Rename to OpenAgents, remove model specs, and update documentation

Major Changes:
- Rename repository from opencode-agents to OpenAgents
- Remove all hardcoded model specifications (now model-agnostic)
- Fix documentation: profile names, component counts, add Business profile
- Add future plans note for other AI coding tools

Repository Rename:
- Update all URLs to github.com/darrenhinde/OpenAgents
- Update git remote, README, install scripts, documentation
- 15 files updated with new repository name

Model-Agnostic Framework:
- Remove model specifications from 6 agent files
- Framework now works with any AI provider (Claude, GPT, Gemini, local models)
- Users control model selection via OpenCode CLI settings

Documentation Fixes:
- Correct profile name: Core → Essential
- Add missing Business profile documentation
- Fix component counts: Developer (19), Advanced (32)
- Document all 5 profiles with accurate descriptions

Future Plans:
- Add note about support for other AI tools (Cursor, Claude Code, etc.)
- Clear focus on stabilizing OpenCode integration first

This makes OpenAgents a truly universal, model-agnostic framework
accessible to all users regardless of their AI provider preference.

.opencode/agent/openagent.md

@@ -1,7 +1,6 @@
 ---
 description: "Universal agent for answering queries, executing tasks, and coordinating workflows across any domain"
 mode: primary
-model: claude-4-sonnet
 temperature: 0.2
 tools:
   read: true

.opencode/agent/subagents/code/build-agent.md

@@ -2,7 +2,6 @@
 
 description: "Type check and build validation agent"
 mode: subagent
-model: claude-4-sonnet
 temperature: 0.1
 tools:
   bash: true

.opencode/agent/subagents/code/codebase-pattern-analyst.md

@@ -1,7 +1,6 @@
 ---
 description: "Codebase pattern analysis agent for finding similar implementations"
 mode: subagent
-model: google/gemini-2.5-flash
 temperature: 0.1
 tools:
   read: true

.opencode/agent/subagents/code/coder-agent.md

@@ -1,7 +1,6 @@
 ---
 description: "Executes coding subtasks in sequence, ensuring completion as specified"
 mode: subagent
-model: claude-4-sonnet
 temperature: 0
 tools:
   read: true

.opencode/agent/subagents/code/reviewer.md

@@ -2,7 +2,6 @@
 
 description: "Code review, security, and quality assurance agent"
 mode: subagent
-model: claude-4-sonnet
 temperature: 0.1
 tools:
   read: true

.opencode/agent/subagents/core/task-manager.md

@@ -1,7 +1,6 @@
 ---
 description: "Breaks down complex features into small, verifiable subtasks"
 mode: subagent
-model: claude-4-sonnet
 temperature: 0.1
 tools:
   read: true

COMPATIBILITY.md

@@ -14,24 +14,24 @@
 
 ### macOS / Linux
 ```bash
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s core
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s essential
 ```
 
 ### Windows (Git Bash)
 ```bash
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s core
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s essential
 ```
 
 ### Windows (PowerShell)
 ```powershell
-Invoke-WebRequest -Uri "https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh" -OutFile "install.sh"
-& "C:\Program Files\Git\bin\bash.exe" install.sh core
+Invoke-WebRequest -Uri "https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh" -OutFile "install.sh"
+& "C:\Program Files\Git\bin\bash.exe" install.sh essential
 ```
 
 ## Test Your System
 
 ```bash
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/scripts/tests/test-compatibility.sh | bash
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/scripts/tests/test-compatibility.sh | bash
 ```
 
 ## Key Compatibility Features
@@ -61,4 +61,4 @@ See [Platform Compatibility Guide](docs/getting-started/platform-compatibility.m
 
 1. Run compatibility test: `bash scripts/tests/test-compatibility.sh`
 2. Check bash version: `bash --version`
-3. Report issues: [GitHub Issues](https://github.com/darrenhinde/opencode-agents/issues)
+3. Report issues: [GitHub Issues](https://github.com/darrenhinde/OpenAgents/issues)

README.md

@@ -1,25 +1,27 @@
 <div align="center">
 
-# OpenCode Agents
+# OpenAgents
 
 ### AI agent framework for plan-first development workflows with approval-based execution
 
-[![GitHub stars](https://img.shields.io/github/stars/darrenhinde/opencode-agents?style=social)](https://github.com/darrenhinde/opencode-agents/stargazers)
+[![GitHub stars](https://img.shields.io/github/stars/darrenhinde/OpenAgents?style=social)](https://github.com/darrenhinde/OpenAgents/stargazers)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![GitHub last commit](https://img.shields.io/github/last-commit/darrenhinde/opencode-agents)](https://github.com/darrenhinde/opencode-agents/commits/main)
+[![GitHub last commit](https://img.shields.io/github/last-commit/darrenhinde/OpenAgents)](https://github.com/darrenhinde/OpenAgents/commits/main)
 [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](docs/contributing/CONTRIBUTING.md)
 [![Buy Me A Coffee](https://img.shields.io/badge/Buy%20Me%20A%20Coffee-support-yellow.svg?style=flat&logo=buy-me-a-coffee)](https://buymeacoffee.com/darrenhinde)
 
 **Multi-language support:** TypeScript • Python • Go • Rust  
 **Features:** Automatic testing • Code review • Validation
 
+> **🚀 Future Plans:** Currently optimized for OpenCode CLI. Support for other AI coding tools (Cursor, Claude Code, etc.) will be added after stabilizing the OpenCode integration.
+
 </div>
 
 [![Watch Demo](https://img.youtube.com/vi/EOIzFMdmox8/maxresdefault.jpg)](https://youtu.be/EOIzFMdmox8?si=4ZSsVlAkhMxVmF2R)
 
 > **Note:** This repository has evolved since the demo video with continuous improvements to make it easier for others to use in their projects. The core concepts remain the same, but installation and component organization have been streamlined.
 
-> 📹 **Following along with the video?** The simplified structure shown in the tutorial is available on the [`video-simple`](https://github.com/darrenhinde/opencode-agents/tree/video-simple) branch.
+> 📹 **Following along with the video?** The simplified structure shown in the tutorial is available on the [`video-simple`](https://github.com/darrenhinde/OpenAgents/tree/video-simple) branch.
 
