agent-kernel

View on GitHub

The Operating System for Scalable Enterprise AI Agents - Run, orchestrate, and deploy Compliant Enterprise AI Agents at scale across frameworks, without lock-in, rewrites or fragile glue code. Native support for MCP, A2A. Interface with all mainstream communication channels seamlessly out of the box, production ready from day one.

★ 19188 forksPythonApache-2.0yaalalabs

Agent Kernel is a Python platform layer for running, orchestrating and deploying production AI agents. It runs OpenAI Agents SDK, LangGraph, CrewAI and Google ADK side by side, adds guardrails, sessions, RAG, sandboxing, channels and MCP/A2A/AG-UI, and deploys to AWS, Azure, GCP or Kubernetes via Terraform and Helm.

Use Cases

Run multi-agent systems with handoffs across frameworksPort agents between OpenAI Agents SDK, LangGraph, CrewAI, Google ADK without rewritesDeploy agents to AWS Lambda/ECS, Azure Functions/Container Apps, GCP Cloud Run or KubernetesAdd PII detection, jailbreak prevention and content guardrails to agent callsServe agents over Slack, WhatsApp, Teams, Telegram, Gmail, Messenger, InstagramExpose agents as MCP tools or connect them to MCP serversAgent-to-agent coordination with A2A messagingAttach vector (ChromaDB) or graph (Neo4j) knowledge bases for RAGRun sandboxed code and shell execution via docker/kubernetes/e2b providersSchedule deferred and recurring agent chats with EventBridge or local timersTrace every agent, tool and LLM call with LangFuse or LogfirePersist sessions and threads in Redis, Valkey, DynamoDB, Cosmos DB or FirestoreStream agent runs to AG-UI frontends like CopilotKitInstall ak-* skills to guide coding assistants when building agents

Built With

Language: Python
Frameworks: OpenAI Agents SDK · LangGraph · CrewAI · Google ADK · MCP · A2A · AG-UI · ChromaDB · Neo4j · LangFuse · OpenLLMetry · Pydantic Logfire · Terraform · Helm · Redis · DynamoDB

agent-kernel

Use Cases

Built With

Tags