https://github.com/berrybytes/01agent

Kubernetes Alert Remediation System An intelligent Kubernetes alert remediation platform powered by LLM agents and LangGraph. Features a modern React web interface (L0) and specialized remediation agent (L1) that analyzes monitoring alerts, retrieves live cluster context via MCP, and generates executable remediation scripts.
https://github.com/berrybytes/01agent

a2a-protocol agentic-ai-development agentic-workflow deepagents-langgraph k8s kubernetes lanchain langraph mcp-server sre-agent-tools

Last synced: about 1 month ago
JSON representation

Host: GitHub
URL: https://github.com/berrybytes/01agent
Owner: BerryBytes
License: mit
Created: 2026-03-06T06:05:13.000Z (3 months ago)
Default Branch: main
Last Pushed: 2026-04-07T11:51:23.000Z (about 2 months ago)
Last Synced: 2026-04-07T13:29:12.761Z (about 2 months ago)
Topics: a2a-protocol, agentic-ai-development, agentic-workflow, deepagents-langgraph, k8s, kubernetes, lanchain, langraph, mcp-server, sre-agent-tools
Language: Python
Homepage:
Size: 663 KB
Stars: 0
Watchers: 0
Forks: 0
Open Issues: 1
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE.md
- Code of conduct: CODE_OF_CONDUCT.md

Awesome Lists containing this project

README

# 01Agents: Kubernetes Alert Remediation System

[![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)
[![React Router v7](https://img.shields.io/badge/React_Router-v7-green.svg)](https://reactrouter.com/)
[![LangGraph](https://img.shields.io/badge/LangGraph-1.0.5-green.svg)](https://langchain.com/langgraph)
[![MCP](https://img.shields.io/badge/MCP-1.24.0-orange.svg)](https://modelcontextprotocol.io/)

A Kubernetes alert remediation system with a modern web interface and intelligent remediation agent. This platform analyzes monitoring alerts, fetches live cluster context, and generates executable remediation scripts through LLM‑powered workflows.

## 🏗️ Architecture Overview

The system follows a two‑tier hierarchical architecture:

```
Monitoring Alerts → L0 Client (UI) → L1 Remediation Agent → Remediation Scripts
```

### **L0 Client: React Router v7 Web Interface**
- **Role**: Modern web interface for alert management and visualization.
- **Port**: Default `3000`.

### **L1: Kubernetes Alert Remediation Agent**
- **Role**: LangGraph‑powered remediation specialist using specialized subagents.
- **Port**: Default `10001`.

---

## 🚀 Quick Start

### Clone the Repository

```bash
git clone git@github.com:BerryBytes/01agent.git
cd 01agent
```

### Choose Your Deployment Approach

- **[Approach 1: Using Pre-built Images](#approach-1-using-pre-built-images)** (Recommended for most users)
- **[Approach 2: Building Custom Images](#approach-2-building-custom-images)** (For developers modifying source code)

---

## Approach 1: Using Pre-built Images

Deploy using ready-to-use images from the `01community` registry. Perfect for quick setup and production use.

### Prerequisites

- **Kubernetes cluster** (Kind, Minikube, or Cloud)
- **Helm 3+**
- **LLM API Key** (OpenRouter, DeepSeek, Google, or Anthropic)

### Step 1: Install MCP Server for Kubernetes

The MCP (Model Context Protocol) Server provides Kubernetes tools for the agents.

#### Clone the MCP Server repository

```bash
git clone https://github.com/Flux159/mcp-server-kubernetes.git
```

#### Update the schema (Required)

```bash
python3 -c "
import json
with open('mcp-server-kubernetes/helm-chart/values.schema.json') as f:
schema = json.load(f)

schema['properties']['observability'] = {
'type': 'object',
'additionalProperties': True
}

with open('mcp-server-kubernetes/helm-chart/values.schema.json', 'w') as f:
json.dump(schema, f, indent=2)
print('Schema updated successfully!')
"
```

#### Install the MCP Server

```bash
helm install mcp-server ./mcp-server-kubernetes/helm-chart \
--set kubeconfig.provider=serviceaccount \
--set transport.mode=http \
--set transport.service.type=ClusterIP \
--set security.allowOnlyNonDestructive=false \
--create-namespace \
--namespace mcp-system
```

### Step 2: Install PostgreSQL Operator

The agents use PostgreSQL for long-term memory. We use the CrunchyData Operator to manage it.