 
 ## Why Use This?
@@ -49,7 +51,7 @@ https://opencode.ai/docs#
 
 ```bash
 # Download the installer
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh -o install.sh
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh -o install.sh
 
 # Run interactively
 bash install.sh
@@ -61,7 +63,7 @@ bash install.sh
 
 ```bash
 # Download the installer
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh -o install.sh
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh -o install.sh
 
 # Run interactively
 bash install.sh
@@ -73,7 +75,7 @@ bash install.sh
 
 ```powershell
 # Download the script
-Invoke-WebRequest -Uri "https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh" -OutFile "install.sh"
+Invoke-WebRequest -Uri "https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh" -OutFile "install.sh"
 
 # Run with Git Bash
 & "C:\Program Files\Git\bin\bash.exe" install.sh
@@ -86,7 +88,7 @@ wsl bash install.sh
 </details>
 
 The installer offers:
-- 🎯 **Quick Profiles**: Core, Developer, Full, or Advanced
+- 🎯 **Quick Profiles**: Essential, Developer, Business, Full, or Advanced
 - 🎨 **Custom Selection**: Pick exactly what you need
 - 📦 **Smart Dependencies**: Auto-installs required components
 - ✨ **Interactive Menus**: User-friendly component browser
@@ -103,17 +105,20 @@ The installer offers:
 <summary><b>macOS / Linux / Git Bash / WSL</b></summary>
 
 ```bash
-# Core - Minimal essentials (9 components)
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s core
+# Essential - Minimal essentials (9 components)
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s essential
+
+# Developer - Recommended for daily work (19 components)
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s developer
 
-# Developer - Recommended for daily work (22 components)
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s developer
+# Business - Business automation and content creation (15 components)
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s business
 
 # Full - Everything included (25 components)
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s full
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s full
 
-# Advanced - Full + System Builder (30 components)
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s advanced
+# Advanced - Full + System Builder (32 components)
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s advanced
 ```
 </details>
 
@@ -122,14 +127,17 @@ curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/in
 
 ```powershell
 # Download script
-Invoke-WebRequest -Uri "https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh" -OutFile "install.sh"
+Invoke-WebRequest -Uri "https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh" -OutFile "install.sh"
 
-# Core profile
-& "C:\Program Files\Git\bin\bash.exe" install.sh core
+# Essential profile
+& "C:\Program Files\Git\bin\bash.exe" install.sh essential
 
 # Developer profile
 & "C:\Program Files\Git\bin\bash.exe" install.sh developer
 
+# Business profile
+& "C:\Program Files\Git\bin\bash.exe" install.sh business
+
 # Full profile
 & "C:\Program Files\Git\bin\bash.exe" install.sh full
 
@@ -143,8 +151,8 @@ Invoke-WebRequest -Uri "https://raw.githubusercontent.com/darrenhinde/opencode-a
 **Option C: Manual Install**
 ```bash
 # Clone this repository
-git clone https://github.com/darrenhinde/opencode-agents.git
-cd opencode-agents
+git clone https://github.com/darrenhinde/OpenAgents.git
+cd OpenAgents
 
 # Install to OpenCode directory (global)
 mkdir -p ~/.opencode
@@ -282,7 +290,7 @@ The System Builder is an interactive tool that generates complete `.opencode` ar
 ### Quick Start
 ```bash
 # Install advanced profile (includes system builder)
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s advanced
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s advanced
 
 # Run the interactive builder
 /build-context-system
@@ -329,7 +337,7 @@ cd ~/.opencode/plugin
 npm install
 
 # Configure
-cd ~/opencode-agents
+cd ~/OpenAgents
 cp env.example .env
 # Edit .env with TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID
 ```
@@ -350,7 +358,7 @@ cd ~/.opencode/tool
 npm install
 
 # Configure
-cd ~/opencode-agents
+cd ~/OpenAgents
 cp env.example .env
 # Edit .env with GEMINI_API_KEY
 ```
@@ -393,48 +401,58 @@ A: Yes! Use the installer's list feature to see all components:
 Or cherry-pick individual files with curl:
 ```bash
 curl -o ~/.opencode/agent/codebase-agent.md \
-  https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/.opencode/agent/codebase-agent.md
+  https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/.opencode/agent/codebase-agent.md
 ```
 
 ---
 
 ## Installation Profiles
 
-The installer offers four pre-configured profiles:
+The installer offers five pre-configured profiles:
 
-### 🎯 Core (Minimal - 9 components)
-Absolute essentials for basic development workflow.
-- **Agents**: task-manager, codebase-agent
-- **Subagents**: tester, documentation, coder-agent
-- **Commands**: commit
+### 🎯 Essential (Minimal - 9 components)
+Minimal starter kit - universal agent with core subagents.
+- **Agents**: openagent
+- **Subagents**: task-manager, documentation
+- **Commands**: context, clean
+- **Tools**: env
 - **Context**: essential-patterns, project-context
 - **Config**: env-example
-- **Best for**: Minimal setup, learning the system
-
-### 💼 Developer (Recommended - 22 components)
-Complete daily development setup with AI assistance.
-- Everything in Core, plus:
-- **Agents**: image-specialist, workflow-orchestrator
-- **Subagents**: reviewer, build-agent, codebase-pattern-analyst
-- **Commands**: test, context, clean, optimize, prompt-enhancer
-- **Tools**: env, gemini (AI image generation)
+- **Best for**: Learning the system, lightweight tasks, minimal setup
+
+### 💼 Developer (Recommended - 19 components)
+Complete software development environment with code generation, testing, review, and build tools.
+- Everything in Essential, plus:
+- **Agents**: codebase-agent
+- **Subagents**: coder-agent, reviewer, tester, build-agent, codebase-pattern-analyst
+- **Commands**: commit, test, optimize
 - **Config**: readme
-- **Best for**: Most developers, daily use, full-featured
+- **Best for**: Most developers, daily use, full-featured development
+
+### 📊 Business (15 components)
+Business process automation, content creation, and visual workflows.
+- **Agents**: openagent
+- **Subagents**: task-manager, documentation, image-specialist
+- **Commands**: context, clean, prompt-enhancer
+- **Tools**: env, gemini (AI image generation)
+- **Plugins**: notify, telegram-notify
+- **Context**: essential-patterns, project-context
+- **Config**: env-example, readme
+- **Best for**: Business automation, content creation, non-developers
 
-### 📦 Full
-Complete installation with all available components.
-- Everything in Developer, plus:
+### 📦 Full (25 components)
+Everything included - all agents, subagents, tools, and plugins.
+- Everything in Developer and Business combined, plus:
 - **Commands**: worktrees (git worktree management)
 - **Best for**: Power users, exploring all features
 
