Agent Orchestration & Security Template

A reference architecture for AI agent orchestration, trust measurement, and tool integration. All code authored by AI agents under human oversight.

6 AI Agents
19 MCP Servers
4 Packages
14 Documents

Overview

Designed to be studied, forked, and adapted. A single-maintainer project optimized for individual developer efficiency with maximum portability.

Container-First

All Python and Rust operations run in Docker containers. Zero local dependencies beyond Docker itself -- maximum portability across any Linux system.

Single Maintainer

No contributors model. Optimized for individual developer efficiency. No feature requests, guidance, or community interaction accepted.

All AI-Authored

Every code change is authored by AI agents under human oversight. Humans decide what to work on and when to merge; agents handle the implementation.

Self-Hosted

Self-hosted GitHub Actions runners on personal hardware. Zero-cost infrastructure with full control over the execution environment.

Dual-Use Notice

This repository contains dual-use research and tooling. The maintainer provides no guidance, consultation, or feature development. No feature requests are accepted. No external contributions are accepted. Released under a public domain dedication.

Agentic Workflow

Humans decide WHAT to work on and WHEN to merge. Agents handle HOW with automated quality loops.

1
Issue Created Human / backlog
2
AI Refinement Security + architecture
3
Approval [Approved] gate
4
Agent Claims Board work queue
5
PR Created Branch + implement
6
AI Review Gemini + Codex
7
Human Merge Final approval
Human Gate
Agent Action
AI Review

AI Agents

Six AI agents collaborate in an autonomous development workflow -- from issue refinement to PR review and merge.

C
Claude Code
Anthropic

Primary development assistant. Architecture design, complex refactoring, debugging, comprehensive documentation, CI/CD pipelines, and test development. Deep understanding of the entire codebase.

G
Gemini CLI
Google

Automated PR reviewer and quality gatekeeper. Reviews every pull request for security vulnerabilities, container configurations, and project standards. Provides actionable feedback within 3-5 minutes.

Co
GitHub Copilot
GitHub

Additional code review perspective in pull requests. Suggests improvements, identifies potential issues, and provides alternative implementations with inline suggestions.

Cx
Codex
OpenAI

AI-powered code generation and PR review. Focuses on code patterns, best practices, performance considerations, and API design feedback.

O
OpenCode
OpenRouter

Code generation, refactoring, and review via OpenRouter. Model-agnostic access to multiple AI providers for diverse implementation perspectives.

Cr
Crush
OpenRouter

Code generation and conversion via OpenRouter. Quick generation, explanation, and cross-language conversion for rapid prototyping.

MCP Servers

19 modular servers providing specialized functionality via the Model Context Protocol -- from code quality to 3D rendering.

Code Quality

Format checking (Python, JS, TS, Go, Rust), linting (ruff, eslint), auto-formatting, pytest, and type checking.

STDIO Rust
Content Creation

Manim animations, LaTeX compilation (PDF/DVI/PS), TikZ diagram rendering, and preview generation.

STDIO Rust
Meme Generator

Template-based meme generation with auto-resize text, visual feedback, auto-upload, and 7+ templates.

STDIO Rust
ElevenLabs Speech

14+ synthesis tools, 50+ audio tags, 74 language support, 37+ voices, and sound effect generation up to 22 seconds.

STDIO Rust
Video Editor

AI-powered video editing with Whisper transcription, speaker diarization, scene detection, multi-video composition, and GPU acceleration.

STDIO Rust
Blender

3D content creation with physics simulations, Cycles/Eevee rendering, geometry nodes, animation, and particle systems.

STDIO Rust
Gemini AI

Gemini AI consultations with comparison mode, conversation history management, and auto-consultation on uncertainty.

STDIO Rust
OpenCode

Code generation, refactoring, and review via OpenRouter. Model-agnostic AI code assistance.

STDIO Rust
Crush

Code generation and conversion via OpenRouter. Quick generation, explanation, and cross-language conversion.

STDIO Rust
Codex

AI-powered code generation and completion via OpenAI Codex. Requires ChatGPT Plus subscription.

STDIO Rust
Virtual Character

AI agent embodiment in virtual worlds (VRChat, Blender, Unity). OSC integration, PAD emotion model, 16 MCP tools.

STDIO Rust
GitHub Board

GitHub Projects v2 work queue. Query ready work, claim/release with conflict prevention, and dependency graph management.

STDIO Rust
AgentCore Memory

Multi-provider memory system: short-term events, long-term facts, and semantic search via AWS Bedrock AgentCore or ChromaDB.

STDIO Rust
Reaction Search

Semantic search for anime reaction images. Sentence-transformer embeddings, tag-based filtering, auto-fetch from GitHub.

