sample-okf-llm-wiki logo
sample-okf-llm-wiki
★ 33
vs
terravision logo
terravision
★ 1.7k

sample-okf-llm-wiki vs terravision

sample-okf-llm-wiki: Data Wiki converts AWS data sources like Glue Data Catalog and Redshift into portable, AI-authored knowledge bundles, making complex data semantics accessible to AI agents. It uses LLMs to generate markdown documentation for datasets, including tables, joins, and metrics, and serves these via the Model Context Protocol (MCP).; terravision: TerraVision automatically generates professional cloud architecture diagrams from Terraform code or JSON graph definitions, utilizing official AWS, Azure, and GCP icons. It ensures diagrams stay in sync with your infrastructure, runs client-side without cloud credentials, and supports various output formats including interactive HTML and editable draw.io files.

01

TL;DR

sample-okf-llm-wiki logo
sample-okf-llm-wikiRAG / Knowledge Base · ★ 33

Enabling AI agents to understand complex AWS data semantics.

terravision logo
terravisionDev Tooling · ★ 1.7k

Automatically generate and keep cloud architecture diagrams updated.

02

Side-by-Side Comparison

Field
sample-okf-llm-wiki logosample-okf-llm-wiki
terravision logoterravision
Category
RAG / Knowledge Base
Dev Tooling
Stars
★ 33
★ 1.7k
License
MIT-0
AGPL-3.0
Install Command
git clone https://github.com/okf/sample-okf-llm-wiki.git && cd sample-okf-llm-wiki && ./scripts/deploy.sh
pipx install terravision
Updated
1d ago
1d ago
Open Source
Yes
Yes
Tags
AWS, LLM, RAG
Terraform, Cloud Diagramming, Infrastructure as Code
03

Features

sample-okf-llm-wiki logosample-okf-llm-wiki
01Automated Induction: AI agents author knowledge bundles from source catalogs.
02Pluggable Data Sources: Supports AWS Glue and Amazon Redshift, with extensible architecture.
03Self-Healing Freshness: Automatically re-harvests on Glue catalog changes and keeps search index in sync.
04Served Over MCP: Enables agents to discover, read, and semantically search bundles via the Model Context Protocol.
05Web Console: Provides a React UI for managing datasets, harvests, and browsing bundles.
terravision logoterravision
01Automatically generate diagrams from Terraform or JSON input.
02Utilizes official AWS, Azure, and GCP icons for professional-grade diagrams.
03Ensures diagrams are always up-to-date with infrastructure code.
04Runs entirely client-side, requiring no cloud credentials.
05Supports interactive HTML output and editable draw.io export.
04

Use Cases

sample-okf-llm-wiki logosample-okf-llm-wiki
↳Enabling AI agents to understand complex AWS data semantics.
↳Automated generation and synchronization of data documentation.
↳Providing semantic search and QA capabilities over enterprise data.
↳Integrating structured data knowledge into LLM applications via MCP.
↳Benchmarking and improving text-to-SQL agent accuracy.
terravision logoterravision
↳Automatically generate and keep cloud architecture diagrams updated.
↳Integrate into CI/CD pipelines to ensure diagrams are always current.
↳Rapidly visualize existing Terraform infrastructure deployments.
↳Create simplified architectural overviews for executive presentations.
↳Describe and render architectures using JSON for AI assistants.
FAQ

FAQ

What is the difference between sample-okf-llm-wiki and terravision?
Both sample-okf-llm-wiki and terravision are in the RAG / Knowledge Base category. sample-okf-llm-wiki has 33 stars, while terravision has 1.7k stars.
Which is better, sample-okf-llm-wiki or terravision?
The best choice depends on your use case. Choose sample-okf-llm-wiki if Enabling AI agents to understand complex AWS data semantics., and terravision if Automatically generate and keep cloud architecture diagrams updated..
Is sample-okf-llm-wiki free or open source?
Yes, sample-okf-llm-wiki is open source on GitHub (MIT-0).
Is terravision free or open source?
Yes, terravision is open source on GitHub (AGPL-3.0).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related