suede-creator-skills
★ 125
vs
cockpit-agent
★ 26
suede-creator-skills vs cockpit-agent
suede-creator-skills: Suede Creator Skills is a comprehensive, MIT-licensed toolkit featuring 67 public skill folders for Claude Code and OpenAI Codex, enabling agents to execute broad outcomes and orchestrate complex workflows. It provides capabilities for multi-agent team coordination, parallel worker fleets, code review with grading, and AI evaluation artifact generation.; cockpit-agent: Cockpit Agent is an edge-cloud collaborative AI agent system designed for smart cockpits, providing a single voice entry point for diverse tasks from millisecond-level vehicle control to multi-day trip planning and deep research. It emphasizes a separation of planning and execution, with LLMs handling understanding and planning while deterministic systems ensure safe and real-time execution of critical functions.
01
TL;DR
suede-creator-skillsMulti-Agent · ★ 125
Automate the full delivery of a release across coding, documentation, CI, and live verification with comprehensive agent coordination.
cockpit-agentMulti-Agent · ★ 26
Context-aware Navigation: Planning complex routes with multiple waypoints, real-time ETA, and dynamic re-routing based on ongoing navigation (e.g., "add a gas station, don't be late").
02
Side-by-Side Comparison
Field
suede-creator-skillscockpit-agentCategory
Multi-Agent
Multi-Agent
Stars
★ 125
★ 26
License
MIT
Apache-2.0
Install Command
git clone https://github.com/JasonColapietro/suede-creator-skills.git && bash suede-creator-skills/install.sh
cp .env.example .env && make proto && make up
Updated
1d ago
4d ago
Open Source
Yes
Yes
Tags
AI Agents, Workflow Automation, Code Review
Multi-Agent System, Smart Cockpit AI, Edge-Cloud Computing
03
Features
suede-creator-skills01Agent Orchestration: Coordinate complex changes across agent lanes with WIP collision detection, RFC mode, rollback trees, and a handoff checklist requiring evidence.
02Codex Worker Fleets: Orchestrate Claude to decompose high-volume jobs, spawn parallel OpenAI Codex CLI workers, and review outputs against acceptance criteria before shipping.
03Code Review & Ship Grade: Conduct deep code findings across multiple lanes and assign an A-F ship grade, including instant-F triggers for critical issues.
04AI Evaluation: Generate AI-SPEC artifacts, failure-mode rubrics, eval cases, and acceptance gates for various AI surfaces like LLMs, RAG, and classifiers.
cockpit-agent01Planning and Execution Separation: LLMs only produce intent/plans, while deterministic executors handle vehicle control with permission validation, ensuring safety.
02Fast/Slow Dual System Architecture: High-frequency, safety-critical commands execute on the edge with millisecond response times and offline availability; complex, cross-domain intents are orchestrated by the cloud LLM Planner.
03Agent Plug-and-Play: New domain agents can be added without modifying core orchestration code, leveraging a unified gRPC contract and Manifest declarations.
04Real Data Priority & Traceability: Integrates with real data sources (e.g., Gaode, Exa, Tushare), rejects mock data in strict mode, and provides source traceability for external data.
05Full-duplex Voice Interaction: Supports a complete streaming voice interaction loop, including KWS, VAD, real-time ASR/TTS, barge-in, and continuous dialogue.
04
Use Cases
suede-creator-skills↳Automate the full delivery of a release across coding, documentation, CI, and live verification with comprehensive agent coordination.
↳Perform an A-F graded code review on staged changes, checking correctness, security, data, UX, tests, and deployment readiness.
↳Decompose a high-volume development job and distribute it among parallel OpenAI Codex CLI workers for efficient, reviewed execution.
↳Design AI evaluation frameworks, failure-mode rubrics, and test cases for LLMs, RAG systems, and other classifier surfaces.
↳Convert a website into an App Store-ready iOS app or build a native Android app from keywords to Play Store launch.
cockpit-agent↳Context-aware Navigation: Planning complex routes with multiple waypoints, real-time ETA, and dynamic re-routing based on ongoing navigation (e.g., "add a gas station, don't be late").
↳Personalized Long-term Memory: The system remembers user preferences (e.g., "wife likes Cantonese food") and applies them to future queries, directly influencing search results rather than just conversational fillers.
↳Mixed Multi-Intent Handling: Simultaneously executing local vehicle controls (e.g., "turn on AC, play music") and sending slower, complex intents to the cloud for parallel processing within a single request.
↳Asynchronous Deep Research: Initiating multi-perspective, iterative background research tasks (e.g., "research solid-state battery progress"), with progress tracking and proactive, referenced reports.
↳Dynamic Scene Creation & Automation: Creating custom car scenarios with natural language (e.g., "create fishing mode: recline seats, dim ambient light"), where LLM compiles during creation, and activation/execution are deterministic.
FAQ
FAQ
What is the difference between suede-creator-skills and cockpit-agent?
Both suede-creator-skills and cockpit-agent are in the Multi-Agent category. suede-creator-skills has 125 stars, while cockpit-agent has 26 stars.
Which is better, suede-creator-skills or cockpit-agent?
The best choice depends on your use case. Choose suede-creator-skills if Automate the full delivery of a release across coding, documentation, CI, and live verification with comprehensive agent coordination., and cockpit-agent if Context-aware Navigation: Planning complex routes with multiple waypoints, real-time ETA, and dynamic re-routing based on ongoing navigation (e.g., "add a gas station, don't be late")..
Is suede-creator-skills free or open source?
Yes, suede-creator-skills is open source on GitHub (MIT).
Is cockpit-agent free or open source?
Yes, cockpit-agent is open source on GitHub (Apache-2.0).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→