Multiple installation methods for every setup — from a 30-second one-liner to Docker and source builds. Works on macOS, Linux, and Windows.
Fastest path — one command handles everything
curl -fsSL https://jaimeena.com/cvc/install.sh | bashNo prerequisites — installs uv and a managed Python automatically. Works on macOS 12+ and Ubuntu 20.04+.
cvc native CLI binary, Python 3.11+ (auto-detected or installed via winget on Windows / Homebrew on macOS / apt on Linux), and the tm-ai Python wheel from PyPI. After it finishes, just run cvc --version to confirm both the CLI and the Python wheel are installed.CVC is lightweight and runs on virtually every developer machine
Choose the method that fits your workflow
The standard Python package manager. Works with any Python 3.11+ install.
# All providers (recommended)
pip install "tm-ai[all]"
# Specific provider only
pip install "tm-ai[anthropic]" # Claude
pip install "tm-ai[openai]" # GPT
pip install "tm-ai[google]" # Gemini
pip install tm-ai # Core only (Ollama / LM Studio)The [all] extra installs Anthropic + OpenAI + Google SDK clients. For Ollama and LM Studio, only the core package is needed (they use plain HTTP).
10–100× faster than pip. Manages Python versions and virtual environments automatically.
# Install uv first (skip if already installed)
curl -LsSf https://astral.sh/uv/install.sh | sh # macOS / Linux
powershell -c "irm https://astral.sh/uv/install.ps1 | iex" # Windows
# Install CVC as a global tool (available in every terminal)
uv tool install "tm-ai[all]"
# Or install into a project virtualenv
uv add "tm-ai[all]"
# Upgrade
uv tool upgrade tm-aiIdeal if you use Anaconda, Miniconda, or Mamba for ML/data workflows.
# Create a dedicated environment
conda create -n cvc-env python=3.12 -y
conda activate cvc-env
# Install CVC via pip inside the conda env
pip install "tm-ai[all]"
cvc --versionFully isolated container. Great for CI/CD pipelines and reproducible environments.
# Interactive agent mode
docker run -it --rm \
-e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY \
-v $(pwd):/workspace -w /workspace \
ghcr.io/mannuking/cvc:latest
# Proxy server in background
docker run -d --name cvc-proxy \
-p 8000:8000 \
-e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY \
ghcr.io/mannuking/cvc:latest cvc serve-v $(pwd):/workspace. The .cvc/ state directory is created inside the mounted folder.For contributors and power users who want the latest features or want to modify CVC.
# Clone the private repository (requires access)
cd cvc
# With uv (recommended)
uv sync --extra dev
# With pip
pip install -e ".[dev]"
cvc --versionConnect CVC to your preferred AI provider
Best reasoning quality + prompt caching = 90% cheaper in practice
Install command
pip install "tm-ai[anthropic]"Environment variable
ANTHROPIC_API_KEYGet your API key at console.anthropic.com/settings/keys
# macOS / Linux / WSL
export ANTHROPIC_API_KEY="your-api-key-here"
# Windows PowerShell
$env:ANTHROPIC_API_KEY = "your-api-key-here"
# Or use CVC interactive wizard
cvc setupSupported models
claude-opus-4-6, claude-sonnet-4-5, claude-haiku-4-5
cvc setup walks you through provider and model selection interactively. Config is saved to ~/.cvc/config.json.Get CVC running in under 2 minutes
Verify installation
cvc --version
# Expected: cvc version 3.6.0 (or newer)
cvc doctor-env
# New command: full env + LLM diagnostics, ✅/⚠️/❌ with fix hintsInitialize CVC in your project
cd my-project
cvc init
# Creates .cvc/ directory (your time machine storage)
# Optionally add to .gitignore:
echo ".cvc/" >> .gitignoreStart the AI agent
cvc
# Starts the interactive AI coding session
# Key slash commands inside the agent:
# /save "checkpoint name" - save current brain state
# /branch feature-x - create an isolated branch
# /log - view all checkpoints
# /rewind <hash> - restore any checkpoint
# /status - current branch + HEADOr launch the Gateway for the full experience
cvc-gateway start
# Opens the CVC Dashboard in your browser
# Manage Agent, Proxy, MCP, Hive Mind, Swarm,
# Memory, Timeline, Models, and Settings
# — all from one unified web interfaceCVC works in four powerful modes
Built-in AI coding agent with 60+ tools — code, browser, vision, computer-use, cron, delegation. Just type cvc.