-### 🚀 Advanced
-Full installation plus **System Builder** and experimental features.
+### 🚀 Advanced (32 components)
+Full installation plus **System Builder** for creating custom AI architectures.
 - Everything in Full, plus:
-- **System Builder**: Interactive AI system generator (7 components)
+- **System Builder**: Interactive AI system generator
   - system-builder agent
   - domain-analyzer, agent-generator, context-organizer, workflow-designer, command-creator subagents
   - build-context-system command
-- **Additional**: .Building/ directory, GitHub workflows
 - **Best for**: Building custom AI systems, contributors, learning the architecture
 
 ## Updating Components
@@ -446,7 +464,7 @@ Keep your components up to date:
 ./update.sh
 
 # Or re-run the installer
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash
 ```
 
 ---

docs/README.md

@@ -1,6 +1,6 @@
-# OpenCode Agents Documentation
+# OpenAgents Documentation
 
-Welcome to the OpenCode Agents documentation! This directory contains all documentation organized by topic.
+Welcome to the OpenAgents documentation! This directory contains all documentation organized by topic.
 
 ## 📚 Documentation Index
 
@@ -35,7 +35,7 @@ Welcome to the OpenCode Agents documentation! This directory contains all docume
 ### For Contributors
 - Read the [Contributing Guide](contributing/CONTRIBUTING.md)
 - Review the [Code of Conduct](contributing/CODE_OF_CONDUCT.md)
-- Check out [good first issues](https://github.com/darrenhinde/opencode-agents/labels/good%20first%20issue)
+- Check out [good first issues](https://github.com/darrenhinde/OpenAgents/labels/good%20first%20issue)
 
 ### For Advanced Users
 - Study the [Agent System Blueprint](features/agent-system-blueprint.md)
@@ -66,7 +66,7 @@ docs/
 
 ### I want to...
 
-**...install OpenCode Agents**
+**...install OpenAgents**
 → [Installation Guide](getting-started/installation.md)
 
 **...understand collision handling**
@@ -82,20 +82,20 @@ docs/
 → [Contributing Guide](contributing/CONTRIBUTING.md)
 
 **...report a bug or request a feature**
-→ [GitHub Issues](https://github.com/darrenhinde/opencode-agents/issues)
+→ [GitHub Issues](https://github.com/darrenhinde/OpenAgents/issues)
 
 ## 💡 Additional Resources
 
 - **Main README**: [../README.md](../README.md)
-- **GitHub Repository**: https://github.com/darrenhinde/opencode-agents
+- **GitHub Repository**: https://github.com/darrenhinde/OpenAgents
 - **OpenCode CLI Docs**: https://opencode.ai/docs
 - **Component Registry**: [../registry.json](../registry.json)
 
 ## 🤝 Community
 
-- **Issues**: [Report bugs or request features](https://github.com/darrenhinde/opencode-agents/issues)
-- **Discussions**: [Ask questions and share ideas](https://github.com/darrenhinde/opencode-agents/discussions)
-- **Pull Requests**: [Contribute code](https://github.com/darrenhinde/opencode-agents/pulls)
+- **Issues**: [Report bugs or request features](https://github.com/darrenhinde/OpenAgents/issues)
+- **Discussions**: [Ask questions and share ideas](https://github.com/darrenhinde/OpenAgents/discussions)
+- **Pull Requests**: [Contribute code](https://github.com/darrenhinde/OpenAgents/pulls)
 
 ## 📝 License
 
@@ -103,4 +103,4 @@ This project is licensed under the MIT License. See [LICENSE](../LICENSE) for de
 
 ---
 
-**Need help?** Check the [Contributing Guide](contributing/CONTRIBUTING.md) or open an [issue](https://github.com/darrenhinde/opencode-agents/issues).
+**Need help?** Check the [Contributing Guide](contributing/CONTRIBUTING.md) or open an [issue](https://github.com/darrenhinde/OpenAgents/issues).

docs/agents/openagent.md

@@ -57,7 +57,7 @@ graph LR
     style C fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
     style D fill:#50E3C2,stroke:#3AB89E,stroke-width:3px,color:#000
     style E fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
-    style F fill:#BD10E0,stroke:#9012B3,stroke-width:3px,color:#fff
+    style F fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
     style G fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
 ```
 
@@ -79,7 +79,7 @@ graph TD
     C --> D[Done!]
     
     style A fill:#4A90E2,stroke:#2E5C8A,stroke-width:3px,color:#000
-    style B fill:#BD10E0,stroke:#9012B3,stroke-width:3px,color:#fff
+    style B fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
     style C fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
     style D fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
 ```
@@ -111,12 +111,12 @@ graph TD
     J --> L[Done!]
     
     style A fill:#4A90E2,stroke:#2E5C8A,stroke-width:3px,color:#000
-    style B fill:#BD10E0,stroke:#9012B3,stroke-width:3px,color:#fff
+    style B fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
     style C fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
     style D fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
     style E fill:#50E3C2,stroke:#3AB89E,stroke-width:3px,color:#000
     style F fill:#D0021B,stroke:#A00116,stroke-width:3px,color:#fff
-    style G fill:#BD10E0,stroke:#9012B3,stroke-width:3px,color:#fff
+    style G fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
     style H fill:#50E3C2,stroke:#3AB89E,stroke-width:3px,color:#000
     style I fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
     style J fill:#50E3C2,stroke:#3AB89E,stroke-width:3px,color:#000
@@ -195,13 +195,39 @@ graph TD
     style Stage1 fill:#4A90E2,stroke:#2E5C8A,stroke-width:4px,color:#fff
     style Stage2 fill:#F5A623,stroke:#C17D11,stroke-width:4px,color:#000
     style Stage3 fill:#50E3C2,stroke:#3AB89E,stroke-width:4px,color:#000
-    style Stage4 fill:#BD10E0,stroke:#9012B3,stroke-width:4px,color:#fff
-    style Stage5 fill:#9013B3,stroke:#7011A0,stroke-width:4px,color:#fff
+    style Stage4 fill:#6B7C93,stroke:#4A5568,stroke-width:4px,color:#fff
+    style Stage5 fill:#5A6C7D,stroke:#3D4E5C,stroke-width:4px,color:#fff
     style Stage6 fill:#7ED321,stroke:#5FA319,stroke-width:4px,color:#000
     style Answer fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
 ```
 
+---
+
 ### Stage 1: Analyze
+
+```mermaid
+graph TD
+    A[Receive User Request] --> B[Read & Parse Request]
+    B --> C{Assess Type}
+    C -->|Informational| D[Question Path]
+    C -->|Action Required| E[Task Path]
+    
+    D --> D1[Prepare Direct Answer]
+    D1 --> D2[No Approval Needed]
+    D2 --> D3[Respond Immediately]
+    
+    E --> E1[Assess Complexity]
+    E1 --> E2[Identify Required Resources]
+    E2 --> E3[Proceed to Stage 2]
+    
+    style A fill:#4A90E2,stroke:#2E5C8A,stroke-width:3px,color:#fff
+    style C fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
+    style D fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
+    style E fill:#50E3C2,stroke:#3AB89E,stroke-width:3px,color:#000
+    style D3 fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
+    style E3 fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
+```
+
 **What happens**: OpenAgent reads your request and decides if it's a question or a task.
 
