source AI copilot for physics research from Physical Superintelligence PBC (PSI), released as a community contribution. GPD helps turn a research question into a structured workflow: scope the problem, plan the work, derive results, verify them, and package the output. Quick Start · Supported Runtimes · Workflow · Commands · Models · Advanced CLI · System Requirements Who This Is For GPD is for hard physics research problems that cannot be handled reliably with manual prompting. It is designed for long-horizon projects that require rigorous verification, structured research memory, multi-step analytical work, complex numerical studies, and manuscri

agentic-aiclaudecodexgeminimeta-promptingopen-sourceopencodephysicsresearch

Quick Facts

Stars819
Forks122
LanguagePython
CategoryCodex Skill
Quality Score51.502/100
Open Issues31
Last Updated2026-06-05
Created2026-03-09
Platformsclaude-code, codex, gemini, python
Est. Tokens~1470k

Compatible Skills

These tools work well together with get-physics-done for enhanced workflows:

  • MakeMoneyWithAI — semantic(0.35)+complementary+same_lang+similar_pop+shared_platform (57%)
  • mcp-memory-service — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
  • flyto-core — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
  • af-deep-research — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (53%)
  • CQAsk — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (53%)

get-physics-done alternative? Top 6 similar tools

Looking for a get-physics-done alternative? If you're comparing get-physics-done with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • openpencil by ZSeven-W · ⭐ 3.4k

    The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. De

  • generative-ai by genieincodebottle · ⭐ 2.3k

    Comprehensive resources on Generative AI, including a detailed roadmap, projects, use cases, interview prepara

  • mcp-memory-service by doobidoo · ⭐ 1.9k

    Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowl

  • skillkit by rohitg00 · ⭐ 1.2k

    Supercharge AI coding agents with portable skills. Install, translate & share skills across Claude Code, Curso

  • awesome-llm-skills by Prat011 · ⭐ 1.1k

    A curated list of awesome LLM and AI Agent Skills, resources and tools for customising AI Agent workflows - th

  • agentsys by agent-sh · ⭐ 830

    AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCod

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is get-physics-done?

get-physics-done is The first open-source agentic AI physicist, by Physical Superintelligence PBC (PSI).. It is categorized as a Codex Skill with 819 GitHub stars.

What programming language is get-physics-done written in?

get-physics-done is primarily written in Python. It covers topics such as agentic-ai, claude, codex.

How do I install or use get-physics-done?

You can find installation instructions and usage details in the get-physics-done GitHub repository at github.com/psi-oss/get-physics-done. The project has 819 stars and 122 forks, indicating an active community.

What are the best alternatives to get-physics-done?

The top alternatives to get-physics-done on Agent Skills Hub include openpencil, generative-ai, mcp-memory-service. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

View on GitHub → Browse Codex Skill tools