The full web dashboard — manage every subsystem from one UI.
Wrap Claude Code, Cursor, Aider with CVC time-travel.
IDE integration via Model Context Protocol.
The full CVC ecosystem after installation
After installing CVC, run cvc-gateway start to open the full web dashboard. Manage every subsystem from one UI: Chat, Operations (visual Commit/Branch/Merge/Restore/Recall/Diff), Models catalog (20+ models, click to switch), Memory & Context viewer, Hive Mind agent management, Proxy control, and comprehensive Settings (Autopilot mode, trust mode, agent behavior, hooks, plugins, Git integration, audit logs).
Multi-agent singularity — all agents share one memory. Create agents from a prompt, manually, or from 36+ templates. Scale to millions with zero conversation overhead.
Use CVC programmatically: from cvc.sdk import HiveMind, Agent. Register agents, commit, recall, and share to the hive — all from code.
Run any AI tool through CVC's time machine
| Tool | Launch Command | Notes |
|---|---|---|
| Claude Code | cvc launch claude | Auto-sets ANTHROPIC_BASE_URL. Zero config. |
| Aider | cvc launch aider | All Aider options work as normal + time-travel. |
| Cursor | cvc launch cursor | Opens Cursor with Base URL pointed to CVC proxy. |
| VS Code (MCP) | cvc mcp | Add to .vscode/mcp.json. Works with Copilot chat. |
| Windsurf | cvc mcp | Add as MCP server in Windsurf settings. |
| Continue / Cline | cvc serve | Point to http://127.0.0.1:8000/v1 as base URL. |
| Codex CLI | cvc launch codex | Set model_provider to cvc in codex config. |
| LangChain | cvc serve | Use CVC function-calling tools in your chain. |
// .vscode/mcp.json
{
"servers": {
"cvc": { "command": "cvc", "args": ["mcp"], "type": "stdio" }
}
}Stay on the latest version for new features and bug fixes
# CLI binary only (default)
cvc update
# CLI binary + Python wheel together (unified upgrade)
cvc update --with-python
# pip
pip install --upgrade tm-ai
# uv
uv tool upgrade tm-ai
# Check current versions (CLI + Python wheel)
cvc --version
# See what changed
cvc --changelogClean removal — CVC leaves nothing behind
# Remove CVC package
pip uninstall tm-ai
# or
uv tool uninstall tm-ai
# Remove global config (optional)
rm -rf ~/.cvc # macOS / Linux
Remove-Item -Recurse ~/.cvc # Windows PowerShell
# Remove project data (optional)
rm -rf .cvc # WARNING: deletes all your checkpoints.cvc/ folder contains all your saved checkpoints. Deleting it is irreversible. Export important sessions first with cvc export.Common issues and how to fix them instantly
"command not found: cvc" after install
Python scripts directory is not in PATH.
# Find where pip installs scripts:
python -m site --user-scripts
# Add to PATH (bash/zsh):
export PATH="$HOME/.local/bin:$PATH"
# Windows: add %APPDATA%\Python\Scripts to System PATHAPI key error / AuthenticationError
Check that your key is correctly set and has sufficient credits.
# Verify key is set
echo $ANTHROPIC_API_KEY
# Re-run setup
cvc setup
# Test connectivity
cvc doctor --check-apiOllama connection refused
Ollama service is not running. Start it first.
# macOS / Linux
ollama serve &
# Windows: Start from system tray or run ollama.exe serve
# Verify running:
curl http://localhost:11434/api/tagspip install fails with build errors
Some dependencies need a C compiler. Install build tools.
# Ubuntu / Debian
apt install build-essential python3-dev
# macOS
xcode-select --install
# Windows: install Visual C++ Build ToolsPermission denied on install
Use --user flag or a virtual environment.
# Install for current user only (no sudo needed)
pip install --user "tm-ai[all]"
# Or use a virtual environment
python -m venv .venv && source .venv/bin/activate
pip install "tm-ai[all]"CVC running slowly or high memory use
Use branching to reduce context size.
# Inside the agent, branch before large tasks
/branch big-refactor
# Merge back when done:
/checkout maincvc doctor for an automated health check — it tests Python version, config, Git, and API connectivity and tells you exactly what needs fixing.Read the full documentation or return to the CVC overview.