Vivekmind

AI systems, tools & infrastructure.

We design and build intelligent products for developers, data teams, and technical organisations — software that thinks alongside you.

Our Products About us

Products

View all

Schema Weaver

Analytics Workspace

The first voice-native analytics workspace for PostgreSQL. Browse live data in a high-performance grid, ask Resona AI in plain English, or talk to your database by voice.

Data Explorer SQL Editor Docs

Explore

Vivekmind CLI

AI Coding Agent

Open-source AI coding agent. Connect any model from any provider, including Claude, GPT, Gemini, all native AWS models from AWS Bedrock, and more — right from your terminal.

Explore

Vivekmind Press

Content Platform

AI-assisted publishing platform. Create, manage, and distribute technical content at scale — documentation, newsletters, and long-form articles — with AI as a native part of the workflow.

Explore

Our mission

Software that thinks with you, not around you.

Every Vivekmind product ships with AI as a first-class citizen — not bolted on as a feature. From database migrations to content publishing, we build tools that are intelligent by default.

About Vivekmind

Products shipped

AI-first

By design

55+

AI tools in Schema Weaver

24/7

Reliability

From the Blog

View all →

engineeringAug 5

The Architecture of a Schema Weaver PostgreSQL Migration Engine

Schema Weaver's PostgreSQL Migration Engine is a state-based migration engine for PostgreSQL that introspects 50+ object types, computes dependency-aware schema diffs, classifies every change by risk, and applies safe migration patterns for production databases. This article explores the architecture behind the engine, from introspection and planning to execution, crash recovery, and risk analysis.

engineeringJul 3

SW Agent: Bridge agent that connects Schema Weaver browser IDE to user's PostgreSQL databases.

Deep-dive into the architecture of SW Agent — a lightweight daemon that bridges browser IDEs to PostgreSQL databases without exposing credentials to the cloud.

engineeringJun 28

SSE Streaming Architecture — How Schema Weaver's Data Explorer Streams 18 Event Types and Chunked Payloads to the Browser

Part 5 of the Data Explorer architecture series. Covers the SSE protocol design, 18+ typed event types, chunked JSON for payloads exceeding 64KB, streaming table artifacts, backend FastAPI endpoint, Node.js proxy, and frontend parser with retry

engineeringJun 19

Model Provider Architecture: How Schema Weaver's Data Explorer Routes, Streams, and Fails Over Across Four LLM Providers

Most AI products ship with one provider hardcoded. When that provider has an outage, rate limits you, or deprecates a model, your product breaks. Schema Weaver's Data Explorer runs on a provider-agnostic abstraction layer that supports AWS Bedrock, OpenAI, Anthropic, and Google GenAI behind a single interface — with per-provider circuit breakers, automatic failover, streaming normalization across four different SSE formats, and unified token/cost tracking. This is the complete model provider architecture — the BaseProvider contract, the router, the failover chain, and every edge case we hit in production. Part 4 of the Data Explorer Architecture Deep Dive.

engineeringJun 16

PostgreSQL DDL Parser from Scratch: The Architecture Behind Schema Weaver's SQL Parser v4

Every database tool that visualizes schemas, plans migrations, or powers AI agents needs to understand SQL structure. Most reach for libpg_query — a C extension that doesn't run in browsers. We built a pure TypeScript DDL parser from scratch that handles 60+ statement types across PostgreSQL 12–19, detects 11 relationship types, runs in the browser with zero dependencies, and passes 378 tests against 3,373 brutal SQL statements. This is the complete architecture — the 6-phase pipeline, the multi-strategy parser, and every design decision that makes it work.

engineeringJun 7

VivekMind CLI: The Open Source Terminal AI Coding Agent with Native AWS Bedrock

VivekMind CLI is an open source terminal AI coding agent that connects to 20+ LLM providers with your own keys — including native AWS Bedrock support for Claude, Nova, and all Bedrock models. It features subagents for parallel workflows, MCP protocol for unlimited external tools, project memory that persists across sessions, and a Telegram bot that lets you code from your phone. No subscriptions. No vendor lockup. Apache 2.0 licensed.

Build with Vivekmind.

Three products. One mission: intelligent software that moves with you.

Explore Products Get in Touch