GitHub-assistant – Natural language questions from your GitHub data
Simon(sfarshid) and I spend a lot of time on GitHub. As data nerds we put together a quick tool to explore your repository’s data. How it works: - Data Loading: We use dlt to pull data (issues, PRs, commits, stars) from GitHub - Semantic Layer: Relta wraps the underlying dataset into a semantic layer so the LLM doesn’t hallucinate. - Text-to-SQL: A text-to-SQL agent transforms your plain-English question into a query using the semantic layer - Generative Charts: assistant-ui dynamically generates a chart based on the SQL query - Refinements: If the semantic layer can’t handle your question,…
GitHub-assistant – Natural language questions from your GitHub data launched on December 22, 2024 with 49 votes, #501 of 5,365 launches that month and more than 90% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
GitHub-assistant lets users ask natural language questions about their repository data, including issues, pull requests, commits, and stars. The tool converts plain-English queries into SQL using a semantic layer to prevent inaccuracies, then displays results as dynamic charts. Built for developers and data analysts who want to explore GitHub repository metrics without writing code, it includes automatic refinement capabilities that submit improvements to the semantic layer via pull requests.
written from the facts on this page · September 2026
From the sources
Explore GitHub repositories with natural language questions - GitHub - reltadev/github-assistant: Explore GitHub repositories with natural language questions
github-assistant is a PoC built using Relta and assistant-ui . You can try it out here and read more about the project in this blog . The Relta sub-module is currently not open source. You can see the semantic layer that was generated by the library and is used in the text-to-SQL pipeline in the server-poc/semantic_layer folder. The full library is available upon request for both commercial and non-commercial uses. Send an email to amir [at] relta.dev for access. git remote add template https://github.com/reltadev/poc-template.git && git submodule update --init --recursive Create a virtual environment for Relta python -m venv .venv && source .venv/bin/activate && pip install -r…from github.com
In the maker’s words, at launch
Simon(sfarshid) and I spend a lot of time on GitHub. As data nerds we put together a quick tool to explore your repository’s data. How it works: - Data Loading: We use dlt to pull data (issues, PRs, commits, stars) from GitHub - Semantic Layer: Relta wraps the underlying dataset into a semantic layer so the LLM…
Does a similar job
all alternatives →
I built an AI that turns GitHub codebases into easy tutorials2025 · github.com · ▲923https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
GitHub Stars Semantic Search2024 · github.com · ▲9Find your GitHub stars easily with natural language search
A graph of the languages you use on Github2012 · aaronparecki.com · ▲35
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
