/agent-brain-start
Output as JSON
> /plugin marketplace add SpillwaveSolutions/agent-brain > /plugin install agent-brain@agent-brain-marketplace
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/agent-brain-start
Context preview
What this command does when you run it.
Output as JSON
Command definition
agent-brain-start.mdname: agent-brain-start
description: Start the Agent Brain server for this project
parameters:
- name: path
description: Project path (default auto-detect project root)
required: false
- name: host
description: Server bind host (overrides config)
required: false
- name: port
description: Server port (overrides config)
required: false
- name: foreground
description: Run in foreground instead of daemonizing
required: false
default: false
- name: timeout
description: Startup timeout in seconds
required: false
default: 30
- name: strict
description: Fail on critical provider configuration errors
required: false
default: false
- name: json
description: Output as JSON
required: false
default: false
context: fork
agent: setup-assistant
skills:
- using-agent-brain
last_validated: 2026-03-16Agent Brain Start
Purpose
Starts the Agent Brain server for the current project. The server provides:
- Document indexing and storage
- Hybrid, semantic, and keyword search
- Multi-instance support with automatic port allocation
Usage
/agent-brain:agent-brain-start [--path <dir>] [--host <host>] [--port <port>] [--foreground] [--strict] [--json]
Parameters
| Parameter | Required | Default | Description | |-----------|----------|---------|-------------| | --path, -p | No | auto-detect | Project path | | --host | No | 127.0.0.1 | Server bind host (overrides config) | | --port | No | auto-select (8000-8100) | Server port (overrides config) | | --foreground, -f | No | false | Run in foreground (don't daemonize) | | --timeout | No | 30 | Startup timeout in seconds | | --strict | No | false | Fail on critical provider config errors | | --json | No | false | Output as JSON |
Execution
Pre-flight Check
Verify the project is initialized:
# Check for .agent-brain/ directory
ls -la .agent-brain/
If not initialized:
agent-brain init
Start Server
# Start in background (default, recommended)
agent-brain start
# Start on a specific port
agent-brain start --port 8080
# Start in foreground for debugging
agent-brain start --foreground
# Start with strict mode (fail on missing API keys)
agent-brain start --strict
# Start for a specific project path
agent-brain start --path /my/project
# JSON output for scripting
agent-brain start --json
Verify Server Started
agent-brain status
Output
Successful Start
Agent Brain Server Running
URL: http://127.0.0.1:8000
PID: 12345
Project: /home/user/my-project
Log: /home/user/my-project/.agent-brain/logs/server.log
Next steps:
- Query: agent-brain query 'search term' --url http://127.0.0.1:8000
- Stop: agent-brain stop
JSON Output
{
"status": "started",
"base_url": "http://127.0.0.1:8000",
"pid": 12345,
"project_root": "/home/user/my-project",
"log_file": "/home/user/my-project/.agent-brain/logs/server.log"
}Runtime Configuration
The server creates a runtime file (in the state directory) with:
{
"schema_version": "1.0",
"mode": "project",
"project_root": "/home/user/my-project",
"instance_id": "a1b2c3d4e5f6",
"base_url": "http://127.0.0.1:8000",
"bind_host": "127.0.0.1",
"port": 8000,
"pid": 12345,
"started_at": "2026-01-31T10:30:00+00:00"
}This file enables automatic server discovery for CLI commands.
Error Handling
Project Not Initialized
Error: Project not initialized at /home/user/my-project
Run 'agent-brain init' to initialize the project.
**Resolution**:
agent-brain init
agent-brain start
Server Already Running
If a server is already running for this project, the command reports the existing URL instead of starting a new one:
Server Running
Server already running!
URL: http://127.0.0.1:8000
PID: 12345
Project: /home/user/my-project
**Resolution**:
- Use the existing server, or
- Stop and restart: `agent-brain stop && agent-brain start`
No Available Port
Error: No available port in range 8000-8100
**Resolution**: Specify a port explicitly or stop other instances:
agent-brain start --port 9000
# or
agent-brain list --all
agent-brain stop
Missing API Keys
The server starts even without API keys, but provider-dependent features will be unavailable. Use `--strict` to force failure on missing keys.
**Resolution**: Set the API key via config file or environment variable and restart.
**Option 1: Config file** (`.agent-brain/config.yaml` or `~/.config/agent-brain/config.yaml`):
embedding:
provider: "openai"
api_key_env: "OPENAI_API_KEY"
**Option 2: Environment variable**:
export OPENAI_API_KEY="sk-proj-..."
Then restart:
agent-brain stop
agent-brain start
Permission Denied
Permission Error: [Errno 13] Permission denied: ...
**Resolution**:
mkdir -p .agent-brain
chmod 755 .agent-brain
agent-brain start
Post-Start Tasks
1. Verify Server Health
agent-brain status
2. Index Documents (if first time)
# Index documentation
agent-brain index docs/
# Index code with type preset
agent-brain index src/ --include-type python
3. Test Search
agent-brain query "test query" --mode hybrid
Server Behavior
Project Root Resolution
The server auto-detects the project root by: 1. Git repository root (`git rev-parse --show-toplevel`) 2. Walking up looking for `.agent-brain/` directory 3. Walking up looking for `.claude/` directory 4. Walking up looking for `pyproject.toml` 5. Falling back to current working directory
Port Allocation
By default, `auto_port` is enabled and the server finds an available port in the 8000-8100 range. Override with `--port` or disable auto-port in `config.json`.
