* docs: adding crewAI integration guide * docs: adding a honcho_crewai package * docs: Using session.search and session summaries to enhance the honcho storage class * docs: updating to use honcho_crewai package * docs: Added honcho_crewAI tools. Updated honcho_crewai tests to better match the specific integration. Built out the package definition more. * docs: Adding all the honcho sdk parameters to crewAI tools, also adding tools and a simple example. * docs: adding logging to HonchoStorage class * docs: updating mdx file to match examples and fixing explanations * Docs: removing session summaries from search * docs: adding files package * docs: simplifying language specifically for theory-of-mind. * chore: code rabbit suggestions. * chore: code rabbit * fix: removing nanoid crewai dependency * docs: adding filtering capability to honcho crewai package and tool examples. * fix: remove factory class in favor of direct class instantiation * docs: adding hybrid memory example * fix: fixing redundent calls to honcho for saving message history * chore: code rabbit fixes |
||
|---|---|---|
| .. | ||
| examples | ||
| src/honcho_crewai | ||
| tests | ||
| LICENSE | ||
| README.md | ||
| pyproject.toml | ||
| uv.lock | ||
README.md
Honcho CrewAI Integration
Build CrewAI agents with persistent memory and reasoning capabilities powered by Honcho.
Installation
pip install honcho-crewai
Quick Start
from crewai import Agent, Task, Crew, Process
from crewai.memory.external.external_memory import ExternalMemory
from honcho_crewai import HonchoStorage
# Initialize Honcho storage
storage = HonchoStorage(user_id="user-123")
external_memory = ExternalMemory(storage=storage)
# Create agent with memory
agent = Agent(
role="AI Assistant",
goal="Help users with persistent memory",
backstory="You remember past conversations.",
)
# Create crew with external memory
crew = Crew(
agents=[agent],
tasks=[task],
external_memory=external_memory
)
Features
- Automatic Memory: CrewAI agents automatically store and retrieve conversation context
- Semantic Search: Find relevant past messages using vector similarity
- Logical Reasoning: Query what the system knows about users via the Dialectic API
- Multi-Agent Support: Give each agent distinct memory and identity
- Tools Integration:
HonchoGetContextTool,HonchoDialecticTool, andHonchoSearchToolfor explicit memory control
Documentation
For comprehensive guides, examples, and API reference, visit: https://docs.honcho.dev/v2/integrations/crewai
Examples
Check out complete examples in the GitHub repository.
License
AGPL-3.0-or-later
Support
- Report issues: GitHub Issues
- Documentation: docs.honcho.dev
- Website: honcho.dev