codeready-toolchain/tarsy

TARSy (Thoughtful Alert Response System) is an intelligent SRE system that automatically processes alerts through parallel agent chains, using MCP (Model Context Protocol) servers and optional runbooks for comprehensive multi-stage incident analysis and automated remediation.

This is the Go-based hybrid rewrite of TARSy, replacing the original Python implementation (now deprecated). The new architecture splits responsibilities between a Go orchestrator and a stateless Python LLM service for better performance, type safety, and scalability.

Demo

Documentation

• README.md – This file: project overview and quick start
• docs/architecture-overview.md – High-level architecture, components, and processing flow
• docs/functional-areas-design.md – Detailed design of each functional area with file paths and interfaces
• docs/slack-integration.md – Slack notification setup, configuration, and threading
• deploy/README.md – Deployment and configuration guide
• deploy/config/README.md – Configuration reference

Prerequisites

• Go 1.27+ – Backend orchestrator
• Python 3.13+ – LLM service runtime
• Node.js 24+ – Dashboard development and build tools
• uv – Modern Python package manager
  • Install: curl -LsSf https://astral.sh/uv/install.sh | sh
• Podman (or Docker) – Container runtime (used for PostgreSQL)

Optional (not needed for make dev):

• protoc – Protocol Buffers compiler (make proto-generate)
• golangci-lint – Go linter (make lint, make check-all)
• Atlas – Migration authoring (make migrate-create)

Quick Check: Run make doctor to verify all prerequisites are installed.

Quick Start

Development Mode

# 1. Install dependencies and bootstrap config
make setup

# 2. Configure environment variables
cp deploy/config/.env.example deploy/config/.env
# Edit deploy/config/.env and set at minimum:
#   - GOOGLE_API_KEY   (required — used by built-in Gemini providers)
#   - KUBECONFIG       (path to your kubeconfig, for Kubernetes investigation)

# 3. Start everything (database, backend, LLM service, dashboard)
make dev

Services will be available at:

• TARSy Dashboard: http://localhost:5173
• Backend API: http://localhost:8080