Installation

Install Draive into a dedicated Python 3.14+ environment so your project dependencies remain isolated. We recommend uv for deterministic installs, but standard pip works as well.

Using pip

python -m pip install --upgrade pip
pip install "draive"

Add provider extras to pull in the SDKs you need:

pip install "draive[openai]"
pip install "draive[anthropic]"
pip install "draive[gemini]"

Combine extras for multi-provider projects:

pip install "draive[openai,anthropic,gemini]"

Using uv

uv venv
uv pip install "draive[openai,anthropic,gemini]"

To sync an existing project with the pinned dependencies from pyproject.toml:

uv sync --all-groups --all-extras --frozen

Optional extras

• draive[openai], draive[openai_realtime] for OpenAI Responses/Realtime.
• draive[anthropic], draive[anthropic_bedrock] for Claude models (direct or via Bedrock).
• draive[mistral], draive[gemini], draive[cohere], draive[cohere_bedrock] for other hosted LLMs.
• draive[bedrock], draive[aws] for AWS model/runtime integrations.
• draive[ollama], draive[vllm] for local or self-hosted deployments.
• draive[qdrant], draive[postgres], draive[surrealdb] for vector/storage backends; the Postgres index requires the pgvector server extension, while a remote SurrealDB connection requires a SurrealDB 3.x server with its namespace and database already defined. SurrealDB tables have to be defined upfront as well - each feature provides a static migrate() (SurrealConversationMemory, SurrealTemplatesRepository, SurrealVectorIndex), while custom models are defined with Surreal.define_table.
• draive[rabbitmq] for message-queue integrations.
• draive[starlette], draive[fastapi] for serving draive applications over HTTP.
• draive[httpx], draive[mcp], draive[opentelemetry], draive[docs] for HTTP utilities, MCP, tracing, and docs site builds.

Verify your environment

python -c "from importlib.metadata import version; print(version('draive'))"

You are ready to jump into the quickstart once the version prints without errors.