Terraform Rag

Web UI- browse 2700+ modules across 175+ repos (AWS / Azure / GCP):

Login:demo@terraform-rag.io/demo(read-only)

MCP- connect your IDE to the knowledge base:

{ "mcpServers": { "terraform-rag": { "type": "http", "url": "https://terraform-rag.io/mcp", "headers": { "Authorization": "Bearer trag_6c495d7a027369cb5d324d877626c272" } } } }

9 tools available:query_modules,pick_modules,list_modules,get_module_details,get_dependencies,get_module_usage,find_similar_usages,fetch_example_code,get_stats(list_modulesalso takessemantic_queryfor natural-language search).

Point it at your Terraform module repositories. It clones them, parses every HCL file, generates embeddings, and builds a searchable knowledge base in PostgreSQL + pgvector. Then it learnshowthose modules are actually used across your consumer repos - naming patterns, variable conventions, tagging strategies, deployment layouts - and distils that into authoritative guidance.

An agentic pipeline (Claude, Bedrock, or any OpenAI-compatible model) explores the knowledge base across multiple tool-use turns to assemble grounded, reviewable answers - assistive retrieval with a human in the loop, not an autonomous code generator. Query from the web UI, the REST API, or directly from your IDE via MCP.

Agentic Query Pipeline- more than a single RAG lookup. The LLM browses modules, checks details, reads conventions, and fetches example code across multiple tool-use turns before composing an answer for you to review. Four query modes: compose, search, optimize, and audit.

Knowledge Layer- indexes consumer repos to learn real-world usage patterns. Distils conventions across six dimensions (naming, variables, tagging, layout, versions, deployment) and treats them as authoritative guidance in all prompts.

MCP Server- Streamable HTTP endpoint works with Claude Code, Cursor, Windsurf, and any MCP-compatible client. Query your module knowledge base directly from your IDE.

Dependency Graph- PostgreSQL recursive CTEs map the full dependency tree between modules. Find what depends on what, trace impact, and visualize relationships with a D3 force-directed graph.

Version Tracking- automatic git tag discovery with per-module version history. Code-hash caching avoids redundant LLM/embedding calls on re-index.

Flexible LLM Backend- Anthropic (direct or Bedrock), OpenRouter, Ollama, or any OpenAI-compatible endpoint. Swap models without changing code.

CI/CD Integration- GitHub Actions workflow and webhook endpoints for automatic re-indexing when.tffiles change.

Authentication- disabled (default), local email/password with JWT, or ALB-terminated SSO via AWS Identity Center / OIDC.

# 1. Clone and configure git clone https://github.com/krzysztofgawrys/rag-for-terraform.git cd rag-for-terraform cp .env.example .env # Edit .env - set POSTGRES_PASSWORD, JWT_SECRET, and your LLM API key # 2. Start everything docker compose up -d # 3. Index your first repo curl -X POST http://localhost:8000/index/ \ -H "Content-Type: application/json" \ -d '{"repo_url": "git@github.com:org/tf-modules.git", "branch": "main"}'

For private repos, place your SSH deploy key at./worker_deploy_key(or setSSH_KEY_PATHin.env).

Connect any MCP-compatible client tohttp://localhost:8000/mcp/.

{ "mcpServers": { "terraform-rag": { "type": "http", "url": "http://localhost:8000/mcp/" } } }

Available tools:query_modules,pick_modules,list_modules,get_module_details,get_dependencies,get_module_usage,find_similar_usages,fetch_example_code,get_stats.

A separate cheap model can be used for module descriptions during indexing (DESCRIPTION_LLM_*variables).

Browser AI Agent / IDE | | +---------+ +--------+ +----------------+ | Frontend|----->| API |----->| PostgreSQL 16 | | (Vite) | | FastAPI| | + pgvector | +---------+ +---+----+ +----------------+ | +----+----+ | Worker | +-------+ | (Celery)|----->| Redis | +---------+ +-------+

- Non-production use (evaluation, testing, development) is permitted
- Production use requires a commercial license from the author
- On 2029-05-25 the license converts to AGPL-3.0

MCP server that ingests project docs once and lets Claude search by meaning instead of reading everything — saving tokens on large codebases

Easily provide codebase context to Large Language Models (LLMs).

Provides up-to-date, version-specific documentation and code examples for libraries directly into your prompt.

A self-hosted MCP server that indexes documentation from various sources and serves it to AI Agents with semantic search.

Free local RAG for Claude Code - Save tokens & time with vector search. Indexes markdown docs and finds relevant info without reading entire files (40x fewer tokens, 15x faster).

The DHTMLX MCP server provides real-time access to official docs and a smart RAG.

A RAG-based Q&A server using a vector store built from Gemini CLI documentation.

Zero-config knowledge base for AI coding agents. Loads your markdown docs into a searchable database and exposes them as MCP tools — search, read, and manage documentation without leaving your editor. Works instantly with SQLite (no setup), upgrades to PostgreSQL + pgvector for hybrid semantic search. Includes skills for searching docs (/gnosis:search), health checks (/gnosis:status), doc management (/gnosis:manage), and first-time setup (/gnosis:setup). 6 MCP tools, 3 resources, FTS5 keyword search, 176 tests.

Local codebase context compiler for AI coding agents, turning TypeScript/Node workspaces into compact, verifiable context packs.