#### Install OLM (Operator Lifecycle Manager)

```bash
curl -sL https://github.com/operator-framework/operator-lifecycle-manager/releases/download/v0.40.0/install.sh | bash -s v0.40.0
```

> [!IMPORTANT]
> OLM installation can take a few minutes. Please ensure all OLM pods in the `olm` namespace are in the **Running** state before proceeding.

#### Install the PostgreSQL Operator

```bash
kubectl create -f https://operatorhub.io/install/postgresql.yaml
```

### Step 3: Configure Agent Settings

Edit `helm-chart/values.yaml` to configure your LLM provider and API key.
You must set the `MODEL_PROVIDER`, `MODEL_NAME` and provide the corresponding API key in the `secret` section.

```yaml
agents:
- name: l0
enabled: true
image: 01community/agent-l0:v1

- name: l1
enabled: true
image: 01community/agent-l1:v1
env:
MODEL_PROVIDER: deepseek # options: gemini, openai, openrouter, anthropic, deepseek
MODEL_NAME: deepseek-chat # examples: gemini-2.0-flash, gpt-4o, claude-3-5-sonnet
MCP_SERVER_URL: http://mcp-server-mcp-server-kubernetes.mcp-system.svc.cluster.local:3001/mcp
ENABLE_K8S_TOOLS: "true"
STM_ENABLE_POSTGRES: "true"
usePostgresql: true
secret:
DEEPSEEK_API_KEY: "your-api-key-here"
# GOOGLE_API_KEY: "your-api-key"
# OPENAI_API_KEY: "your-api-key"
# OPENROUTER_API_KEY: "your-api-key"
# ANTHROPIC_API_KEY: "your-api-key"
```

### Step 4: Deploy 01Agents

```bash
helm upgrade --install 01agent ./helm-chart -n 01cloud --create-namespace
```
> [!IMPORTANT]
> Ensure all the pods in the namespace have initialized successfully and running

### Step 5: Access the Application

Port-forward the UI service:

```bash
kubectl port-forward svc/agent-l0 -n 01cloud 3000:3000
```

Open your browser and navigate to `http://localhost:3000`

### Step 6: Monitoring & Observability (Optional)

For advanced monitoring with Grafana, Loki, Tempo, and OpenTelemetry, see [OTEL-setup.md](./OTEL-setup.md). These features are **disabled by default** and should only be enabled if you have the observability stack configured.

---

## Approach 2: Building Custom Images

Build and deploy your own modified images from source code. Ideal for developers customizing the system.

### Prerequisites

- **Kubernetes cluster** (Kind, Minikube, or Cloud)
- **Helm 3+**
- **Docker** (for building images)
- **Node.js 25+** & **npm** (for L0 Client modifications)
- **Python 3.11+** (for L1 Agent modifications)
- **LLM API Key** (OpenRouter, DeepSeek, Google, or Anthropic)

### Step 1: Install MCP Server for Kubernetes

The MCP (Model Context Protocol) Server provides Kubernetes tools for the agents.

#### Clone the MCP Server repository

```bash
git clone https://github.com/Flux159/mcp-server-kubernetes.git
```

#### Update the schema (Required)

```bash
python3 -c "
import json
with open('mcp-server-kubernetes/helm-chart/values.schema.json') as f:
schema = json.load(f)

schema['properties']['observability'] = {
'type': 'object',
'additionalProperties': True
}

with open('mcp-server-kubernetes/helm-chart/values.schema.json', 'w') as f:
json.dump(schema, f, indent=2)
print('Schema updated successfully!')
"
```

#### Install the MCP Server

### Step 2: Install PostgreSQL Operator

The agents use PostgreSQL for long-term memory. We use the CrunchyData Operator to manage it.

#### Install OLM (Operator Lifecycle Manager)

```bash
curl -sL https://github.com/operator-framework/operator-lifecycle-manager/releases/download/v0.40.0/install.sh | bash -s v0.40.0
```

> [!IMPORTANT]
> OLM installation can take a few minutes. Please ensure all OLM pods in the `olm` namespace are in the **Running** state before proceeding.