Stale State Cleanup
If a previous server died without cleanup, `agent-brain start` automatically detects and cleans up
Read more
name: agent-brain-start
description: Start the Agent Brain server for this project
parameters:
- name: path
description: Project path (default auto-detect project root)
required: false
- name: host
description: Server bind host (overrides config)
required: false
- name: port
description: Server port (overrides config)
required: false
- name: foreground
description: Run in foreground instead of daemonizing
required: false
default: false
- name: timeout
description: Startup timeout in seconds
required: false
default: 30
- name: strict
description: Fail on critical provider configuration errors
required: false
default: false
- name: json
description: Output as JSON
required: false
default: false
context: fork
agent: setup-assistant
skills:
- using-agent-brain
last_validated: 2026-03-16Agent Brain Start
Purpose
Starts the Agent Brain server for the current project. The server provides:
- Document indexing and storage
- Hybrid, semantic, and keyword search
- Multi-instance support with automatic port allocation
Usage
/agent-brain:agent-brain-start [--path <dir>] [--host <host>] [--port <port>] [--foreground] [--strict] [--json]
Parameters
| Parameter | Required | Default | Description | |-----------|----------|---------|-------------| | --path, -p | No | auto-detect | Project path | | --host | No | 127.0.0.1 | Server bind host (overrides config) | | --port | No | auto-select (8000-8100) | Server port (overrides config) | | --foreground, -f | No | false | Run in foreground (don't daemonize) | | --timeout | No | 30 | Startup timeout in seconds | | --strict | No | false | Fail on critical provider config errors | | --json | No | false | Output as JSON |
Execution
Pre-flight Check
Verify the project is initialized:
# Check for .agent-brain/ directory ls -la .agent-brain/
If not initialized:
agent-brain init
Start Server
# Start in background (default, recommended) agent-brain start # Start on a specific port agent-brain start --port 8080 # Start in foreground for debugging agent-brain start --foreground # Start with strict mode (fail on missing API keys) agent-brain start --strict # Start for a specific project path agent-brain start --path /my/project # JSON output for scripting agent-brain start --json
Verify Server Started
agent-brain status
Output
Successful Start
Agent Brain Server Running URL: http://127.0.0.1:8000 PID: 12345 Project: /home/user/my-project Log: /home/user/my-project/.agent-brain/logs/server.log Next steps: - Query: agent-brain query 'search term' --url http://127.0.0.1:8000 - Stop: agent-brain stop
JSON Output
{
"status": "started",
"base_url": "http://127.0.0.1:8000",
"pid": 12345,
"project_root": "/home/user/my-project",
"log_file": "/home/user/my-project/.agent-brain/logs/server.log"
}Runtime Configuration
The server creates a runtime file (in the state directory) with:
{
"schema_version": "1.0",
"mode": "project",
"project_root": "/home/user/my-project",
"instance_id": "a1b2c3d4e5f6",
"base_url": "http://127.0.0.1:8000",
"bind_host": "127.0.0.1",
"port": 8000,
"pid": 12345,
"started_at": "2026-01-31T10:30:00+00:00"
}This file enables automatic server discovery for CLI commands.
Error Handling
Project Not Initialized
Error: Project not initialized at /home/user/my-project Run 'agent-brain init' to initialize the project.
**Resolution**:
agent-brain init agent-brain start
Server Already Running
If a server is already running for this project, the command reports the existing URL instead of starting a new one:
Server Running Server already running! URL: http://127.0.0.1:8000 PID: 12345 Project: /home/user/my-project
**Resolution**:
- Use the existing server, or
- Stop and restart: `agent-brain stop && agent-brain start`
No Available Port
Error: No available port in range 8000-8100
**Resolution**: Specify a port explicitly or stop other instances:
agent-brain start --port 9000 # or agent-brain list --all agent-brain stop
Missing API Keys
The server starts even without API keys, but provider-dependent features will be unavailable. Use `--strict` to force failure on missing keys.
**Resolution**: Set the API key via config file or environment variable and restart.
**Option 1: Config file** (`.agent-brain/config.yaml` or `~/.config/agent-brain/config.yaml`):
embedding: provider: "openai" api_key_env: "OPENAI_API_KEY"
**Option 2: Environment variable**:
export OPENAI_API_KEY="sk-proj-..."
Then restart:
agent-brain stop agent-brain start
Permission Denied
Permission Error: [Errno 13] Permission denied: ...
**Resolution**:
mkdir -p .agent-brain chmod 755 .agent-brain agent-brain start
Post-Start Tasks
1. Verify Server Health
agent-brain status
2. Index Documents (if first time)
# Index documentation agent-brain index docs/ # Index code with type preset agent-brain index src/ --include-type python
3. Test Search
agent-brain query "test query" --mode hybrid
Server Behavior
Project Root Resolution
The server auto-detects the project root by: 1. Git repository root (`git rev-parse --show-toplevel`) 2. Walking up looking for `.agent-brain/` directory 3. Walking up looking for `.claude/` directory 4. Walking up looking for `pyproject.toml` 5. Falling back to current working directory
Port Allocation
By default, `auto_port` is enabled and the server finds an available port in the 8000-8100 range. Override with `--port` or disable auto-port in `config.json`.
Stale State Cleanup
If a previous server died without cleanup, `agent-brain start` automatically detects and cleans up
A RAG-based (Retrieval-Augmented Generation) document indexing and semantic search system for AI agents and applications. Agent Brain enables intelligent querying of documentation and source code using natural language.
Other commands on agent-brain.
ag-install-local
Local build-and-install of Agent Brain server + CLI + plugin for rapid testing.
ag-remove-local-instal…
Remove all local Agent Brain installations, caches, and plugin artifacts.
implement-python
Senior Python engineer implementation command. Launches a background agent with full Python development capabilities and access…
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task…

