Clarity for Every Concept. Where Knowledge Becomes Insight.
Features • Tech Stack • Licensing • Support
Academic Oracle is a learning-focused AI platform designed to maximize understanding, not passive consumption.
Instead of immediately giving answers, Academic Oracle follows a scientifically grounded flow:
Ask → Think → Hint → Attempt → Feedback → Pattern → Insight → Mastery
The goal is not memorization — it’s deep, durable learning.
Most AI tools optimize for speed.
Academic Oracle optimizes for retention, intuition, and reasoning.
- Active recall before answers
- Progressive hinting instead of instant solutions
- Error-correction loops
- Pattern discovery over rote explanation
- Minimal UI disruption to maintain cognitive flow
You don’t just learn faster — you learn properly.
- Hint-based reasoning flow (Ask first, reveal progressively)
- Structured thinking prompts with richer Oracle Memory JSON returns
- Feynman-technique reinforcement when understanding needs to be rebuilt from first principles
- Exam-style adaptation and wider mastery branching for more context-aware coaching
- Pattern extraction instead of answer dumping
- Follow-up suggestion system (NEW v2.3.0)
- Context-aware follow-up buttons appear on text selection
- Enables deeper exploration without breaking learning flow
- Reduces friction between curiosity → action
- Auto-generated concept-specific quizzes
- Multi-question adaptive testing
- Mastery popups & performance feedback
- Reinforcement-based correction
- Mid-session language switching
- Unified Chat + Quiz UI system
- Short-query routing can jump directly into Balanced race mode for fast lightweight prompts
- Dedicated dashboard tab for learner overview and progress reflection
- Displays user profile, academic level, current topic, and learning level
- Circular learning-efficiency indicator based on tracked performance
- Expandable topic panels with key notes, formulas/cues, quiz attempts, and recommended next focus
- Surfaces strengths, weaknesses, and overall session summary in one place
- Integrated Download Session Summary action from the dashboard
- Multi-mode execution pipeline:
- Standard
- Fast
- Balanced
- Agentic
- Web Search
- Real-time system state visibility via Loading Status Text Bar
- Displays current processing stage
- Improves transparency of AI behavior
- Dynamic routing based on:
- Query complexity
- Latency conditions
- System load
Academic Oracle doesn’t just respond — it decides how to think first.
- JigsawStack-powered search pipeline
- Designed for:
- Real-time knowledge retrieval
- SPA / dynamic site parsing
- Activated only when needed (cost-efficient routing)
- Hybrid reasoning:
- AI + live data synthesis
- All AI API calls moved to Supabase backend
- No direct client exposure of sensitive keys
- Production-grade architecture
- Secure Edge Function orchestration
- Core prompt logic migrated into Supabase Edge Functions for tighter backend control
- Encrypted handling of sensitive internal data
- Supabase-backed session continuity
- Jailbreak detection & filtering system
- Prompt sanitation before model execution
- Controlled response shaping to prevent misuse
Academic Oracle is no longer just a frontend AI tool —
it is a secured distributed AI system.
- Robust Markdown rendering
- Math (KaTeX)
- Tables
- Code blocks
- Dark / Light mode
- Responsive design (desktop & mobile)
- Structured session summary generation backed by Oracle Memory data
- Non-blocking UI architecture
- Failures never crash the interface
- Graceful degradation on errors
- Node.js (v18+ recommended)
- Install dependencies:
npm install- Setup your Supabase project
- Create database
- Configure auth
- Deploy Edge Functions
- Configure public environment variables:
VITE_SUPABASE_URL=YOUR_SUPABASE_URL
VITE_SUPABASE_ANON_KEY=YOUR_SUPABASE_ANON_KEY
VITE_JIGSAWSTACK_KEY=YOUR_JIGSAWSTACK_API_KEY- Start development server:
npm run devImportant Note
This public repository intentionally excludes certain backend infrastructure, deployment configuration, and protected service implementation details.
As a result, some advanced production features may not be fully reproducible from the public repository alone.
- Frontend: React 19 + TypeScript
- Backend (AI Orchestration): Supabase Edge Functions
- Models:
- Google GenAI (Gemini-3, Gemini-2.5)
- Minimax-2.5 (fallback / high-load routing)
- Web Search: JigsawStack API
- Auth & Database: Supabase (Postgres + OAuth)
- Build Tool: Vite 6
- Styling: Tailwind CSS
- Math Rendering: KaTeX
Academic Oracle aims to redefine how AI integrates into education:
- Not as a solver.
- Not as a shortcut.
But as a structured reasoning partner.
The long-term goal is to build a universal academic cognition system that scales from secondary education to research-level inquiry.
This is the official upstream source repository for Universal Academic Oracle.
Canonical source:
https://github.com/Henrycoding-design/Academic-Oracle-AI-Chatbot-Model
Live product:
https://academicoracle.onrender.com
This repository uses a mixed-license structure.
Unless otherwise stated, the public code in this repository is licensed under the Apache License 2.0.
However, selected files containing core product logic, orchestration behavior, service intelligence, and project-defining implementation details are excluded from Apache-2.0 and remain All Rights Reserved.
Public visibility of excluded files does not grant permission to copy, redistribute, or reuse them outside the official upstream repository.
See:
The project name, branding, visual identity, screenshots, release identity, and related non-code brand elements are not granted under Apache-2.0 unless explicitly stated otherwise.
Forks, mirrors, and derivative versions may not present themselves as the official version of this project or imply endorsement by the original author.
See:
Universal Academic Oracle was designed and built by Vo Tan Binh (Henrycoding-design).
This project represents original work in:
- Learning-science–driven AI interaction design
- Progressive reasoning and hint-based pedagogy
- Closed-feedback AI tutoring systems
- Secure, minimal, and distraction-free educational UX
If you build on Apache-licensed portions of this project, please preserve attribution and clearly reference the original source.
For protected files, branding, and excluded components, refer to the repository's licensing and policy documents.
If Academic Oracle helps your learning:
-
⭐ Star the repository
-
☕ Support via Buy Me a Coffee