tableArth.ai

Loktra

Loktra is an AI data assistant for SaaS teams, enabling natural language queries across SQL databases and internal documents within a single conversation. It provides sourced answers, linking every data point to specific rows or document pages. With audit logs and role-based access control, Loktra ensures data conclusions are traceable and verifiable, streamlining data access for non-technical users.

MindReader

MindReader is a fully open-source AI tool that simulates how a brain responds to content, region by region. It is built on Meta FAIR's TRIBE v2 and 35 years of neuro research. The project encourages tinkering and invites academic collaboration. Public information is limited; see the official site for details.

TableTurn

TableTurn is an AI-powered chart report tool. Pick X/Y columns to generate shareable charts. AI reads data, finds patterns, and writes summaries. Supports Google Sheets and CSV, with paste link or drag-and-drop. Utilizes DeepSeek V4 Pro, matching GPT-4 on translation and reasoning benchmarks at 10x lower cost. Supports 20+ languages.

Echo Chamber Analytics Engine

The Echo Chamber Analytics Engine is a live data pipeline that tracks online groups worldwide. It collects global media streams in real time and uses AI tools like DistilBERT and K-Means clustering to sort text into distinct narrative bubbles. It also tracks emotional shifts and calculates an Echo Chamber Index to score polarization. This tool helps users, investors, and developers monitor narrative trends as they happen.

MarginWard

MarginWard connects LLM cost data with Stripe revenue to show per-customer gross margin for AI SaaS teams, flagging accounts that lose money.

Quation

Quation is a data analytics company that turns raw data into actionable insights. It offers customized analytics solutions across manufacturing, healthcare, retail, banking, logistics, and more, helping organizations improve decision-making and optimize operations.

Banana Slides: AI-native slide generator built on Nano Banana Pro

Banana Slides is an AI-native slide generator built on Nano Banana Pro. It accepts a single sentence, an outline, or an uploaded document to produce editable PPTX or PDF decks with transitions, extractable text, and optional AI voiceover narration. It runs locally or in Docker under an AGPL-3.0 license, noted as non-commercial. Primary languages are Python and React. As of collection, it has 14,811 stars on GitHub.

fiftyone: Open-source Computer Vision Workbench

fiftyone is an open-source computer vision workbench developed by Voxel51, providing a unified Python API to visualize datasets, curate data, evaluate models, and fix labels. The project is primarily written in Python, licensed under Apache-2.0, with 10787 GitHub stars as of collection time.

Quilt: AWS-Based Scientific Data Management Platform

Quilt is an open-source scientific data management platform built on AWS. It helps teams and AI systems efficiently find, trust, and reuse data through deep versioning and rich contextual data packages. The project targets research and AI development teams that require reproducibility and traceability in data workflows. Its primary language is TypeScript, and it is licensed under Apache-2.0.

materialize: Streaming SQL database that keeps PostgreSQL views live

materialize is a streaming SQL database written in Rust. It keeps PostgreSQL-dialect views live as data changes, allowing applications and AI agents to query fresh joined state with low latency. The project has an Other license and, as of collection time, had 6324 GitHub stars.

portaljs: Build Data Portals with Natural Language, AI-Native Framework

portaljs is an open-source, AI-native framework that enables users to build data portals using natural language descriptions. It loads datasets from various backends like CKAN and GitHub in minutes, making it suitable for governments, research institutions, and businesses to quickly publish data assets and lower the barrier to portal creation. The primary language is TypeScript, licensed under MIT, with 2281 GitHub stars at the time of collection.

saiku: Open-source semantic layer based on Mondrian and Calcite

saiku is an open-source semantic layer built on Mondrian and Apache Calcite, unifying data access across various tools. It provides a consistent data cube, supporting queries from Excel (via MDX/XMLA), traditional dashboards, and AI agents (using the MCP protocol). This simplifies data access and ensures a shared business semantic layer, ideal for enterprise teams.