I build local AI inference engines, developer tooling, compilers, and multi-agent systems from scratch in Rust, TypeScript, Python, and C++. Most of my projects focus on running large models on consumer hardware, verifying LLM outputs against real data, and keeping infrastructure fast and self-contained.
| Project | Category | Stack | Description | |
|---|---|---|---|---|
| 🚀 | HARNESS | Local Coder Agent Engine | Rust · Axum · wgpu/CUDA · VS Code API | Local 30B to 32B Coder Agent Engine & Native VS Code Chat Provider: Runs Qwen3-Coder-30B-A3B Sparse MoE & Qwen2.5-Coder-32B at 16k to 64k context on 8 GB VRAM (446.86 tok/s prefill, 21.40 tok/s decode, 100% HumanEval+) |
| ⚡ | ChronoFact | Epistemic AI Backbone | Rust · Tokio · SQLite WAL · React 19 | 4-Pillar Epistemic AI Backbone: Real-time temporal cutoff calibration, Pre-NLI claim verifier (<0.15ms), zero-pollution L1 to L3 memory, and TF-IDF tool pruning (124/124 unit + 140/140 blind held-out tests) |
| 🛡️ | SPINE | Behavioral AI Firewall | Rust · Axum · React 19 HUD | Biological-Cybernetic Anti-Sycophancy Reality Gateway: 33-vertebrae epistemic firewall, Level 1 to 4 Brutal Reality dial, reflexive apology interception, and pushback verification (58/58 unit + 100/100 blind held-out tests) |
| 📱 | PulseBridge | Remote AI IDE Bridge | Rust · Win32 GDI · Axum · React 19 PWA | Universal Remote AI IDE Companion & Telemetry Bridge: 75.5 req/sec Win32 GDI desktop streaming, bidirectional caret injection, 7 to 30d multi-IDE discovery, and Zero-Trust SecOps (62/62 verified) for Antigravity, Cursor, and VS Code |
| 🌐 | MCPlex | Agent Infrastructure | Rust · Tokio · Axum | The MCP Smart Gateway: Semantic tool routing (70% to 90% token savings), RBAC guardrails, Prometheus metrics, and multi-model support |
| 🔍 | AgentLens | Observability | TypeScript · React 19 · Next.js | Chrome DevTools for AI Agents: Time-travel debugging, real-time per-model token & cost tracking, anomaly detection, and native MCP support |
| 🔥 | The Forge | Code Evolution | Python · Vitalis JIT · Multi-LLM | Multi-Agent Code Evolution: 4 LLMs compete head-to-head in an arena, judged by a JIT compiler and bred across generations |
| 🦀 | Vitalis | Compilers & Languages | Rust · Cranelift JIT + AOT | Custom self-evolving compiled language: 345 modules, 6,742 tests, native x86-64, ARM64, and RISC-V execution |
| 🧠 | Gestalt Blueprint | Cognitive Systems | Python · FastAPI · Multi-GPU | Cognitive Architecture & Blueprint Engine: Cross-platform multi-GPU hardware profiling, dynamic VRAM fit, and local SLM synthesis |
| 🏆 | Neuromantix ARC-AGI-3 | Neuro-Symbolic AI | Python · SMT · Z3 · AST | 88.0% Verified Win Rate (22/25 Games Won) on ARC-AGI-3 with bit-exact deterministic replay |
| 📊 | Neuromantix LiveBench | AI Benchmarking | Python · Symbolic Engines | Official LiveBench submission: 97.0% Reasoning, 100% Data Analysis, 81% Math |
| ✨ | Humaniser | Privacy & NLP | Vanilla JS · Web APIs | Zero-dependency AI writing humaniser with multi-provider Deep Rewrite (OpenAI, Gemini, Claude, DeepSeek) |
| 📈 | Infinity Signal | Quant Systems | Next.js · TypeScript | Multi-indicator market dashboard (15 indicators, 33 instruments, 4 timeframes) |
| 🛡️ | Infinity Security | IAM & Zero-Trust | Rust · Axum · OIDC | Open-source, Rust-native replacements for SaaS: Infinity ID secure IAM (OIDC/OAuth2, MFA, RBAC) + edge gateway |
⚡ ChronoFact · The 4-Pillar Epistemic AI Backbone
A fast Rust microservice, MCP server, and React 19 cockpit built to solve model training freezes, hallucinations, cross-session amnesia, and token cost bloat across frontier LLMs (Gemini 4 Argon, Claude Opus 5.5, GPT-6 Astra/Sol, Grok 4.7).
