One CLI to Rule Them All.
Tired of juggling multiple AI coding assistants? CAM is a unified Python CLI to manage configurations, prompts, skills, and plugins for 17 AI assistants including Claude, Codex, Gemini, Qwen, Copilot, Blackbox, Goose, Continue, and more from a single, polished terminal interface.
Since CAM is not yet published to PyPI, install it locally:
# Clone the repository git clone https://github.com/Chat2AnyLLM/code-assistant-manager.git cd code-assistant-manager # Run the install script ./install.sh# Install using the install script directly ./install.sh # Or install from the web curl -fsSL https://raw.githubusercontent.com/Chat2AnyLLM/code-assistant-manager/main/install.sh | bash # Install from source directly git clone https://github.com/Chat2AnyLLM/code-assistant-manager.git cd code-assistant-manager pip install -e ".[dev]"-
Create your base config files:
mkdir -p ~/.config/code-assistant-manager cp code_assistant_manager/providers.json ~/.config/code-assistant-manager/providers.json touch ~/.env chmod 600 ~/.env
-
Set up your API keys in
.env:export ANTHROPIC_API_KEY="your-anthropic-key" export GITHUB_TOKEN="your-github-token" export GEMINI_API_KEY="your-gemini-key"
-
Source the environment file and verify setup:
source ~/.env cam doctor
-
Launch the interactive menu:
cam launch
-
Select your assistant and start coding!
CAM uses these main configuration files:
~/.config/code-assistant-manager/providers.json: endpoint/provider settings used bycam.~/.env: API keys and sensitive environment variables.~/.config/code-assistant-manager/config.yaml: repository-source config for skills, agents, and plugins.
- CAM loads
~/.config/code-assistant-manager/config.yamlfirst; if missing, it falls back to bundledcode_assistant_manager/config.yaml. - The file defines source lists for
skills,agents, andplugins. - Local JSON sources (
skill_repos.json,agent_repos.json,plugin_repos.json) are loaded first. - Remote sources are merged after local sources and do not override existing local keys.
- Remote responses are cached in
~/.cache/code-assistant-manager/repos(TTL controlled byconfig.yaml).
In the era of AI-driven development, developers often use multiple powerful assistants like Claude, GitHub Copilot, and Gemini. However, this leads to a fragmented and inefficient workflow:
- Scattered Configurations: Each tool has its own setup, API keys, and configuration files.
- Inconsistent Behavior: System prompts and custom instructions diverge, leading to different AI behaviors across projects.
- Wasted Time: Constantly switching between different CLIs and UIs is a drain on productivity.
CAM solves this by providing a single, consistent interface to manage everything, turning a chaotic toolkit into a cohesive and powerful development partner.
- Unified Management: One tool (
cam) to install, configure, and run all your AI assistants - Centralized Configuration: Manage all API keys and endpoint settings from a single
providers.jsonfile with environment variables in.env - Interactive TUI: A polished, interactive menu (
cam launch) for easy navigation and operation with arrow-key navigation - MCP Registry: Built-in registry with 381 pre-configured MCP servers ready to install across all supported tools
- Extensible Framework: Standardized architecture for managing agents, prompts, skills, and plugins
CAM supports 17 AI coding assistants:
| Assistant | Command | Install Method |
|---|---|---|
| Claude | claude | Shell script |
| Codex | codex | npm |
| Gemini | gemini | npm |
| Qwen | qwen | npm |
| Copilot | copilot | npm |
| CodeBuddy | codebuddy | npm |
| Droid | droid | Shell script |
| iFlow | iflow | npm |
| Crush | crush | npm |
| Cursor | cursor-agent | Shell script |
| Blackbox | blackbox | Shell script |
| Neovate | neovate | npm |
| Qoder | qodercli | npm |
| Zed | zed | Shell script |
| Goose | goose | Shell script |
| Continue | continue | npm |
| OpenCode | opencode | npm |
Manage standalone assistant configurations with markdown-based definitions and YAML front matter.
Reusable system prompts with fancy name generation synced across assistants at user or project scope.
Custom tools and functionalities for your agents (directory-based with SKILL.md).
Marketplace extensions for supported assistants (GitHub repos or local paths).
| Command | Alias | Description |
|---|---|---|
cam launch [TOOL] | l | Launch interactive TUI or a specific assistant |
cam doctor | d | Run diagnostic checks on environment and API keys |
cam agent | ag | Manage agent configurations (list, install, fetch from repos) |
cam prompt | p | Manage and sync system prompts across assistants |
cam skill | s | Install and manage skill collections |
cam plugin | pl | Manage marketplace extensions (plugins) |
cam mcp | m | Manage MCP servers (add, remove, list, install) |
cam upgrade [TARGET] | u | Upgrade tools (default: all) with parallel execution |
cam install [TARGET] | i | Alias for upgrade |
cam uninstall [TARGET] | un | Uninstall tools and backup configurations |
cam config | cf | Manage CAM's internal configuration files |
cam version | v | Display current version |
Note: non-boolean CLI options are long-form only. For example, use --config and --scope (not -c or -s).
CAM is governed by a speckit-driven development framework ensuring consistent, high-quality evolution with:
- Constitutional Principles: Unified interface, security-first design, TDD practices, extensible architecture, quality assurance
- Enterprise Security: Config-first approach eliminates shell injection vulnerabilities
- Comprehensive Testing: Enterprise-grade test suite with 1,423+ tests
- Automated Quality Assurance: Built-in complexity monitoring, file size limits, and CI/CD quality gates
- Discord: Join our community for discussions and support
- GitHub Issues: Report bugs and request features
- Contributing: See our Contributing Guidelines
This project is licensed under the MIT License.