CodePartner AI
CodePartner AI is a powerful agentic AI coding co-pilot that goes far beyond simple chat. Built with an "agent-first" philosophy, it autonomously plans, researches, edits code safely, runs commands, controls a browser, manages Git, and learns reusable Skills — all while following strict engineering best practices.
It supports 5 LLM providers (OpenAI, Azure, Anthropic, Google, Ollama), inline completions, MCP tools, semantic search, multi-agent collaboration, and a beautiful glassmorphism UI with tabs for Plan, Timeline, Artifacts, and Skills.
✨ Key Features
🧠 Agentic Capabilities
- Three Operating Modes:
- Fast Mode: Direct, concise responses and immediate actions
- Planning Mode: Generates detailed implementation plans + artifacts; waits for approval before editing
- Architect Mode: Drafts changes in-memory for review before bulk application
- Multi-Agent System: Automatically dispatches to specialized sub-agents (
researcher, code_expert, tester, writer)
- Proactive Skill Discovery: Suggests saving repeated workflows as reusable global Skills
- Timeline & Revert: Full audit trail of every tool action with one-click undo
- Safe File Operations:
read_file (always first), precise search/replace editing, create_file, grep_search
- Terminal & Testing: Runs shell commands, auto-detects and runs tests (
run_tests)
- Browser Control: Navigate, click, type, screenshot web pages for research (cross-platform via Puppeteer)
- Git Integration: Status, stage, AI commit messages, branches, and GitHub PR creation
- Web & Knowledge: DuckDuckGo search, document indexing (
index_docs + query_knowledge)
- MCP Support: Connect to external Model Context Protocol servers for custom tools
- Artifacts: Persistent storage of code, markdown, logs, and screenshots in
~/.codepartner
🔍 Smart Context
@workspace - Semantic TF-IDF search across your codebase@web - Real-time web search@file mentions and automatic context from active file + open tabs- Context compaction for long conversations
- Image/file attachments support
🎨 Premium UX
- Beautiful glassmorphism sidebar with tabs (Chat, Plan, Timeline, Artifacts, Skills)
- Inline ghost text completions (toggle with
Ctrl+Shift+I)
- Diff views, apply/insert/copy actions on code blocks
- Model selector, mode switcher, chat history with rename/delete
- Feedback button for bugs/features
🚀 Quick Start
- Install from the VS Code Marketplace
- Configure API:
- Open Command Palette (
Ctrl+Shift+P) → "Preferences: Open Settings (UI)"
- Search for "CodePartner"
- Set:
provider (e.g. openai, anthropic, ollama)apiKeymodel (e.g. gpt-4o, claude-3-5-sonnet-20241022, llama3)
- Open Sidebar: Click the robot icon in Activity Bar or press
Ctrl+L / Cmd+L
- Try it:
- Fast: "Explain this function"
- Plan: Switch to Planning mode and ask "Add user authentication with JWT"
- Use slash commands:
/fix, /explain, /test
Tip: Use @workspace for project-wide awareness and @web for research.
⌨️ Commands & Keybindings
| Command |
Title |
Keybinding |
Description |
codepartner.focus |
Focus on Chat Sidebar |
Ctrl+L / Cmd+L |
Open the sidebar |
codepartner.toggleInlineCompletions |
Toggle Inline Completions |
Ctrl+Shift+I / Cmd+Shift+I |
Enable/disable ghost text |
codepartner.explainSelection |
Explain Selected Code |
Ctrl+Shift+; / Cmd+Shift+; (when selection) |
Context-aware explanation |
codepartner.fixErrors |
Fix Errors in File |
Ctrl+Shift+' / Cmd+Shift+' |
Auto-fix diagnostics |
codepartner.generateTests |
Generate Tests for File |
- |
Create unit tests |
codepartner.showDebugLog |
Show Debug Log |
- |
Open output channel |
Slash Commands in Chat: /fix, /explain, /test, /compact, /clear
⚙️ Configuration
Key settings (full list in VS Code Settings):
| Setting |
Default |
Description |
codepartner.provider |
openai |
openai, azure, anthropic, google, ollama |
codepartner.apiKey |
`` |
Your API key |
codepartner.model |
gpt-4 |
Model name/deployment |
codepartner.apiEndpoint |
https://api.openai.com/v1 |
Custom endpoint |
codepartner.inlineCompletions |
false |
Enable ghost text completions |
codepartner.inlineCompletionDebounce |
500 |
Debounce ms for completions |
codepartner.mcpServers |
{} |
MCP server configurations |
codepartner.addAICoAuthor |
true |
Add Co-authored-by to Git commits |
codepartner.maxTokens |
4096 |
Max output tokens |
📁 Global Persistence (~/.codepartner)
- Skills: Reusable instruction sets (
.md files)
- Artifacts: Generated plans, code snippets, screenshots, logs
- Knowledge: Indexed documentation via
index_docs
- Global Instructions:
global_instructions.md applied to every chat
Skills and knowledge travel with you across all projects.
📸 Screenshots
(Screenshots will be added to the marketplace listing. Current assets in /media)
- Glassmorphism Sidebar with multiple tabs
- Planning Mode with task tracker
- Timeline showing tool executions and revert options
- Artifact gallery with screenshots
- Inline completions in editor
- Diff review workflow
🔄 How It Works (Agent Rules)
CodePartner follows strict internal guidelines:
- Always
read_file before edit_file
- Use exact text matching for search/replace
- Create full, complete implementations (no truncated code)
- In Planning Mode: Research → Create Plan Artifact → Wait for "proceed" → Execute → Verify with tests
- Explains reasoning in responses
- Uses markdown formatting
See full system prompt and tool definitions in src/extension.ts.
CodePartner excels in:
- Broadest provider support including local Ollama (no subscription required)
- Global reusable Skills and proactive suggestions
- Browser automation (unique vs Copilot)
- Timeline with undo and Architect drafting mode
- Zero lock-in — bring your own keys
For a detailed comparison (including gaps like inline completions in earlier versions), see codepartner_comparison_analysis.md.
Note: Inline completions were added in v2.0.2. Semantic search and MCP bring it closer to industry leaders.
📄 License
This project is licensed under the MIT License.
Developed with ❤️ by AnandShah
GitHub Repository | Report Issue | Marketplace Page
Happy Coding! Try asking CodePartner to "build a full-featured todo app with tests" in Planning mode.
