Simple, step-by-step installation for all platforms.
macOS
brew install nodeUbuntu/Debian
curl -fsSL https://deb.nodesource.com/setup_20.x | sudo -E bash -
sudo apt-get install -y nodejsWindows Download from nodejs.org
npm install -g lynkrlynkr startThat's it! Lynkr is now running on http://localhost:8081
On first run, Lynkr creates a .env file in ~/.lynkr/.env
-
Install Ollama
# macOS/Linux curl -fsSL https://ollama.com/install.sh | sh # Or download from https://ollama.com
-
Pull a model
ollama pull qwen2.5-coder:latest
-
Edit
~/.lynkr/.envMODEL_PROVIDER=ollama FALLBACK_ENABLED=false OLLAMA_MODEL=qwen2.5-coder:latest OLLAMA_ENDPOINT=http://localhost:11434 # Recommended settings POLICY_MAX_STEPS=50 POLICY_MAX_TOOL_CALLS=100 POLICY_SAFE_COMMANDS_ENABLED=false -
Restart Lynkr
lynkr start
-
Get API key from openrouter.ai
-
Edit
~/.lynkr/.envMODEL_PROVIDER=openrouter OPENROUTER_API_KEY=sk-or-v1-your-key-here FALLBACK_ENABLED=false # Recommended settings POLICY_MAX_STEPS=50 POLICY_MAX_TOOL_CALLS=100 -
Restart Lynkr
lynkr start
-
Get AWS credentials
-
Edit
~/.lynkr/.envMODEL_PROVIDER=bedrock AWS_BEDROCK_API_KEY=your-aws-key AWS_BEDROCK_MODEL_ID=anthropic.claude-3-5-sonnet-20241022-v2:0 FALLBACK_ENABLED=false # Recommended settings POLICY_MAX_STEPS=50 POLICY_MAX_TOOL_CALLS=100 -
Restart Lynkr
lynkr start
export ANTHROPIC_BASE_URL=http://localhost:8081
export ANTHROPIC_API_KEY=dummy
claude "write hello world in python"Add to your ~/.zshrc or ~/.bashrc to make permanent:
echo 'export ANTHROPIC_BASE_URL=http://localhost:8081' >> ~/.zshrc
echo 'export ANTHROPIC_API_KEY=dummy' >> ~/.zshrc
source ~/.zshrc- Open Cursor Settings
- Go to Models section
- Set Base URL:
http://localhost:8081/v1 - Set API Key:
any-value - Click Save
Edit ~/.codex/config.toml:
model_provider = "lynkr"
[model_providers.lynkr]
base_url = "http://localhost:8081/v1"
wire_api = "responses"brew tap fast-editor/lynkr
brew install lynkr
lynkr --version
lynkr startUpgrade later with brew update && brew upgrade lynkr — the formula tracks the latest lynkr npm release automatically.
git clone https://github.com/Fast-Editor/Lynkr.git
cd Lynkr
docker-compose up -dYour .env file is in the repo root.
git clone https://github.com/Fast-Editor/Lynkr.git
cd Lynkr
npm install
cp .env.example .env
npm startEdit .env in the repo directory.
curl http://localhost:8081/healthShould return: {"status":"healthy"}
export ANTHROPIC_BASE_URL=http://localhost:8081
export ANTHROPIC_API_KEY=dummy
claude "say hello"Should get a response from your configured model.
# If installed via npm
lynkr start
# Look for:
# [Ollama] Server ready, model "qwen2.5-coder:latest" available
# Claude→Databricks proxy listening on http://localhost:8081NPM global bin directory not in PATH.
Fix:
# Find npm global bin path
npm config get prefix
# Add to PATH (example for /usr/local)
echo 'export PATH="/usr/local/bin:$PATH"' >> ~/.zshrc
source ~/.zshrcDependencies not installed.
Fix:
npm install -g lynkr --forceNPM doesn't have write permissions.
Fix (macOS/Linux):
sudo npm install -g lynkrBetter fix (avoid sudo):
mkdir ~/.npm-global
npm config set prefix '~/.npm-global'
echo 'export PATH="~/.npm-global/bin:$PATH"' >> ~/.zshrc
source ~/.zshrc
npm install -g lynkrSomething else is using port 8081.
Fix: Edit ~/.lynkr/.env
PORT=8082Then update your tools to use http://localhost:8082
Ollama not running.
Fix:
# macOS/Linux - check if running
ps aux | grep ollama
# Start Ollama
ollama serve
# Or restart
pkill ollama && ollama servenpm update -g lynkrOr force reinstall:
npm uninstall -g lynkr
npm install -g lynkrnpm uninstall -g lynkr
rm -rf ~/.lynkrNeed help? Open an issue or ask in Discussions