 **Your experience**: Instant - you don't see this happening.
@@ -209,6 +235,31 @@ graph TD
 ---
 
 ### Stage 2: Approve ⚠️ (MANDATORY for tasks)
+
+```mermaid
+graph TD
+    A[Task Identified] --> B[Analyze Requirements]
+    B --> C[Create Step-by-Step Plan]
+    C --> D[Format Plan for User]
+    D --> E[Present Plan to User]
+    E --> F{User Response}
+    
+    F -->|Approve| G[Proceed to Stage 3]
+    F -->|Request Changes| H[Revise Plan]
+    F -->|Reject/Cancel| I[Cancel Task]
+    
+    H --> C
+    I --> J[End - Task Cancelled]
+    
+    style A fill:#4A90E2,stroke:#2E5C8A,stroke-width:3px,color:#fff
+    style E fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
+    style F fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
+    style G fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
+    style H fill:#50E3C2,stroke:#3AB89E,stroke-width:3px,color:#000
+    style I fill:#D0021B,stroke:#A00116,stroke-width:3px,color:#fff
+    style J fill:#D0021B,stroke:#A00116,stroke-width:3px,color:#fff
+```
+
 **What happens**: OpenAgent creates a plan and shows it to you.
 
 **Your experience**: You see something like:
@@ -227,6 +278,43 @@ graph TD
 ---
 
 ### Stage 3: Execute
+
+```mermaid
+graph TD
+    A[Approval Received] --> B[Review Plan Steps]
+    B --> C{Need Context Files?}
+    
+    C -->|Yes| D[Create Session]
+    C -->|No| E[Proceed Without Session]
+    
+    D --> F[Generate Session ID]
+    F --> G[Create Context Files]
+    G --> H[Update Manifest]
+    
+    H --> I{Delegate or Direct?}
+    E --> I
+    
+    I -->|Delegate| J[Identify Specialist Agent]
+    I -->|Direct| K[Execute Steps Directly]
+    
+    J --> L[Pass Context Files]
+    L --> M[Specialist Executes]
+    M --> N[Integrate Results]
+    
+    K --> O[Complete Execution]
+    N --> O
+    
+    O --> P[Proceed to Stage 4]
+    
+    style A fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
+    style C fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
+    style D fill:#50E3C2,stroke:#3AB89E,stroke-width:3px,color:#000
+    style I fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
+    style J fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
+    style K fill:#50E3C2,stroke:#3AB89E,stroke-width:3px,color:#000
+    style P fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
+```
+
 **What happens**: OpenAgent carries out the plan, either directly or by delegating to specialist agents.
 
 **Your experience**: You might see:
@@ -240,6 +328,55 @@ graph TD
 ---
 
 ### Stage 4: Validate ⚠️ (MANDATORY for tasks)
+
+```mermaid
+graph TD
+    A[Execution Complete] --> B[Check Quality]
+    B --> C{Tests Applicable?}
+    
+    C -->|Yes| D[Run Tests]
+    C -->|No| E[Manual Validation]
+    
+    D --> F{Tests Pass?}
+    E --> G{Quality OK?}
+    
+    F -->|Pass| H[All Checks Passed]
+    G -->|Yes| H
+    
+    F -->|Fail| I[STOP Execution]
+    G -->|No| I
+    
+    I --> J[Report Issues Clearly]
+    J --> K[Propose Fix Plan]
+    K --> L[Request Approval]
+    L --> M{User Approves Fix?}
+    
+    M -->|Yes| N[Apply Fixes]
+    M -->|No| O[End - Issues Remain]
+    
+    N --> D
+    
+    H --> P[Ask: Additional Checks?]
+    P --> Q{User Response}
+    
+    Q -->|Run More Tests| R[Run Specific Tests]
+    Q -->|Review Files| S[Review Specific Files]
+    Q -->|Proceed| T[Proceed to Stage 5]
+    
+    R --> H
+    S --> H
+    
+    style A fill:#50E3C2,stroke:#3AB89E,stroke-width:3px,color:#000
+    style C fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
+    style F fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
+    style G fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
+    style H fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
+    style I fill:#D0021B,stroke:#A00116,stroke-width:3px,color:#fff
+    style L fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
+    style M fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
+    style T fill:#5A6C7D,stroke:#3D4E5C,stroke-width:3px,color:#fff
+```
+
 **What happens**: OpenAgent checks the quality of the work, runs tests if applicable, and ensures everything works correctly.
 
 **Your experience when validation passes**: You see:
@@ -288,6 +425,33 @@ If OpenAgent runs tests or validation and finds issues, it follows a **strict pr
 ---
 
 ### Stage 5: Summarize
+
+```mermaid
+graph TD
+    A[Validation Complete & User Satisfied] --> B{Task Complexity}
+    
+    B -->|Simple Question| C[Natural Conversational Response]
+    B -->|Simple Task| D[Brief Summary]
+    B -->|Complex Task| E[Formal Summary]
+    
+    D --> D1[Brief: Created X or Updated Y]
+    
+    E --> E1[List Accomplishments]
+    E1 --> E2[Detail Changes Made]
+    E2 --> E3[Suggest Next Steps]
+    
+    C --> F[Proceed to Stage 6]
+    D1 --> F
+    E3 --> F
+    
+    style A fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
+    style B fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
+    style C fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
+    style D fill:#50E3C2,stroke:#3AB89E,stroke-width:3px,color:#000
+    style E fill:#5A6C7D,stroke:#3D4E5C,stroke-width:3px,color:#fff
+    style F fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
+```
+
 **What happens**: After validation passes and you're satisfied, OpenAgent creates a summary of what was accomplished.
 
 **Your experience**: You see a summary like:
@@ -307,6 +471,41 @@ Created README.md with project documentation.
 ---
 
 ### Stage 6: Confirm Completion ⚠️ (MANDATORY for tasks)
+
+```mermaid
+graph TD
+    A[Summary Presented] --> B[Ask: Is This Satisfactory?]
+    B --> C{User Satisfied?}
+    
+    C -->|No| D[Identify Issues]
+    D --> E[Return to Appropriate Stage]
+    
+    C -->|Yes| F{Session Files Created?}
+    
+    F -->|No| G[Task Complete]
+    
+    F -->|Yes| H[Ask: Cleanup Session Files?]
+    H --> I{User Approves Cleanup?}
+    
+    I -->|No| J[Keep Session Files]
+    J --> K[Task Complete - Files Preserved]
+    
+    I -->|Yes| L[Delete Context Files]
+    L --> M[Update Manifest]
+    M --> N[Remove Session Folder]
+    N --> O[Confirm Cleanup Complete]
+    O --> P[Task Complete - Cleaned Up]
+    
+    style A fill:#5A6C7D,stroke:#3D4E5C,stroke-width:3px,color:#fff
+    style C fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
+    style D fill:#D0021B,stroke:#A00116,stroke-width:3px,color:#fff
+    style F fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
+    style G fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
+    style I fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
+    style K fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
+    style P fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
+```
+
 **What happens**: OpenAgent asks if you're satisfied and if temporary files should be cleaned up.
 
 **Your experience**: You see:
@@ -506,9 +705,9 @@ graph TD
     style B fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
     style C fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
     style D fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
-    style E fill:#BD10E0,stroke:#9012B3,stroke-width:3px,color:#fff
-    style F fill:#BD10E0,stroke:#9012B3,stroke-width:3px,color:#fff
-    style G fill:#BD10E0,stroke:#9012B3,stroke-width:3px,color:#fff
+    style E fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
+    style F fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
+    style G fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
     style H fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
 ```
 

docs/contributing/CONTRIBUTING.md

@@ -1,4 +1,4 @@
-# Contributing to OpenCode Agents
+# Contributing to OpenAgents
 
 Thank you for your interest in contributing! This guide will help you add new components to the registry.
 
@@ -31,8 +31,7 @@ All markdown files should include YAML frontmatter:
 ---
 description: "Brief description of what this does"
 mode: primary  # For agents only
-model: claude-4-sonnet  # For agents only
-temperature: 0.1  # For agents only
+temperature: 0.1  # Optional - for agents only
 tools:  # For agents only
   read: true
   edit: true

docs/features/system-builder/README.md

@@ -9,7 +9,7 @@
 The system builder is included in the **Advanced** profile:
 
 ```bash
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s advanced
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s advanced
 ```
 
 **What you get:**
@@ -25,7 +25,7 @@ Already have `core`, `developer`, or `full` profile? Add system builder:
 
 ```bash
 # Run advanced profile
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s advanced
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s advanced
 
 # When prompted about collisions:
 # Choose: 1) Skip existing

docs/features/system-builder/quick-start.md

@@ -15,7 +15,7 @@ An **interactive AI system generator** that creates complete `.opencode` archite
 
 ```bash
 # Install Advanced profile (includes system builder)
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s advanced
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s advanced
 ```
 
 **What you get:**
@@ -33,7 +33,7 @@ Already have `developer` or `full` profile? Add system builder:
 
 ```bash
 # Run advanced profile
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s advanced
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s advanced
 
 # When prompted about collisions:
 # Choose: 1) Skip existing
@@ -178,7 +178,7 @@ When you install **advanced** profile, you get:
 
 **Installation:**
 ```bash
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s advanced
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s advanced
 ```
 
 **Usage:**

docs/getting-started/context-aware-system/QUICK_START_SYSTEM_BUILDER.md

@@ -15,7 +15,7 @@ An **interactive AI system generator** that creates complete `.opencode` archite
 
 ```bash
 # Install Advanced profile (includes system builder)
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s advanced
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s advanced
 ```
 
 **What you get:**
@@ -33,7 +33,7 @@ Already have `developer` or `full` profile? Add system builder:
 
 ```bash
 # Run advanced profile
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s advanced
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s advanced
 
 # When prompted about collisions:
 # Choose: 1) Skip existing

docs/getting-started/installation.md

@@ -113,11 +113,11 @@ mv .opencode.backup.20251118-143022/.opencode .opencode
 ## Example Session
 
 ```bash
-$ bash <(curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh) --developer
+$ bash <(curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh) --developer
 
 ╔════════════════════════════════════════════════════════════════╗
 ║                                                                ║
-║           OpenCode Agents Installer v1.0.0                    ║
+║           OpenAgents Installer v1.0.0                    ║
 ║                                                                ║
 ╚════════════════════════════════════════════════════════════════╝
 
@@ -207,7 +207,7 @@ Enter your choice [1-4]: 1
 3. Start using OpenCode agents:
    opencode
 
-ℹ Documentation: https://github.com/darrenhinde/opencode-agents
+ℹ Documentation: https://github.com/darrenhinde/OpenAgents
 ```
 
 ---

docs/getting-started/platform-compatibility.md

@@ -1,6 +1,6 @@
 # Platform Compatibility Guide
 
-The OpenCode Agents installer is designed to work across multiple platforms and bash versions.
+The OpenAgents installer is designed to work across multiple platforms and bash versions.
 
 ## Supported Platforms
 
@@ -11,10 +11,10 @@ The OpenCode Agents installer is designed to work across multiple platforms and
 
 ```bash
 # Standard installation
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash
 
 # Profile-based installation
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s core
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s core
 ```
 
 **Dependencies:**
@@ -32,10 +32,10 @@ brew install curl jq
 
 ```bash
 # Standard installation
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash
 
 # Profile-based installation
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s developer
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s developer
 ```
 
 **Dependencies:**
@@ -90,10 +90,10 @@ apk add curl jq bash
 **Run Installer:**
 ```bash
 # Standard installation
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash
 
 # Profile-based installation
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s full
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s full
 ```
 
 #### Option 2: WSL (Windows Subsystem for Linux)
@@ -110,7 +110,7 @@ wsl --install
 **Run Installer:**
 ```bash
 # In WSL terminal
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash
 ```
 
 **Dependencies:**
@@ -125,7 +125,7 @@ sudo apt-get install curl jq
 
 ```powershell
 # Download the script
-Invoke-WebRequest -Uri "https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh" -OutFile "install.sh"
+Invoke-WebRequest -Uri "https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh" -OutFile "install.sh"
 
 # Run with Git Bash
 & "C:\Program Files\Git\bin\bash.exe" install.sh core
@@ -186,15 +186,15 @@ Run the compatibility test to verify your system:
 
 ```bash
 # Download and run the test
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/scripts/tests/test-compatibility.sh | bash
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/scripts/tests/test-compatibility.sh | bash
 ```
 
 Or manually:
 
 ```bash
 # Clone the repo
-git clone https://github.com/darrenhinde/opencode-agents.git
-cd opencode-agents
+git clone https://github.com/darrenhinde/OpenAgents.git
+cd OpenAgents
 
 # Run the test
 bash scripts/tests/test-compatibility.sh
@@ -217,7 +217,7 @@ The test checks:
 **Cause:** Using bash version < 4.0  
 **Solution:** This should be fixed in the latest version. Update the installer:
 ```bash
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh > install.sh
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh > install.sh
 bash install.sh core
 ```
 
@@ -274,7 +274,7 @@ sudo bash install.sh core
 **Solution:** Use Git Bash or WSL:
 ```powershell
 # Download first
-Invoke-WebRequest -Uri "https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh" -OutFile "install.sh"
+Invoke-WebRequest -Uri "https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh" -OutFile "install.sh"
 
 # Run with Git Bash
 & "C:\Program Files\Git\bin\bash.exe" install.sh
@@ -302,8 +302,8 @@ If you can't use the installer:
 
 ```bash
 # 1. Clone or download the repository
-git clone https://github.com/darrenhinde/opencode-agents.git
-cd opencode-agents
+git clone https://github.com/darrenhinde/OpenAgents.git
+cd OpenAgents
 
 # 2. Copy to OpenCode directory
 mkdir -p ~/.opencode
@@ -326,7 +326,7 @@ If you encounter issues:
 
 1. **Run the compatibility test:**
    ```bash
-   curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/scripts/tests/test-compatibility.sh | bash
+   curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/scripts/tests/test-compatibility.sh | bash
    ```
 
 2. **Check your bash version:**
@@ -341,7 +341,7 @@ If you encounter issues:
    ```
 
 4. **Report issues:**
-   - [GitHub Issues](https://github.com/darrenhinde/opencode-agents/issues)
+   - [GitHub Issues](https://github.com/darrenhinde/OpenAgents/issues)
    - Include: Platform, Bash version, Error message
 
 ---

docs/github/GITHUB_SETTINGS.md

@@ -11,7 +11,7 @@ After merging this PR, update these GitHub repository settings:
 AI agent framework for plan-first development workflows with approval-based execution. Multi-language support (TypeScript, Python, Go, Rust) with automatic testing, code review, and validation.
 ```
 
-**Website:** `https://github.com/darrenhinde/opencode-agents`
+**Website:** `https://github.com/darrenhinde/OpenAgents`
 
 ## 2. Topics (Add All 16)
 

docs/model-providers/oss/LM-STUDIO-SETUP.md

@@ -0,0 +1,267 @@
+# LM Studio Optimal Settings for OpenCode
+
+This guide provides battle-tested configurations for running Qwen3-Coder and GPT-OSS-20B with OpenCode via LM Studio.
+
+## Quick Start
+
+1. Copy the configuration from `lmstudio-config-example.json` to your `opencode.json`
+2. Download your models in LM Studio
+3. Start the LM Studio server on port 1234
+4. Launch OpenCode and use `/models` to select your local model
+
+---
+
+## Model-Specific Settings
+
+### **Qwen3-Coder-30B** (Recommended Primary Model)
+
+Best for: Precise tool calling, code generation, debugging
+
+```json
+{
+  "limit": {
+    "context": 24000,
+    "output": 4000
+  },
+  "options": {
+    "temperature": 0.1,
+    "topP": 0.8,
+    "minP": 0.01,
+    "repetitionPenalty": 1.05
+  }
+}
+```
+
+**Why these settings:**
+- **Temperature 0.1**: Maximizes deterministic tool calling reliability. Use 0.2-0.3 for more creative exploration.
+- **Top-P 0.8**: Constrains token diversity appropriately for coding tasks
+- **Min-P 0.01**: Lower than llama.cpp default (0.1) for better tool use
+- **Repetition Penalty 1.05**: Prevents infinite loops during multi-step tool calls
+- **Context 24000**: Handles large codebases without frequent compaction
+- **Output 4000**: Sufficient for most code generation tasks
+
+### **GPT-OSS-20B** (Alternative/Backup Model)
+
+Best for: General coding, conversation, when you need higher creativity
+
+```json
+{
+  "limit": {
+    "context": 16000,
+    "output": 4000
+  },
+  "options": {
+    "temperature": 0.4,
+    "topP": 0.9,
+    "minP": 0.05,
+    "repetitionPenalty": 1.05
+  }
+}
+```
+
+**Why these settings:**
+- **Temperature 0.4**: Higher than Qwen3 due to different architecture - still reliable for tools
+- **Top-P 0.9**: More diversity for MoE (Mixture of Experts) architecture
+- **Min-P 0.05**: Slightly higher for better creative balance
+- **Repetition Penalty 1.05**: Same as Qwen3 for loop prevention
+- **Context 16000**: Sufficient for most tasks, adjust based on VRAM
+
+---
+
+## LM Studio Application Settings
+
+### **GPU Acceleration (Critical)**
+
+In LM Studio Settings → Hardware:
+
+1. **GPU Offload Layers**: Set to MAXIMUM your GPU can handle
+   - RTX 4060 8GB: 36 layers
+   - RTX 4070 12GB: 40 layers
+   - RTX 4090 24GB: All layers
+   - Mac M1/M2/M3: All layers (MLX preferred)
+
+2. **Keep Model in VRAM**: ✅ Enable
+3. **Offload KV Cache to GPU**: ✅ Enable (4x speedup on compatible hardware)
+
+### **Context Settings**
+
+- **Context Length**: Match or exceed your config (24000 for Qwen3, 16000 for GPT-OSS)
+- **Batch Size**: 512 (default) or higher if VRAM allows
+- **Threads**: Set to CPU cores - 2 (e.g., 14 threads for 16-core CPU)
+
+### **Speculative Decoding** (Advanced)
+
+For 30B+ models, enable speculative decoding:
+- **Draft Model**: Use a small 1-3B model from the same family
+- **Speedup**: 1.5x-3x without quality loss
+
+---
+
+## OpenCode Integration
+
+### Full Configuration Example
+
+```json
+{
+  "$schema": "https://opencode.ai/config.json",
+  "provider": {
+    "lmstudio": {
+      "npm": "@ai-sdk/openai-compatible",
+      "name": "LM Studio (Local)",
+      "options": {
+        "baseURL": "http://127.0.0.1:1234/v1"
+      },
+      "models": {
+        "qwen3-coder-30b": {
+          "name": "Qwen3-Coder-30B (Local)",
+          "tools": true,
+          "limit": {
+            "context": 24000,
+            "output": 4000
+          },
+          "options": {
+            "temperature": 0.1,
+            "topP": 0.8,
+            "minP": 0.01,
+            "repetitionPenalty": 1.05
+          }
+        },
+        "gpt-oss-20b": {
+          "name": "GPT-OSS-20B (Local)",
+          "tools": true,
+          "limit": {
+            "context": 16000,
+            "output": 4000
+          },
+          "options": {
+            "temperature": 0.4,
+            "topP": 0.9,
+            "minP": 0.05,
+            "repetitionPenalty": 1.05
+          }
+        }
+      }
+    }
+  },
+  "model": "lmstudio/qwen3-coder-30b",
+  "agents": {
+    "build": {
+      "mode": "primary",
+      "description": "Main build agent"
+    }
+  }
+}
+```
+
+### Switching Models
+
+Use the `/models` command in OpenCode to switch between your configured models without restarting.
+
+---
+
+## Troubleshooting
+
+### Tool Calls Not Working
+
+1. **Increase context window** in LM Studio to 16k-32k minimum
+2. **Verify temperature** is set correctly (0.1 for Qwen3, 0.4 for GPT-OSS)
+3. **Check repetition penalty** is set to 1.05
+4. **Restart LM Studio server** after changing settings
+
+### Slow Performance
+
+1. **Maximize GPU layers** - check LM Studio logs for "offloaded X/Y layers"
+2. **Enable KV cache offload** in GPU settings
+3. **Reduce context length** if hitting VRAM limits
+4. **Try speculative decoding** with a draft model
+
+### Out of Memory
+
+1. **Reduce context length**: 16000 → 12000 → 8000
+2. **Reduce GPU layers**: Start at 50% and increase
+3. **Switch to smaller quantization**: Q6 → Q5 → Q4
+4. **Close other applications** using VRAM
+
+### Model Repeating Itself
+
+1. **Increase repetition penalty**: 1.05 → 1.10 → 1.15
+2. **Lower temperature slightly**: 0.1 → 0.05
+3. **Check min-P setting**: Should be 0.01-0.05
+
+---
+
+## Hardware Recommendations
+
+### Minimum Specs (Qwen3-Coder-30B)
+- **GPU**: 12GB VRAM (RTX 4070, RTX 3080 12GB)
+- **RAM**: 16GB system RAM
+- **Quantization**: Q4_K_M or Q5_K_M
+
+### Recommended Specs (Qwen3-Coder-30B)
+- **GPU**: 16-24GB VRAM (RTX 4080, RTX 4090)
+- **RAM**: 32GB system RAM
+- **Quantization**: Q6_K or Q8
+
+### Minimum Specs (GPT-OSS-20B)
+- **GPU**: 8GB VRAM (RTX 4060)
+- **RAM**: 16GB system RAM
+- **Quantization**: Q4_K_M
+
+### Mac Users
+- **MLX versions strongly recommended** over GGUF
+- Significantly faster on Apple Silicon
+- Use LM Studio's MLX support or native MLX inference
+- M1/M2/M3 with 16GB+ unified memory works well
+
+---
+
+## Performance Expectations
+
+### Qwen3-Coder-30B (Q5_K_M on RTX 4080)
+- **Tokens/second**: 15-25 t/s
+- **Context loading**: 2-3 seconds
+- **Tool call reliability**: 95%+
+
+### GPT-OSS-20B (Q5_K_M on RTX 4060)
+- **Tokens/second**: 20-30 t/s
+- **Context loading**: 1-2 seconds
+- **Tool call reliability**: 90%+
+
+---
+
+## Settings Comparison Table
+
+| Setting | Qwen3-Coder | GPT-OSS-20B | Reasoning |
+|---------|-------------|-------------|-----------|
+| **Temperature** | 0.1 | 0.4 | Qwen3 needs lower for tool calling |
+| **Top-P** | 0.8 | 0.9 | MoE models benefit from more diversity |
+| **Min-P** | 0.01 | 0.05 | Lower for deterministic tool use |
+| **Repetition Penalty** | 1.05 | 1.05 | Prevents loops in both |
+| **Context** | 24000 | 16000 | Qwen3 handles larger contexts better |
+| **Output** | 4000 | 4000 | Standard for code generation |
+
+---
+
+## When to Adjust Settings
+
+### For More Creativity
+- Increase temperature: 0.1 → 0.3 (Qwen3) or 0.4 → 0.6 (GPT-OSS)
+- Increase top-P: 0.8 → 0.9 or 0.9 → 0.95
+
+### For More Precision
+- Decrease temperature: 0.1 → 0.05 (careful: may reduce quality)
