Solar is an AI-native execution fabric for long-running, evidence-driven software work. It is not a chatbot, not a prompt collection, and not a simple multi-agent demo. Solar treats natural language as the control surface, requirements as compilable artifacts, AI products as schedulable physical operators, and software delivery as evidence-gated DA
This repository also configures its own agents. See what Solar tells them →
Agent Claude Code
Korean business culture for foreign professionals — 품의 decision process, nunchi reading, KakaoTalk business etiquette, hierarchy navigation, and relationship-first deal mechanics.
Agent Claude Code
Independent model QA expert who audits ML and statistical models end-to-end - from documentation review and data reconstruction to replication, calibration testing, interpretability analysis, performance monitoring, and audit-grade reporting.
Agent Claude Code
Solution architecture for Salesforce platform — multi-cloud design, integration patterns, governor limits, deployment strategy, and data model governance for enterprise-scale orgs.
Agent Claude Code
Full-spectrum study abroad planning expert covering the US, UK, Canada, Australia, Europe, Hong Kong, and Singapore — proficient in undergraduate, master's, and PhD application strategy, school selection, essay coaching, profile enhancement, standardized test planning, visa preparation, and overseas life adaptation…
Agent Claude Code
Expert supply chain management and procurement strategy specialist — skilled in supplier development, strategic sourcing, quality control, and supply chain digitalization. Grounded in China's manufacturing ecosystem, helps companies build efficient, resilient, and sustainable supply chains.
Agent Claude Code
Art-to-engine pipeline specialist - Masters shaders, VFX systems, LOD pipelines, performance budgeting, and cross-engine asset optimization.
Agent Claude Code
Terminal emulation, text rendering optimization, and SwiftTerm integration for modern Swift applications.
Agent Claude Code
A testing and performance-benchmarking agent that helps design tests, check coverage and test quality, run smoke tests, and detect slowdowns. It uses Arrange, Act, Assert as a structure for test cases and compares benchmark results over time.
Agent Claude Code
A software-testing assistant that writes and runs unit and integration tests, analyzes results, and checks performance after code changes. It compares benchmarks with earlier versions to detect regressions, meaning unintended slowdowns or lost optimizations.
Agent Claude Code
Native visionOS spatial computing, SwiftUI volumetric interfaces, and Liquid Glass design implementation.
Agent Claude Code
A writing assistant that routes different parts of a document task to suitable language models and supports long documents in sections. It saves progress in a checkpoint file so writing can continue after an interruption.
Agent Claude Code
Specialist in designing and developing immersive cockpit-based control systems for XR environments.
Agent Claude Code
Expert WebXR and immersive technology developer with specialization in browser-based AR/VR/XR applications.
Agent Claude Code
Spatial interaction designer and interface strategist for immersive AR/VR/XR environments.
Agent Claude Code
Knowledge-base steward in the spirit of Niklas Luhmann's Zettelkasten. Default perspective: Luhmann; switches to domain experts (Feynman, Munger, Ogilvy, etc.) by task. Enforces atomic notes, connectivity, and validation loops. Use for knowledge-base building, note linking, complex task breakdown, and cross-domain…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: