Integrations¶
HiveFlow connects to external systems through optional dependency groups and Studio configuration.
| Integration | Package extra | Doc |
|---|---|---|
| OpenAI | hiveflow[llm] |
OpenAI |
| Anthropic | hiveflow[llm] |
Anthropic |
| Redis (bus / blackboard) | hiveflow[redis] |
Redis |
| PostgreSQL (Studio) | Studio backend deps | PostgreSQL |
| LangGraph (plan export/import) | Core adapter (no extra) | LangGraph PoC |
Full guide: Ecosystem compatibility (LangChain · LangGraph · MCP)
Optional dependency groups¶
pip install "hiveflow-core[security]" # cryptography, jsonschema
pip install "hiveflow-core[redis]" # redis
pip install "hiveflow-core[llm]" # openai, anthropic
pip install "hiveflow-core[rag]" # numpy, scikit-learn
pip install "hiveflow-core[all]" # everything above
Contributing a new integration¶
- Implement against existing abstractions (
LLMClient,BlackboardBackend,EventBus,MCPPluginManager) - Add optional dependency in
packages/core/pyproject.toml - Add a page under
docs/integrations/and link from this index - Add an example under
examples/and register inrun_smoke_tests.py
See CONTRIBUTING.md for PR requirements.