+- Decrease top-P: 0.8 → 0.7
+
+### For Handling Repetition
+- Increase repetition penalty: 1.05 → 1.10
+- Add frequency penalty: 0 → 0.3
+
+---
+
+## Notes
+
+- These settings are optimized for **tool calling reliability** with OpenCode
+- Raw performance benchmarks show Ollama may be faster, but **tool calling is unreliable**
+- LM Studio's proper parameter handling makes it the recommended choice for OpenCode
+- Settings can be adjusted per-use-case, but these defaults work for 90% of coding tasks
+

docs/model-providers/oss/lmstudio-config-example.json

@@ -0,0 +1,54 @@
+{
+  "$schema": "https://opencode.ai/config.json",
+  "provider": {
+    "lmstudio": {
+      "npm": "@ai-sdk/openai-compatible",
+      "name": "LM Studio (Local)",
+      "options": {
+        "baseURL": "http://127.0.0.1:1234/v1"
+      },
+      "models": {
+        "qwen3-coder-30b": {
+          "name": "Qwen3-Coder-30B (Local)",
+          "tools": true,
+          "limit": {
+            "context": 24000,
+            "output": 4000
+          },
+          "options": {
+            "temperature": 0.1,
+            "topP": 0.8,
+            "minP": 0.01,
+            "repetitionPenalty": 1.05,
+            "frequencyPenalty": 0,
+            "presencePenalty": 0
+          }
+        },
+        "gpt-oss-20b": {
+          "name": "GPT-OSS-20B (Local)",
+          "tools": true,
+          "limit": {
+            "context": 16000,
+            "output": 4000
+          },
+          "options": {
+            "temperature": 0.4,
+            "topP": 0.9,
+            "minP": 0.05,
+            "repetitionPenalty": 1.05,
+            "frequencyPenalty": 0,
+            "presencePenalty": 0
+          }
+        }
+      }
+    }
+  },
+  "model": "lmstudio/qwen3-coder-30b",
+  "agents": {
+    "build": {
+      "mode": "primary",
+      "description": "Main build agent for code generation and fixes"
+    }
+  }
+}
+

install.sh

@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 
 #############################################################################
-# OpenCode Agents Installer
+# OpenAgents Installer
 # Interactive installer for OpenCode agents, commands, tools, and plugins
 #
 # Compatible with:
@@ -44,9 +44,9 @@ else
 fi
 
 # Configuration
-REPO_URL="https://github.com/darrenhinde/opencode-agents"
+REPO_URL="https://github.com/darrenhinde/OpenAgents"
 BRANCH="${OPENCODE_BRANCH:-main}"  # Allow override via environment variable
-RAW_URL="https://raw.githubusercontent.com/darrenhinde/opencode-agents/${BRANCH}"
+RAW_URL="https://raw.githubusercontent.com/darrenhinde/OpenAgents/${BRANCH}"
 REGISTRY_URL="${RAW_URL}/registry.json"
 INSTALL_DIR=".opencode"
 TEMP_DIR="/tmp/opencode-installer-$$"
@@ -65,7 +65,7 @@ print_header() {
     echo -e "${CYAN}${BOLD}"
     echo "╔════════════════════════════════════════════════════════════════╗"
     echo "║                                                                ║"
-    echo "║           OpenCode Agents Installer v1.0.0                    ║"
+    echo "║           OpenAgents Installer v1.0.0                         ║"
     echo "║                                                                ║"
     echo "╚════════════════════════════════════════════════════════════════╝"
     echo -e "${NC}"
@@ -227,7 +227,7 @@ check_interactive_mode() {
         echo "For interactive mode, download the script first:"
         echo ""
         echo -e "${CYAN}# Download the script${NC}"
-        echo "curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh -o install.sh"
+        echo "curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh -o install.sh"
         echo ""
         echo -e "${CYAN}# Run interactively${NC}"
         echo "bash install.sh"
@@ -235,7 +235,7 @@ check_interactive_mode() {
         echo "Or use a profile directly:"
         echo ""
         echo -e "${CYAN}# Quick install with profile${NC}"
-        echo "curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s essential"
+        echo "curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s essential"
         echo ""
         echo "Available profiles: essential, developer, business, full, advanced"
         echo ""
@@ -880,7 +880,7 @@ main() {
             echo "Examples:"
             echo "  $0 essential"
             echo "  $0 --developer"
-            echo "  curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash -s essential"
+            echo "  curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash -s essential"
             echo ""
             echo "Without options, runs in interactive mode"
             exit 0

registry.json

@@ -1,6 +1,6 @@
 {
   "version": "1.0.0",
-  "repository": "https://github.com/darrenhinde/opencode-agents",
+  "repository": "https://github.com/darrenhinde/OpenAgents",
   "categories": {
     "essential": "Minimal components for basic functionality",
     "standard": "Standard components for typical use",

scripts/README.md

@@ -1,6 +1,6 @@
 # Scripts
 
-This directory contains utility scripts for the OpenCode Agents system.
+This directory contains utility scripts for the OpenAgents system.
 
 ## Available Scripts
 

scripts/tests/README.md

@@ -15,7 +15,7 @@ bash scripts/tests/test-compatibility.sh
 
 **Run remotely:**
 ```bash
-curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/scripts/tests/test-compatibility.sh | bash
+curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/scripts/tests/test-compatibility.sh | bash
 ```
 
 **What it tests:**

scripts/tests/test-compatibility.sh

@@ -162,7 +162,7 @@ fi
 # Test 12: Network connectivity
 echo ""
 echo "Test 12: Network Connectivity"
-if curl -fsSL --max-time 5 https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/README.md > /dev/null 2>&1; then
+if curl -fsSL --max-time 5 https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/README.md > /dev/null 2>&1; then
     pass "Network connectivity to GitHub works"
 else
     warn "Network connectivity test failed (may be offline)"
@@ -175,5 +175,5 @@ echo "╚═══════════════════════
 echo ""
 echo "Your system is compatible with the OpenCode installer."
 echo "You can safely run:"
-echo "  curl -fsSL https://raw.githubusercontent.com/darrenhinde/opencode-agents/main/install.sh | bash"
+echo "  curl -fsSL https://raw.githubusercontent.com/darrenhinde/OpenAgents/main/install.sh | bash"
 echo ""

update.sh

@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 
 #############################################################################
-# OpenCode Agents Updater
+# OpenAgents Updater
 # Updates existing OpenCode components to latest versions
 #############################################################################
 
@@ -15,7 +15,7 @@ CYAN='\033[0;36m'
 BOLD='\033[1m'
 NC='\033[0m'
 
-REPO_URL="https://raw.githubusercontent.com/darrenhinde/opencode-agents/main"
+REPO_URL="https://raw.githubusercontent.com/darrenhinde/OpenAgents/main"
 INSTALL_DIR=".opencode"
 
 print_success() { echo -e "${GREEN}✓${NC} $1"; }
@@ -26,7 +26,7 @@ print_header() {
     echo -e "${CYAN}${BOLD}"
     echo "╔════════════════════════════════════════════════════════════════╗"
     echo "║                                                                ║"
-    echo "║           OpenCode Agents Updater v1.0.0                     ║"
+    echo "║           OpenAgents Updater v1.0.0                           ║"
     echo "║                                                                ║"
     echo "╚════════════════════════════════════════════════════════════════╝"
     echo -e "${NC}"