|
🕒 Temporal Radar Tracks weight freeze vs. cutoff deltas and triggers SSRF-safe live web grounding when temporal risk >= 0.35 |
🛡️ Pre-NLI Verifier Decomposes outputs into atomic claims and audits against evidence & CI code invariants in <0.15ms |
🧠 Zero-Pollution Memory 3-tier L1/L2/L3 SQLite WAL dossier with adaptive quantile gating (0 unrelated tokens leaked across sessions) |
✂️ Token Cost Optimizer Intent-boosted TF-IDF schema pruning (70% to 92% token cut) with 1,024-token prompt cache prefix floor alignment |
🛡️ SPINE · Biological-Cybernetic Anti-Sycophancy Reality Gateway & HUD
A biological-cybernetic firewall and anti-sycophancy gateway mapping human spinal biomechanics to 33 discrete epistemic invariants (C1 to C7, T1 to T12, L1 to L5, S1 to S5, Co1 to Co4). SPINE strips flattery traps, ignores credential intimidation, intercepts unearned apologies in real-time SSE streams, and streams live vertebral telemetry to a React 19 HUD (:3333).
|
Core Epistemic Defenses
|
Production & Enterprise Capabilities
|
🚀 HARNESS · Local 30B to 32B Coder Agent Engine, Native VS Code Chat Provider & Rust GPU Suite
An open-source local coding agent engine, lossless Rust/Axum OpenAI proxy (crates/harness-server), native VS Code Language Model Chat Provider extension (vscode.lm.registerLanguageModelChatProvider), and standalone Rust/wgpu GPU kernel & safety suite built to run 30B to 32B Coder models (Qwen3-Coder-30B-A3B-Instruct Sparse MoE, Qwen2.5-Coder-32B-Instruct Dense, Qwen2.5-Coder-14B-Instruct) at full 16k to 64k agentic context windows on an 8 GB VRAM GPU (RTX 5060 8,151 MiB GDDR7 + 32 GB DDR4).
|
Long-Context 8 GB VRAM Engine & Native VS Code Agent
|
Verified SWE Benchmarks & Standalone Rust
|
📱 PulseBridge · Universal Remote AI IDE Companion & Telemetry Bridge
A zero-dependency Rust host daemon (pulsebridge-server), mobile-first React 19 progressive web app (pulsebridge-web), VS Code/Cursor companion extension (pulsebridge-extension), and Model Context Protocol server (pulsebridge-mcp) that streams your workstation's AI IDE (Google Antigravity, Cursor, VS Code) and live agent reasoning directly to your phone over LAN or TLS-encrypted WAN/4G tunnels.
|
TeamViewer IDE Streaming & Multi-Workspace Control
|
Zero-Trust SecOps Architecture (
|
⚡ MCPlex · The Model Context Protocol Smart Gateway
A high-throughput, asynchronous gateway for the Model Context Protocol (MCP) written in Rust. MCPlex sits between AI agents and dozens of MCP tool servers to route requests, cut token bloat, and enforce RBAC policies.