#### Install the PostgreSQL Operator

```bash
kubectl create -f https://operatorhub.io/install/postgresql.yaml
```

### Step 3: Build Custom Images

Navigate to the repository root and build your images:

#### Build L0 Frontend

```bash
docker build -t your-registry/agent-l0:latest ./k8s-agent/level-0-agent
```

#### Build L1 Backend Agent

```bash
docker build -t your-registry/agent-l1:latest ./k8s-agent/level-1-agent
```

### Step 4: Push or Load Images

**For remote clusters** - Push to your registry:

```bash
docker push your-registry/agent-l0:latest
docker push your-registry/agent-l1:latest
```

**For local Kind clusters** - Load images directly:

```bash
kind load docker-image your-registry/agent-l0:latest --name 01cloud-cluster
kind load docker-image your-registry/agent-l1:latest --name 01cloud-cluster
```

### Step 5: Configure Agent Settings

Edit `helm-chart/values.yaml` to use your custom images and configure your LLM provider.
You must set the `MODEL_PROVIDER`, `MODEL_NAME`, `image` and provide the corresponding API key in the `secret` section.

```yaml
agents:
- name: l0
enabled: true
image: your-registry/agent-l0:latest # Your custom image

- name: l1
enabled: true
image: your-registry/agent-l1:latest # Your custom image
env:
MODEL_PROVIDER: deepseek # options: gemini, openai, openrouter, anthropic, deepseek
MODEL_NAME: deepseek-chat # examples: gemini-2.0-flash, gpt-4o, claude-3-5-sonnet
MCP_SERVER_URL: http://mcp-server-mcp-server-kubernetes.mcp-system.svc.cluster.local:3001/mcp
ENABLE_K8S_TOOLS: "true"
STM_ENABLE_POSTGRES: "true"
usePostgresql: true
secret:
DEEPSEEK_API_KEY: "your-api-key-here"
# GOOGLE_API_KEY: "your-api-key"
# OPENAI_API_KEY: "your-api-key"
# OPENROUTER_API_KEY: "your-api-key"
# ANTHROPIC_API_KEY: "your-api-key"
```

### Step 6: Deploy 01Agents

```bash
helm upgrade --install 01agent ./helm-chart -n 01cloud --create-namespace
```
> [!IMPORTANT]
> Ensure all the pods in the namespace have initialized successfully and running

### Step 7: Access the Application

Port-forward the UI service:

```bash
kubectl port-forward svc/agent-l0 -n 01cloud 3000:3000
```

Open your browser and navigate to `http://localhost:3000`

### Step 8: Monitoring & Observability (Optional)

For advanced monitoring with Grafana, Loki, Tempo, and OpenTelemetry, see [OTEL-setup.md](./OTEL-setup.md).

---

## 🔌 Local Development Tools

Access these services via port-forwarding for development and debugging:

```bash
# PostgreSQL Database
kubectl port-forward svc/agents-primary -n 01cloud 5432:5432

# MCP Server
kubectl port-forward svc/mcp-server-mcp-server-kubernetes -n mcp-system 3001:3001
```

---

## 📁 Repository Structure

- `helm-chart/`: Core Helm chart for deployment
- `k8s-agent/`: Source code for L0 and L1 agents
- `OTEL-setup.md`: Optional guide for monitoring (Prometheus, Grafana, Loki)

---

## 🤝 Contributing

We welcome contributions from the community! Whether you are reporting a bug, suggesting a feature, or submitting a pull request, your help is appreciated.

- **Found a bug?** [Open an issue](https://github.com/BerryBytes/01agent/issues/new?template=bug_report.md)
- **Have a feature idea?** [Suggest it here](https://github.com/BerryBytes/01agent/issues/new?template=feature_request.md)
- **Want to contribute code?** Check out our [Contributing Guidelines](./CONTRIBUTING.md)

This project is maintained by [Bishal Singh (@bsalsingh)](https://github.com/bsalsingh) and the 01Cloud community.

---

## 📜 Code of Conduct

To ensure a welcoming and inclusive community, please review and follow our [Code of Conduct](./CODE_OF_CONDUCT.md).

---

## ⚖️ License

This project is licensed under the [MIT License](./LICENSE.md).

---

## 📚 Component Documentation

- [L0 Client (Frontend)](k8s-agent/level-0-agent/README.md)
- [L1 Agent (Backend)](k8s-agent/level-1-agent/README.md)

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Awesome

https://github.com/berrybytes/01agent

Awesome Lists containing this project

README