quelch 0.9.2

What is Quelch?

Quelch v2 is a knowledge-platform operator tool for teams using Jira and Confluence. It ingests data into Cosmos DB as the system of record, uses Azure AI Search (via the embedded rigg library) for hybrid semantic retrieval, and exposes a five-tool MCP API that agents (Copilot Studio, VS Code Copilot, Claude, Codex) can call directly.

One Rust binary, one YAML config file, three runtime roles: quelch ingest, quelch mcp, and the operator CLI.

Architecture overview

Sources → quelch ingest → Cosmos DB → AI Search Indexer → AI Search Index
                              ↑                                ↑
                              └─ quelch-meta (cursors)         │
                                                               │
                       quelch mcp ────────────────────────────┘
                              ↑
                       Agent (Copilot Studio / VS Code / Claude / etc.)

See docs/architecture.md for details.

Features

• Cosmos DB as system of record — exact queries, counts, exhaustive listings, and cursor-based pagination without hitting search
• Azure AI Search via rigg — indexes, skillsets, indexers, knowledge sources, and knowledge bases all managed from quelch.yaml
• Five-tool MCP API — search (Knowledge Base agentic retrieval), query (Cosmos SQL), get (point-read), list_sources, aggregate
• Incremental sync — minute-resolution windows with safety lag, backfill resume, soft-delete reconciliation
• Agent bundle generator — quelch agent generate produces grounded bundles for Copilot Studio, Claude Code, VS Code Copilot, Copilot CLI, Codex, and Markdown
• On-prem artefacts — quelch generate-deployment writes docker-compose, systemd, or Kubernetes manifests; Quelch never SSHes anywhere
• Operator CLI — azure plan, azure deploy, azure indexer, azure logs with Bicep + az shell-outs
• Rich TUI — fleet dashboard showing live ingest state per worker, polling quelch-meta

Installation

Homebrew (macOS/Linux)

brew install mklab-se/tap/quelch

Cargo

cargo install quelch

Binary download

Download pre-built binaries from the latest release.

Quick start

# Generate a starter config interactively
quelch init

# Validate the generated config
quelch validate

# Plan Azure resources (Bicep + rigg files) — no Azure calls yet
quelch azure plan ingest --no-what-if

# Deploy to Azure (calls az + rigg-client)
quelch azure deploy ingest

# Run the ingest worker
quelch ingest

# Start the MCP server
quelch mcp

CLI surface

quelch — Cosmos + AI Search knowledge platform operator

COMMANDS:
  validate            Validate config without running
  effective-config    Print the resolved config for a deployment
  status              Show live ingest state from quelch-meta
  ingest              Run the ingest worker
  mcp                 Start the MCP HTTP server
  dev                 Run sim + ingest + MCP in one process (no Azure needed)
  azure plan          Show Bicep + rigg diff against live Azure
  azure deploy        Apply Bicep + rigg to Azure
  azure pull          Pull live rigg state to disk
  azure indexer       Run / reset / status the AI Search Indexer
  azure logs          Tail Container Apps log stream
  azure destroy       Tear down all Azure resources for a deployment
  query               Run a Cosmos SQL query from the CLI
  search              Run a Knowledge Base search from the CLI
  get                 Fetch a single document from Cosmos
  reset               Reset ingest cursors
  generate-deployment Generate docker-compose / systemd / k8s artefacts
  agent generate      Generate agent or skill bundles for agent platforms
  init                Interactive config wizard
  ai                  Configure AI (ailloy) embedding model

OPTIONS:
  -c, --config <PATH>   Config file (default: quelch.yaml)
  --help                Print help
  --version             Print version

See docs/cli.md for every command and flag with examples.

Documentation

License

MIT