colossus-lab

colossus-lab / openarg_backend

Public

AI-powered analysis engine for Argentine government open data. Multi-agent pipeline (LangGraph) with 10 data connectors, NL2SQL, semantic caching, and real-time streaming. Built with FastAPI, PostgreSQL + pgvector, Celery, and Gemini/Claude LLMs.

16
0
100% credibility
Found Mar 24, 2026 at 16 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

AI backend that powers a chat platform for querying Argentine open government data in natural language, fetching from multiple sources, generating analyses with charts and citations.

How It Works

1
👀 Discover OpenArg

You hear about OpenArg, a friendly helper that explains Argentine public data like budgets and economy in simple words.

2
🌐 Visit the site

Head to openarg.org and find the chat box ready for your questions.

3
💬 Ask naturally

Type a question in everyday Spanish, like 'What's inflation doing lately?' or 'How much do deputies earn?'.

4
🧠 AI works its magic

The assistant quickly gathers real data from government sites, makes charts, and thinks deeply to give you a smart answer.

5
📊 Get your insights

See a clear explanation with key facts, graphs, sources to check, and even policy thoughts if you want.

✅ Stay informed

You're now clear on public data, can ask follow-ups, and trust the cited official sources for more details.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 16 to 16 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is openarg_backend?

Openarg_backend is an AI-powered analysis engine that lets you query Argentine government open data in natural language, pulling from 10 connectors like economic time series, congressional transcripts, and patrimonial declarations. It delivers structured answers with citations, charts, and confidence scores via FastAPI endpoints and WebSocket streaming, handling everything from semantic caching to NL2SQL on cached PostgreSQL tables. Built in Python with Celery workers for ingestion and LangGraph for multi-agent orchestration using Gemini or Claude LLMs.

Why is it gaining traction?

This AI-powered analysis tool shines for Argentine public data, automating ingestion from CKAN portals and BCRA APIs while generating charts and policy evaluations on demand. Developers appreciate the production Docker Compose setup, real-time metrics, and hexagonal ports/adapters that make it easy to swap LLMs or add connectors without breaking the query pipeline. Semantic caching and few-shot NL2SQL cut costs and latency, making it a practical AI-powered project on GitHub for gov transparency apps.

Who should use this?

Argentine data journalists querying inflation trends or deputy assets without SQL hassle. Policy analysts evaluating government efficacy via the optional policy agent. Devs building AI-powered dashboards for open data portals, especially those tired of manual ETL from datos.gob.ar.

Verdict

Solid foundation for an AI-powered analysis platform, with excellent docs, Makefile dev workflow, and tests—but only 16 stars and 1.0% credibility signal early maturity. Fork and deploy if you're in LatAm gov data; otherwise, watch for more adoption.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.