Toolbox/Other harnesses/capgym/cap-x

capgym/cap-x

A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation

View on GitHub →

PythonMIT

Stars

656

Δ 7d

—

Δ 30d

—

Age

4 mo

Last push

55d ago

90-day star history

#24 of 49 in Other harnesses

Most-wanted open issues

Ranked by 👍 reactions. 5 open issues total, checked 2026-07-23.

Issue	👍	Comments	Opened
libero_object_task bddl files not present with current submodule version of LIBERO-PRO	0	1	1 mo
Behaviour not available; add submodule.	0	1	3 mo
Additional robot support: Stretch 3	0	0	2 mo
WebUI multi-turn feedback does not preserve chat history and can lose dynamic LIBERO task goal	0	0	1 mo
VDM (visual differencing) receives the full code-generation prompt as its task context, which makes code-capable VLMs emit code instead of a scene description	0	1	1 mo

Alternatives in Other harnesses

browser-use/video-use

Edit videos with coding agents

⭐17.6k

+6157d

Python

3 mo

bojieli/ai-agent-book

《深入理解 AI Agent：设计原理与工程实践》（李博杰著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

⭐17.5k

+16,4077d

Python

10 mo

GreyDGL/PentestGPT

Automated Penetration Testing Agentic Framework Powered by Large Language Models

⭐14.4k

+1567d

Python

3 yrs

SakanaAI/AI-Scientist

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

⭐14.3k

Jupyter Notebook

1 yr

wanshuiyin/Auto-claude-code-research-in-sleep

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model re…

⭐13.7k

Python

4 mo

SakanaAI/AI-Scientist-v2

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

⭐6.9k

Python

1 yr