Search

More Filters

Show More
Add Listing
Go Back

kagent

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

kagent is a Kubernetes-native framework for building, deploying and managing AI agents. It provides Kubernetes custom resources and controllers so developers and cluster operators can define agents declaratively as an Agent resource that bundles a system prompt, tools and an LLM configuration. The project targets teams that run workloads on Kubernetes and need a reproducible, observable and extensible platform for agentic applications. Kagent integrates multiple LLM providers via a ModelConfig CRD, connects agents to tool servers through an MCP mechanism, supports memory for agents to access up-to-date context, and offers observability via OpenTelemetry. The repository also includes a web UI, a controller, an engine that runs agents using ADK, and a CLI to manage agents and tools. Documentation and local development guidance are provided to help contributors and operators get started.

Links

Stars
1280
App URL
https://github.com/kagent-dev/kagent
Github Repository
https://github.com/kagent-dev/kagent/blob/main/README.md

Categorization

App Details

Features
Kagent exposes Agents as a Kubernetes custom resource and ModelConfig to represent LLM provider settings. It supports multiple LLM providers including OpenAI, Azure OpenAI, Anthropic, Google Vertex AI and Ollama, and allows custom providers via AI gateways. Agents can use MCP Tools provided by ToolServer custom resources and the project ships an MCP server with tools for Kubernetes, Istio, Helm, Argo, Prometheus, Grafana and Cilium. The framework includes memory support so agents can access recent information, OpenTelemetry tracing for observability, and a declarative YAML-first design for reproducible deployments. Core components include a controller to reconcile resources, a web UI, an engine leveraging ADK to run agents, and a CLI for management. The codebase emphasizes extensibility, testability and Kubernetes-native patterns.
Use Cases
Kagent helps teams who want to run agentic AI workloads inside Kubernetes by providing a structured, production-oriented framework that reuses Kubernetes primitives and best practices. It reduces engineering overhead by representing agents, models and tools as CRDs so operators can manage them with familiar tooling and declarative manifests. Built-in provider integrations make it easier to switch or combine LLMs while the MCP tool system lets agents interact with cluster services and observability stacks. Memory support lets agents access contextual state, and OpenTelemetry integration helps trace agent activity for debugging and monitoring. The web UI and CLI simplify day-to-day operations and the repository includes documentation and local development instructions to accelerate adoption and contribution.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*