IntuitAI
Non-profit AI research
Open-Source Agentic AI Research & Real-World Applications
We build open-source tools for problems people actually have — routing and caching LLM traffic, keeping multi-agent workflows from deadlocking, recovering text nobody can read any more — and we publish what we learn, free.
Mission
Our mission is to democratize artificial intelligence by developing open-source, practical solutions that tackle real-world challenges. We believe AI should be accessible to everyone, and we advance this goal through collaborative research, innovative tools, and community-driven development.
Our AI Research & Open-Source Projects
Discover our initiatives in agentic AI, LLM infrastructure, and practical machine learning. We build open-source tools that solve real-world problems through collaborative research and community-driven development.
- Model Gateway — A high-performance gateway for intelligent routing and management of Large Language Model requests across multiple providers. Features automatic failover, cost optimization, and request caching.
- Reverb — A semantic response cache with knowledge-aware invalidation for LLM applications. Provides two-tier caching (exact match and semantic similarity) to reduce redundant LLM calls, with automatic invalidation when the underlying knowledge base changes. Built in Go with pluggable backends and standalone HTTP/gRPC servers.
- Tangle — Deadlock and livelock detection for multi-agent AI workflows. Monitors agent interactions in real time, detects when agents are stuck or looping without progress, and triggers configurable resolution actions. Works as an embedded Python library or standalone FastAPI sidecar with native LangGraph and OpenTelemetry support.
- Random Number MCP Server — An MCP server that generates random numbers using national weather data as entropy sources. Built with the FastMCP framework and includes comprehensive test coverage.
- QuranLLM — An LLM-powered search application for the Quran that leverages artificial intelligence to enable intelligent querying and semantic search of Islamic scripture.
- Recovering text from obsolete PDF — Recovering Bengali text from a legacy PDF memoir encoded with the proprietary SutonnyMJ ANSI font by using Tesseract 5.x's LSTM neural-network OCR on rasterized page images, achieving 98–99% accuracy. The machine learning approach bypassed the intractable problem of reverse-engineering ANSI-to-Unicode font mappings by treating visual glyph recognition as an image classification task, successfully converting the document to clean UTF-8 Unicode text in the pdf book. Technical report
Books
We publish free, open educational material alongside our software.
Everyday Programming Free
Volume I: Basics of Computer Programs, by Dr. Nobel Khandaker. A first course in Python for absolute beginners, built on nothing more than tenth-grade mathematics. Twenty-one chapters in seven parts, plus 445 Find the Bug exercises with full worked solutions, and a free sample of Chapters 1–2. Text and code licensed under Apache 2.0.
- 21chapters, in seven parts
- 445Find the Bug exercises
- 890runnable Python programs
- Freeto read, in full, online
Source code · Machine learning icons created by Becris — Flaticon