MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
ai-vibecode-superpower
This repository provides cross-platform installers to deploy a standardized set of Codex agent rules, system command documentation, and reusable skills into the user's local Codex configuration directory, without installing Codex itself.
Stars
3
7-day growth
No data
Forks
0
Open issues
0
License
Apache-2.0
Last updated
2026-07-30
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It offers a safe, backup-supported, and conflict-preventive method to enforce consistent AI agent behavior across projects, while keeping authentication and concurrent installs secure.
Who it is for
- Codex CLI users seeking standardized agent behavior
- Developers integrating AI agents into their workflow
- Teams managing shared AI configuration across machines
- System administrators automating AI tool setup
Use cases
- Deploying a global set of AI agent rules and system command docs to all team members
- Installing pre-built skills like image generation and project documentation planning
- Restoring previous configuration after a failed or unsatisfactory update
- Ensuring consistent AI behavior across different operating systems
Strengths
- Cross-platform install scripts (PowerShell for Windows, POSIX shell for macOS/Linux)
- Automatic backup of existing AGENTS.md, docs, and skills before overwriting
- Concurrent installation prevention and rejection of symlinked paths (Windows)
- Clear separation of concerns: agent rules, system docs, and skills are organized in distinct directories
Considerations
- Requires a pre-existing Codex installation (not included in this repo)
- Installation completely overwrites the three target directories (backup provided, but no merge option)
- Only basic concurrent install protection; advanced locking or distributed deployment is left to the user
README quick start
安装
Related repositories
Similar projects matched by category, topics, and programming language.
lopopolo
Featured
harness-engineering
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.