Skip to main content

Agent Brain CLI - Command-line interface for managing AI agent memory and knowledge retrieval

Project description

Agent Brain CLI

Command-line interface for managing AI agent memory and knowledge retrieval with the Agent Brain RAG server.

Agent Brain (formerly doc-serve) is an intelligent document indexing and semantic search system designed to give AI agents long-term memory. This CLI provides a convenient way to manage your Agent Brain server and knowledge base.

PyPI version Python 3.10+ License: MIT

Why Agent Brain?

AI agents need persistent memory to be truly useful. Agent Brain provides the retrieval infrastructure that enables context-aware, knowledge-grounded AI interactions.

Search Capabilities

Search Type Description Best For
Semantic Search Natural language queries using OpenAI embeddings Conceptual questions, related content
Keyword Search (BM25) Traditional keyword matching with TF-IDF ranking Exact matches, technical terms
Hybrid Search Combines vector + BM25 approaches General-purpose queries
GraphRAG Knowledge graph retrieval Understanding relationships

Installation

pip install agent-brain-cli

Quick Start

agent-brain init          # Initialize project
agent-brain start         # Start server
agent-brain index ./docs  # Index documents
agent-brain query "search term"

Note: The legacy command doc-svr-ctl is still available but deprecated. Please use agent-brain for new installations.

Development Installation

cd agent-brain-cli
poetry install

Usage

# Check server status
agent-brain status

# Search documents
agent-brain query "how to use python"

# Index documents from a folder
agent-brain index ./docs

# Reset/clear the index
agent-brain reset --yes

Configuration

Set the server URL via environment variable:

export AGENT_BRAIN_URL=http://localhost:8000

Or use the --url flag:

agent-brain --url http://localhost:8000 status

Note: The legacy environment variable DOC_SERVE_URL is still supported for backwards compatibility.

Commands

Server Management

Command Description
init Initialize project for Agent Brain (creates .claude/doc-serve/)
start Start the Agent Brain server for current project
stop Stop the running server
list List all running Agent Brain instances
status Check server health and indexing status

Data Management

Command Description
query Search indexed documents
index Start indexing documents from a folder
reset Clear all indexed documents

Options

All commands support:

  • --url - Server URL (or AGENT_BRAIN_URL / DOC_SERVE_URL env var)
  • --json - Output as JSON for scripting

Example Workflow

# 1. Initialize a new project
cd my-project
agent-brain init

# 2. Start the server
agent-brain start

# 3. Index your documentation
agent-brain index ./docs ./src

# 4. Query your knowledge base
agent-brain query "How does authentication work?"

# 5. Stop when done
agent-brain stop

Documentation

Release Information

Related Packages

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agent_brain_cli-2.0.0.tar.gz (18.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agent_brain_cli-2.0.0-py3-none-any.whl (26.1 kB view details)

Uploaded Python 3

File details

Details for the file agent_brain_cli-2.0.0.tar.gz.

File metadata

  • Download URL: agent_brain_cli-2.0.0.tar.gz
  • Upload date:
  • Size: 18.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.3

File hashes

Hashes for agent_brain_cli-2.0.0.tar.gz
Algorithm Hash digest
SHA256 819f74867daf3ec914837f115a0f4fd362acd27052ab4d23bf803e6b655c1f60
MD5 60c4933d6ce91e6721b2fb14813ddac8
BLAKE2b-256 81a0c47685f1ca6a8fa04edcccde76c8017e672867d316cf8df5f9a583b97dbb

See more details on using hashes here.

File details

Details for the file agent_brain_cli-2.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for agent_brain_cli-2.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 1c4a537b2bdcdde7b31b262aefcdab9de1da16990772d31f7aee0e55e4c476aa
MD5 b9033dfd933f77b25af0ffe394a134a6
BLAKE2b-256 cc580090e22f46f94ff67b23ebd549d170b66c9764a7bd8500001545b9c861a7

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page