|
🎯 Semantic Routing Dynamic vector-based tool selection saving 70% to 90% in prompt token overhead per agent turn |
🔒 RBAC Guardrails Fine-grained authorization, tool execution policies, and dangerous argument sanitization |
📊 Observability Prometheus metrics, latency histograms, and structured JSON audit logs for production runs |
⚡ Rust-Native Speed Sub-millisecond routing overhead built on Tokio async runtime and Axum web framework |
┌─────────────────────────────────────────────────────────────┐
│ AI Agent (Claude / GPT-4o / Gemini / Local SLM / Cursor) │
└──────────────────────────────┬──────────────────────────────┘
│ MCP Request (JSON-RPC)
▼
┌─────────────────────────────────────────────────────────────┐
│ ⚡ MCPlex Smart Gateway │
│ • Token Optimizer • RBAC Guardrails • Prometheus Monitor │
└──────────────┬───────────────┼───────────────┬──────────────┘
▼ ▼ ▼
[ Local Filesystem ] [ PostgreSQL ] [ GitHub / Slack ]
🔍 AgentLens · Chrome DevTools for AI Agents
An interactive developer cockpit and observability tool built for agentic LLM workflows. Inspect multi-turn agent execution loops, track per-model token spend in real time, and debug tool-calling failures.
|
Key Features
|
Observability Panels
|
🔥 The Forge · Multi-Agent Code Evolution Arena
An open-source multi-agent code evolution platform where 4 distinct LLMs compete in an arena to generate, optimize, and evolve algorithmic implementations. Solutions are judged by an automated JIT compiler test suite and bred across generations using genetic algorithms.
|
Evolutionary Workflow
|
Engine Highlights
|
🧬 Vitalis · The Self-Evolving Programming Language
A compiled programming language built from scratch in Rust that generates native machine code via Cranelift JIT and AOT. Includes a built-in code evolution engine, static effect system, and lifetime analysis. Cross-compiles to x86-64, AArch64 (ARM64), and RISC-V 64.
Source (.sl) → Lexer → Parser → AST → Type Checker → SSA IR → Optimize → Cranelift → Native Binary
↕
C FFI & Python Bridge
|
Compiler Pipeline
|
Runtime Features
|
🧠 Gestalt Blueprint · Cognitive Architecture Engine
Cross-platform multi-GPU hardware profiling, practical VRAM model fitting, and local small-language-model (SLM) synthesis. Dynamically allocates tasks across available compute tiers (discrete GPUs, Apple Silicon Unified Memory, and CPU fallbacks).
🛠️ Free Developer Tools & Ecosystem (infinitytechstack.uk)
A collection of 13+ developer tools, interactive AI academies, and browser utilities. Everything is free to use with no sign-up required.
|
Free Developer Tools
|
Interactive Academies & Resources
|
|
Languages |
AI & ML |
Cloud & DevOps |
Security |
Admin |
|
|
|
|
|
|
- 🚀 HARNESS: Local 30B to 32B Sparse MoE & Dense Coder inference at 16k to 64k context on 8 GB VRAM with native VS Code Language Model Chat Provider multi-tool agent integration
- ⚡ ChronoFact & SPINE Dual-Pillar Grounding: Real-time temporal horizon calibration, Pre-NLI claim verification, and 33-vertebrae anti-sycophancy enforcement for frontier models (
Gemini 4 Argon,Claude Opus 5.5,GPT-6 Astra) - 📱 PulseBridge:
75.5 req/secWin32 GDI remote AI IDE streaming, 7 to 30d multi-IDE workspace discovery, and Zero-Trust mobile human-in-the-loop MCP telemetry for Antigravity, Cursor, and VS Code - 🌐 Expanding MCPlex smart gateway with dynamic semantic routing and vector tool-indexing
- 🔍 Advancing AgentLens for deep inspection and real-time cost tracking of multi-agent runtimes
- 🧬 Vitalis compiler cross-compilation (x86_64, AArch64, RISC-V) and self-hosted bootstrap pipeline
- 🤖 Scaling multi-agent code evolution and Pareto consensus in The Forge
- 🛡️ Open-source zero-trust security architectures, IAM, and AI agent guardrails
Building systems from the ground up.
100% Open-Source Focus · Rust · Python · TypeScript · C++ · Model Context Protocol (MCP)