OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

DevIntel AI

DevIntel AI is an open-source code-intelligence platform that indexes repositories into a PostgreSQL vector database and uses retrieval-augmented generation to answer codebase questions. It also provides code-health metrics, AST-based architecture diagrams and automated pull-request reviews through a web app, backend and VS Code extension.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

DevIntel AI — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use DevIntel AI when repository-specific questions or code analysis need to draw on indexed source rather than general-purpose chat alone. The public demo is described with a pre-seeded repository for evaluation.

Who it is for

  • Developers who want to ask questions grounded in an indexed repository.
  • Teams seeking repository code-health analysis, architecture diagrams or automated pull-request reviews.
  • Developers evaluating a code-intelligence platform or deploying its documented stack themselves.

Documented uses

  • Index a repository so its code can be retrieved as context for questions.
  • Ask for explanations or insights grounded in indexed code.
  • Review multidimensional code-health metrics and AST-based architecture diagrams.
  • Automate pull-request review tasks through the platform or VS Code extension.
Before you choose

Requirements & limits

The README describes a public demo using a pre-seeded repository without GitHub OAuth setup. The repository is licensed under MIT. Local setup requires an AI provider API key and configured backend secrets.

  • The project uses PostgreSQL 16 with pgvector for vector storage and retrieval.
  • Gemini is the documented default AI provider; OpenAI is an alternative configured through AI_PROVIDER.
  • Tree-sitter-based indexing supports the documented language set and falls back to line-based partitioning when parsing fails.
  • The default maximum file size is 5 MB, and configured ignored directories are excluded from ingestion.
  • Redis 7 is optional for distributed caching and rate limiting.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up DevIntel AI locally

Prepare the backend and frontend development services using the documented local setup.

Before you start

  • Python 3.11 and Node.js 18 or later
  • PostgreSQL 16 with pgvector
  • A Google Gemini API key or OpenAI API key
  • A configured DATABASE_URL and the required application secret values

Steps

  1. Clone the repository and enter the project directory.

  2. In devintel-backend, create and activate a Python virtual environment, install requirements.txt, and copy .env.example to .env.

  3. Set DATABASE_URL and the relevant AI provider key, then apply migrations with alembic upgrade head.

  4. Start the API with uvicorn app.main:app --reload --host 0.0.0.0 --port 8000.

  5. In devintel-frontend, run npm install and npm run dev.

Expected outcome

The documented setup serves the API on port 8000 and the Vite frontend on port 5173.

Guide limitations

  • This is a local development setup recipe; it does not document connecting a new repository or completing an analysis task.
  • The README lists JWT_SECRET_KEY, SECRET_KEY and TOKEN_ENCRYPTION_KEY as required backend configuration.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
DevIntel AIIndex a repository so its code can be retrieved as context for questions.Cloud, Docker, WebThe README describes a public demo using a pre-seeded repository without GitHub OAuth setup. The repository is licensed under MIT. Local setup requires an AI provider API key and configured backend secrets.
Chatbot with PDF for Semantic SearchPrepare document content as embeddings and save it to a supported vector database.WebThe repository is identified as open source and publicly visible on GitHub.
AI LLM PlaygroundAsk questions about PDF documents through an assistant interface.Web
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
josephkamau32/devintel · Official homepage title · retained in its source language
How we review sourcesSuggest a correction