Purpose & architecture
9.2 KB. Real. On-device. Artificial General Intelligence architecture implemented in pure C++.
This page records a pinned branch snapshot. Differences are compared with the audited default branch, not assumed to be chronological improvements. Author claims in the source documentation are retained as claims. Source recovery does not establish successful deployment, scientific validity, or equivalence with another branch.
This source generation
This record follows the claude/agi-architecture-diagram-01GJ7CohfKvLb77yiKpHqd6d branch of Janady13/ai-brain-core at commit 365850e27004318edd582881225024026b118c2d. The snapshot identifies the source inspected in this audit. It is not a statement about which revision is currently running on a device.
| Field | Source record |
|---|---|
| Revision | 365850e27004318edd582881225024026b118c2d |
| Branch | claude/agi-architecture-diagram-01GJ7CohfKvLb77yiKpHqd6d |
| Recorded generation | Preserved branch generation |
Recovered implementation structure
These paths locate the components and entry points represented by this build. The source register contains their inspected revisions.
- README.md
- frontend/index.html
- httpd.cpp
Behavior & verification limits
Read-only source inspection. No native engine, generator, database, payment, or production service was executed.
Original project documentation
The following documentation is preserved as a dated source account. Claims in it retain the source’s wording and must be read alongside the implementation notes above.
AGI Brain Core
9.2 KB. Real. On-device. Artificial General Intelligence architecture implemented in pure C++.
Architecture
- Input Processor: Clean + Tokenize natural language
- Knowledge Base: 150K+ words + learned actions (FNV-1a hashing)
- Context Memory: 64-turn circular buffer
- Scoring Engine: Energy + Context + Recency scoring
- Action Executor: fork() + execve() sandboxed execution
- Response Generator: Human-like natural language output
Quick Start
# Build the frontend server
make
# Run the server
./httpdOpen http://localhost:8080 in your browser to explore the interactive architecture diagram.
Implementation
- Pure C++ (no Python, no dependencies)
- Lightweight HTTP server for frontend
- Interactive Mermaid.js diagrams
- Real-time AGI visualization
Architecture Diagram
The frontend provides 5 interactive views: 1. Full System - Complete AGI pipeline 2. Ingestion - File system knowledge acquisition 3. Memory & Context - Circular buffer management 4. Reasoning - Scoring engine details 5. Actions - Command execution flow