This release is a pre-release and may not be stable for production use.
KAgent CrewAI Integration
This package provides CrewAI integration for KAgent with A2A (Agent-to-Agent) server support and session-aware memory storage.
Features
- A2A Server Integration: Compatible with KAgent's Agent-to-Agent protocol
- Event Streaming: Real-time streaming of crew execution events
- FastAPI Integration: Ready-to-deploy web server for agent execution
- Session-aware Memory: Store and retrieve agent memories scoped by session ID
- Flow State Persistence: Save and restore CrewAI Flow states to KAgent backend
Quick Start
This package supports both CrewAI Crews and Flows. To get started, define your CrewAI crew or flow as you normally would, then replace the kickoff command with the KAgentApp which will handle A2A requests and execution.
from kagent.crewai import KAgentApp
from kagent.core import KAgentConfig
# This is the crew or flow you defined
from research_crew.crew import ResearchCrew
app = KAgentApp(
crew=ResearchCrew().crew(),
agent_card={
"name": "my-crewai-agent",
"description": "A CrewAI agent with KAgent integration",
"version": "0.1.0",
"capabilities": {"streaming": True},
"defaultInputModes": ["text"],
"defaultOutputModes": ["text"],
},
config=KAgentConfig.from_file(),
)
fastapi_app = app.build()
uvicorn.run(fastapi_app, host="0.0.0.0", port=8080)
User Guide
Creating Tasks
For this version, tasks should either accept a single input parameter (string) or no parameters at all. Future versions will allow JSON / structured input where you can replace multiple values in your task to make it more flexible.
For example, you can create a task like follow with yaml (see CrewAI docs) and when triggered from the A2A client, the input field will be populated with the input text if provided.
research_task:
description: >
Research topics on {input} and provide a summary.
This is equivalent of crew.kickoff(inputs={"input": "your input text"}) when triggering agents manually.
Session-aware Memory
CrewAI Crews
Session scoped memory is implemented using the LongTermMemory interface in CrewAI. If you wish to share memories between agents, you must interact with them in the same session to share long term memory so they can search and access the previous conversation history (because agent ID is volatile, we must use session ID). You can enable this by setting memory=True when creating your CrewAI crew. Note that this memory is also scoped by user ID so different users will not see each other's memories.
Our KAgent backend is designed to handle long term memory saving and retrieval with the identical logic as LTMSQLiteStorage which is used by default for LongTermMemory in CrewAI, with the addition of session and user scoping. It will search the LTM items based on the task description and return the most relevant items (sorted and limited).
Note that when you set
memory=True, you are responsible to ensure that short term and entity memory are configured properly (e.g. withOPENAI_API_KEYor set your own providers). The KAgent CrewAI integration only handles long term memory.
CrewAI Flows
In flow mode, we implement memory similar to checkpointing in LangGraph so that the flow state is persisted to the KAgent backend after each method finishes execution. We consider each session to be a single flow execution, so you can reuse state within the same session by enabling @persist() for flow or methods. We do not manage LongTermMemory for crews inside a flow since flow is designed to be very customizable. You are responsible for implementing your own memory management for all the crew you use in the flow.
Tracing
To enable tracing, follow this guide on Kagent docs. Once you have Jaeger (or any OTLP-compatible backend) running and the kagent settings updated, your CrewAI agent will automatically send traces to the configured backend.
Architecture
The package mirrors the structure of kagent-adk and kagent-langgraph but uses CrewAI for multi-agent orchestration:
- CrewAIAgentExecutor: Executes CrewAI workflows within A2A protocol
- KAgentApp: FastAPI application builder with A2A integration
- Event Converters: Translates CrewAI events into A2A events for streaming.
- Task history: The public A2A gateway persists client-visible task and event history.
For local development, configure the HTTP endpoint used by protocol traffic:
# Load process settings from /config/config.json (see Configuration).
Deployment
The uses the same deployment approach as other KAgent A2A applications (ADK / LangGraph). You can refer to samples/crewai/ for examples.
Runtime configuration file
Managed runtimes receive /config/config.json from the controller. For a standalone
process, create that file and load it with KAgentConfig.from_file():
{"runtime":{"control_plane_url":"http://localhost:8083","gateway_url":"http://localhost:8083","name":"my-agent","namespace":"default","log_level":"info"}}
Provider credentials and standard OTEL_* overrides remain environment inputs.
1 maintainer
Metadata
1 maintainer
Release files for kagent-crewai 1.0.0a16
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| kagent_crewai-1.0.0a16.tar.gz | 9.7 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| kagent_crewai-1.0.0a16-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 18.9 kB
Release files / kagent_crewai-1.0.0a16.tar.gz
| Download URL | kagent_crewai-1.0.0a16.tar.gz |
|---|---|
| Size | 9.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
429728d4f9de5bdf6fc854b02ef16c673533b305586eaf4eed88b9ea4490996b
|
|
BLAKE2b-256 checksum How to use checksums |
3d523ea8b6f43d1b1a2f5901641ce73ade1daac94d465fdb1df95cd065134ca5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.13.1 {"installer":{"name":"uv","version":"0.13.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / kagent_crewai-1.0.0a16-py3-none-any.whl
| Download URL | kagent_crewai-1.0.0a16-py3-none-any.whl |
|---|---|
| Size | 9.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8b4cd0e2b71570f6085309fa94bd80a068fc761f70c891bf856f784ef0412f46
|
|
BLAKE2b-256 checksum How to use checksums |
dd5f07982b64b409b3c3fb18a17d76beef8fbe890983d0a83845e3070fc4d241
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.13.1 {"installer":{"name":"uv","version":"0.13.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for kagent-crewai 1.0.0a16
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
