### Run AIBrain setup Source: https://myaibrain.org Initial configuration command to be run after installation. ```bash aibrain setup ``` -------------------------------- ### Local installation Source: https://myaibrain.org/docs/getting-started.html Manual installation for full control over service execution. ```bash $ pip install aibrain && aibrain setup $ cp config.json.example config.json ``` -------------------------------- ### Install all MCP servers and add individually Source: https://myaibrain.org/docs/guide.html Commands to install all MCP servers at once with 'aibrain mcp install' or add individual servers via 'claude mcp add'. The examples show adding aibrain-memory, it-support, and peer-discovery servers. ```bash # Install all MCP servers at once $ aibrain mcp install # Or add individually $ claude mcp add aibrain-memory -- python mcp_server.py --db aibrain.db $ claude mcp add it-support -- python mcp_it_support.py $ claude mcp add peer-discovery -- python mcp_peer_discovery.py ``` -------------------------------- ### Install via pip Source: https://myaibrain.org/docs/getting-started.html The simplest installation method providing the CLI, MCP server, and memory system. ```bash $ pip install aibrain $ aibrain setup ``` -------------------------------- ### Launch services Source: https://myaibrain.org/docs/getting-started.html Start the services using the provided scripts for your operating system. ```bash # Windows > start.bat # Unix / macOS $ ./start.sh ``` -------------------------------- ### Install via Docker Source: https://myaibrain.org/docs/getting-started.html Runs the full stack including backend and frontend dashboard in containers. ```bash $ pip install aibrain && aibrain setup $ cp config.json.example config.json # Edit config.json with your settings $ docker compose up --build ``` -------------------------------- ### Install AIBrain via pip Source: https://myaibrain.org Use pip to install the AIBrain Python package. ```bash pip install aibrain ``` -------------------------------- ### Install AIBrain on Mac, Linux, or WSL Source: https://myaibrain.org Use the curl command to install AIBrain on Unix-based systems. ```bash curl -fsSL https://myaibrain.org/install.sh | bash ``` -------------------------------- ### Install AIBrain on Windows PowerShell Source: https://myaibrain.org Use the PowerShell command to install AIBrain on Windows systems. ```powershell irm https://myaibrain.org/install.ps1 | iex ``` -------------------------------- ### Install MCP dependencies Source: https://myaibrain.org/docs/getting-started.html Install required packages for the MCP server functionality. ```bash $ pip install mcp sentence-transformers sqlite-vec ``` -------------------------------- ### Start services manually Source: https://myaibrain.org/docs/getting-started.html Run the backend and frontend services manually in separate terminals. ```bash # Terminal 1 — Backend $ cd backend $ pip install -r ../requirements.txt $ python -m uvicorn main:app --host 0.0.0.0 --port 8001 --reload # Terminal 2 — Frontend (optional) $ cd frontend $ npm install && npm run dev -- --host ``` -------------------------------- ### Initialize and Use Brain API Source: https://myaibrain.org A basic example showing how to initialize the Brain, add a memory, and perform a search. ```python from aibrain import Brain brain = Brain() brain.add("I love tennis", user_id="alice") brain.search("hobbies", user_id="alice") ``` -------------------------------- ### Marketplace Operations Source: https://myaibrain.org/docs/guide.html Commands for packaging, publishing, searching, installing, and viewing revenue for brain configurations. ```bash $ aibrain marketplace package --name "devops-brain" # Package for sale $ aibrain marketplace publish devops-brain.brain # Publish $ aibrain marketplace search "machine learning" # Browse $ aibrain marketplace install # Install a brain $ aibrain marketplace revenue # Revenue dashboard ``` -------------------------------- ### View workflow dependency map Source: https://myaibrain.org/docs/workflows.html Use the deps command to view the full dependency map or dependencies for a specific workflow. The example shows viewing dependencies for contradiction_detector. ```bash # View the full dependency map $ aibrain workflows deps # View dependencies for a specific workflow $ aibrain workflows deps contradiction_detector ``` -------------------------------- ### Define schedules in scheduled_jobs.json Source: https://myaibrain.org/docs/workflows.html Manually define schedules for workflows in the scheduled_jobs.json file. Each entry specifies whether the workflow is enabled, its cron expression, and the script path. The example shows a weather briefing at 6:30 AM daily and memory consolidation at 3:00 AM on Sundays. ```json { "weather_briefing": { "enabled": true, "cron": "30 6 * * *", "script": "workflows/weather_briefing.py" }, "memory_consolidation": { "enabled": true, "cron": "0 3 * * 0", "script": "workflows/memory_consolidation.py" } } ``` -------------------------------- ### AIBrain CLI: Search, Summary, Export, Import, Forget Source: https://myaibrain.org/docs/guide.html Shows the AIBrain CLI commands for searching memories, getting memory stats, exporting/importing the brain, and deleting memories. Uses '--confirm' flag for the forget command. ```bash aibrain search "kubernetes deployment" # Search memories aibrain summary # Memory stats aibrain brain export # Export as JSON aibrain brain import backup.json # Import from file aibrain forget "outdated topic" --confirm # Delete memories ``` -------------------------------- ### Enable recommended starter set with aibrain workflows enable --recommended Source: https://myaibrain.org/docs/workflows.html Command to enable the recommended starter set of workflows. The set includes 7 agent improvement, 5 personal intelligence, and 2 utility workflows (daily planner + weekly review). ```bash # Enable the recommended starter set $ aibrain workflows enable --recommended # Sync to your OS scheduler $ aibrain workflows sync # Preview what would be created (optional) $ aibrain workflows sync --dry-run ``` -------------------------------- ### AIBrain workflow commands Source: https://myaibrain.org/docs/guide.html Shows how to list workflows, enable the recommended starter set, sync OS scheduled tasks, and run a specific workflow immediately. Workflows use the OS scheduler (cron on Linux, schtasks on Windows, launchctl on macOS) and require no daemon process. ```bash $ aibrain workflows list # Show all workflows + status $ aibrain workflows enable --recommended # Enable the starter set $ aibrain workflows sync # Create OS scheduled tasks $ aibrain workflows run weekly_wins # Run one immediately ``` -------------------------------- ### Manage aibrain licenses via CLI Source: https://myaibrain.org/docs/guide.html Use these commands to view current pricing details or activate a license key. ```bash $ aibrain license tiers # See pricing details $ aibrain license activate # Activate your license ``` -------------------------------- ### Execute Swarm Training Source: https://myaibrain.org/docs/guide.html Commands to initialize a multi-agent swarm and harvest the resulting training data. ```bash $ aibrain mesh swarm create research -n 100 # Create 100-agent swarm $ aibrain mesh swarm harvest research # Merge swarm results ``` -------------------------------- ### Configure environment variables Source: https://myaibrain.org/docs/getting-started.html Optional step to set environment overrides. ```bash $ cp .env.example .env # Edit .env with any overrides ``` -------------------------------- ### Configure MCP server Source: https://myaibrain.org/docs/getting-started.html Add the AIBrain memory server to your MCP configuration file. ```json { "mcpServers": { "aibrain-memory": { "command": "python", "args": ["/path/to/aibrain/mcp_server.py"] } } } ``` -------------------------------- ### Create custom workflow by subclassing UserWorkflow Source: https://myaibrain.org/docs/workflows.html Create a custom workflow by subclassing UserWorkflow. Define the name, schedule (cron), description, and implement the run method. The run method can read from the brain, process data, and store results back. ```python # my_workflow.py from aibrain.workflows import UserWorkflow class MyCustomWorkflow(UserWorkflow): name = "my_custom_workflow" schedule = "0 9 * * *" # 9am daily description = "My custom daily workflow" def run(self, brain): # Read from the brain memories = brain.search("project status") # Do your work summary = self.process(memories) # Write back to the brain brain.store( content=summary, memory_type="project", importance=7 ) ``` -------------------------------- ### Manage Brain Packs Source: https://myaibrain.org/docs/getting-started.html Commands to browse, activate, and check active domain specialization bundles. ```bash $ aibrain packs # Browse all packs $ aibrain packs activate developer # Activate the developer pack $ aibrain packs active # See what's active ``` -------------------------------- ### Enable workflow with auto-enabled dependencies Source: https://myaibrain.org/docs/workflows.html Enabling a Tier 3 workflow automatically enables its Tier 2 dependencies. The output shows the enabled workflow and the list of auto-enabled dependencies. ```bash $ aibrain workflows enable contradiction_detector Enabled: contradiction_detector Auto-enabled dependencies: correction_learner memory_hygiene user_model ``` -------------------------------- ### Sync workflows to OS scheduler Source: https://myaibrain.org/docs/workflows.html Creates native scheduled tasks from enabled workflows. Use --dry-run to preview changes without applying. On Linux, entries are added to the user crontab; on Windows, tasks are created via schtasks; on macOS, launchctl plist files are used. ```bash # Create native scheduled tasks from enabled workflows $ aibrain workflows sync # Preview changes without applying $ aibrain workflows sync --dry-run ``` -------------------------------- ### AIBrain pack management commands Source: https://myaibrain.org/docs/guide.html Commands to browse, activate, and show active Brain Packs. Use 'aibrain packs' to list available packs, 'aibrain packs activate developer' to activate a specific pack, and 'aibrain packs active' to display currently active packs. ```bash $ aibrain packs # Browse available packs $ aibrain packs activate developer # Activate a pack $ aibrain packs active # Show active packs ``` -------------------------------- ### Manage AIBrain Mesh Agents Source: https://myaibrain.org/docs/guide.html Commands to check status, register agents, merge consensus, and distribute brain updates across the mesh. ```bash $ aibrain mesh status # Show mesh agent status $ aibrain mesh register myagent agent.db # Register an agent $ aibrain mesh merge # Merge all agents (consensus) $ aibrain mesh distribute # Push merged brain to all ``` -------------------------------- ### Pull Ollama model Source: https://myaibrain.org/docs/getting-started.html Command to pull a local model for zero-cost inference. ```bash $ ollama pull llama3.2 ``` === COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.