From agent-brain
Initializes Agent Brain for the project by creating .agent-brain/ directory with config.json and placeholders for chroma_db/ and bm25_index/. Supports --path, --host, --port, --force, --state-dir options.
How this command is triggered — by the user, by Claude, or both
Slash command
/agent-brain:agent-brain-initThe summary Claude sees in its command listing — used to decide when to auto-load this command
# Initialize Agent Brain Project ## Purpose Initializes the current project for Agent Brain by creating the necessary configuration directory and files. This sets up per-project isolation, allowing each project to have its own Agent Brain instance with separate configuration and data. ## Usage ### Parameters | Parameter | Required | Default | Description | |-----------|----------|---------|-------------| | --path / -p | No | Auto-detect | Project path (auto-detects git root or project markers) | | --host | No | 127.0.0.1 | Server bind host | | --port | No | Auto-select | Preferred se...
Initializes the current project for Agent Brain by creating the necessary configuration directory and files. This sets up per-project isolation, allowing each project to have its own Agent Brain instance with separate configuration and data.
/agent-brain:agent-brain-init [--path <path>] [--host <host>] [--port <port>] [--force] [--state-dir <dir>] [--json]
| Parameter | Required | Default | Description |
|---|---|---|---|
| --path / -p | No | Auto-detect | Project path (auto-detects git root or project markers) |
| --host | No | 127.0.0.1 | Server bind host |
| --port | No | Auto-select | Preferred server port (disables auto-port if set) |
| --force / -f | No | false | Overwrite existing configuration |
| --state-dir / -s | No | .agent-brain | Custom state directory for index data |
| --json | No | false | Output as JSON |
/agent-brain:agent-brain-init
/agent-brain:agent-brain-init --path /my/project
/agent-brain:agent-brain-init --port 8080
/agent-brain:agent-brain-init --state-dir /custom/path
/agent-brain:agent-brain-init --force
agent-brain init
agent-brain init --path /my/project
agent-brain init --port 8080
agent-brain init --state-dir /custom/path
agent-brain init --force
This creates the .agent-brain/ directory structure in the project root.
ls -la .agent-brain/
Agent Brain Initialization
==========================
Initializing Agent Brain for current project...
Running: agent-brain init
Created directory structure:
.agent-brain/
config.json - Project configuration
chroma_db/ - Vector store (created on first index)
bm25_index/ - Keyword index (created on first index)
Project initialized successfully!
Configuration file: .agent-brain/config.json
{
"project_name": "my-project",
"created_at": "2025-01-31T12:00:00Z",
"mode": "project"
}
Next steps:
1. Start server: /agent-brain:agent-brain-start
2. Index documents: /agent-brain:agent-brain-index ./docs
3. Search: /agent-brain:agent-brain-search "your query"
The initialization creates the following structure:
.agent-brain/
config.json # Project configuration (bind_host, port, chunk settings, exclude patterns)
data/
chroma_db/ # ChromaDB vector store (created on index)
bm25_index/ # BM25 keyword index (created on index)
llamaindex/ # LlamaIndex persistence (created on index)
logs/ # Server logs
Contains project-specific settings:
{
"bind_host": "127.0.0.1",
"port_range_start": 8000,
"port_range_end": 8100,
"auto_port": true,
"chunk_size": 512,
"chunk_overlap": 50,
"exclude_patterns": [
"**/node_modules/**",
"**/__pycache__/**",
"**/.venv/**",
"**/venv/**",
"**/.git/**",
"**/dist/**",
"**/build/**",
"**/target/**"
],
"project_root": "/path/to/project"
}
Create a config.yaml in the project's .agent-brain/ directory for project-specific provider settings:
# .agent-brain/config.yaml
project:
state_dir: null # Use default
embedding:
provider: "openai"
api_key: "sk-proj-..." # Or use api_key_env: "OPENAI_API_KEY"
summarization:
provider: "anthropic"
api_key: "sk-ant-..."
Note: Agent Brain searches for config.yaml in multiple locations. Project-level config takes precedence over user-level (~/.agent-brain/config.yaml).
Created when server starts, contains:
{
"port": 49321,
"pid": 12345,
"started_at": "2025-01-31T12:00:00Z",
"state_dir": ".agent-brain"
}
Project already initialized.
Existing configuration found at: .agent-brain/config.json
Options:
- Continue using existing configuration
- Reset with: rm -rf .agent-brain && agent-brain init
- Check status: agent-brain status
Error: Cannot create directory .agent-brain/
Permission denied.
Solutions:
1. Check directory permissions: ls -la .
2. Ensure write access to current directory
3. Create manually: mkdir -p .agent-brain
4. Check if .claude exists and is writable
Warning: No git repository or project markers found.
Agent Brain will initialize here, but consider:
1. Navigate to your project root first
2. Initialize git: git init
3. Then run: agent-brain init
Error: Cannot create .claude directory
The parent directory may not exist or is not writable.
Check:
1. Current directory exists: pwd
2. You have write permissions: ls -la .
3. Disk is not full: df -h .
To completely reset a project's Agent Brain configuration:
# Stop server if running
agent-brain stop
# Remove existing configuration
rm -rf .agent-brain
# Re-initialize
agent-brain init
Warning: This deletes all indexed documents. You will need to re-index after re-initialization.
Each project should be initialized separately. Agent Brain uses the .agent-brain/ directory to isolate:
This allows running multiple Agent Brain instances for different projects simultaneously, each on its own port.
npx claudepluginhub spillwavesolutions/agent-brain --plugin agent-brain/initInitializes hierarchical AGENTS.md for AI agent documentation and .agents.yml config, gathering tech stack, experience level, workflow, and stack-specific details via questions.
/initCreates or updates AgentBridge project config files (.agentbridge/config.json and collaboration.md) in the current workspace with defaults for daemon ports, agents, markers, turn coordination, roles, thinking patterns, communication, and review process.
/initInitializes a new project with Claude Code agent system, best practices, and framework setup.
/setup-agentsScaffolds a multi-agent AI configuration for any repo by scanning the codebase and interviewing the developer. Generates agent configs for Copilot, Claude Code, Cursor, Codex, and Windsurf. Also supports upgrade, add, and review modes.
/ai-agents-setupInitializes multi-agent orchestration project using @ai-sdk-tools/agents, creating directory structure, TypeScript agent files for coordinator/researcher/coder/reviewer, and installing Node.js dependencies.