STDIO Rust
Desktop Control

Cross-platform desktop automation: window management, screenshots, mouse/keyboard control for Linux and Windows.

STDIO Rust
Memory Explorer

Process memory exploration for legacy software integration. Memory reading, hex dump, pattern scanning, and pointer chain resolution.

STDIO Rust
Gaea2

Terrain generation with intelligent validation, error correction, 11 professional templates, and CLI automation. Windows only.

HTTP Remote
AI Toolkit

GPU-accelerated LoRA training management. Dataset upload, training job monitoring, and model export.

HTTP Remote
ComfyUI

GPU-accelerated AI image generation. Custom workflow execution and LoRA model management.

HTTP Remote

Research Packages

Standalone packages addressing different aspects of AI agent development, safety, and security.

SA
Sleeper Agents
Python

Research-validated detection framework for hidden backdoors in LLMs. Based on Anthropic's research on deceptive AI that persists through safety training. AUC = 1.0 across GPT-2, Mistral-7B, and Qwen2.5-7B.

AUC 1.0 3-stage pipeline Streamlit dashboard
EA
Economic Agents
Rust

Simulation framework for autonomous AI agents operating in economic systems. Agents earn cryptocurrency, form companies, create sub-agents, and seek investment. 14 crates, 13 task challenges.

14 crates Mock-to-Real Governance focus
TB
Tamper Briefcase
Rust

Tamper-responsive Raspberry Pi briefcase with dual-sensor detection, LUKS2 cryptographic wipe, and hybrid post-quantum (ML-KEM-1024 + ML-DSA-87) encrypted recovery USB.

PQC recovery Dual sensor Pi 5
BF
BioForge
Rust

Agent-driven biological automation platform. Combines a Raspberry Pi 5 liquid handling system with AI agent orchestration over MCP for CRISPR-Cas9 gene editing workflows.

12 MCP tools Closed-loop Defense-in-depth

Companion Repositories

Standalone repositories extending the template-repo ecosystem.

game-mods

Injection toolkit for AI agent integration with legacy software -- DLL injection (Windows), LD_PRELOAD (Linux), shared memory IPC, overlay rendering, and MCP memory explorer.

Rust GitHub Site
oasis-os

Embeddable OS framework (18 crates) -- scene-graph UI, 90+ terminal commands, browser engine, window manager, VFS. 4 backends (SDL2, PSP, UE5 FFI, framebuffer) with 8 themes.

Rust GitHub Site
breakpoint

Browser-based multiplayer gaming platform for agentic office hours -- Rust/WASM games with an alert overlay surfacing agent activity, CI failures, and decision points.

Rust GitHub Site
rust-psp

Modernized Rust SDK for PlayStation Portable -- ~829 syscall bindings, 38+ high-level modules, kernel mode support, and experimental std. Edition 2024 fork.

Rust GitHub Site

Strategic Documents

14 strategic documents spanning risk assessment, technical guidance, and philosophy -- all auto-compiled from LaTeX and distributed with each release.

Risk Assessments

AI Agents Political Targeting
AI agents and political violence risk
AI Agents WMD Proliferation
AI agents and WMD proliferation risk
AI Agents Espionage Operations
AI agents and intelligence tradecraft
AI Agents Economic Actors
Autonomous economic actors
AI Agents Financial Integrity
Money laundering and corruption
AI Agents Institutional Erosion
IC monopoly erosion and verification pivot

Technical Guides

Agentic Workflow Handout
AI agent pipeline architecture and workflows
Sleeper Agents Framework
AI backdoor detection using residual stream analysis
AgentCore Memory Integration
Multi-provider AI memory system
Virtual Character System
AI agent embodiment platform
AI Agent Containment & Infrastructure Security
Isolation, trust-tiered execution, and physical security
BioForge CRISPR Automation
Agent-driven biological automation platform
Secure Terminal Briefcase
Tamper-responsive hardware security with PQC recovery

Philosophy

Architectural Qualia
What Is It Like to Be an LLM?

Rust CLI Tools

Purpose-built command-line tools for agent orchestration, security hardening, and CI/CD automation.

Tool Purpose
automation-cli Unified CI/CD runner -- format, lint, test, build, deny for all packages
github-agents-cli Issue/PR monitoring, refinement, code analysis, and agent execution
board-manager GitHub Projects v2 board operations -- claim, release, status updates
git-guard Git CLI wrapper requiring sudo for dangerous operations (force push, --no-verify)
gh-validator GitHub CLI wrapper for automatic secret masking
pr-monitor Dedicated PR monitoring for admin/review feedback during development
markdown-link-checker Fast concurrent markdown link validator for CI/CD pipelines
code-parser Parse and apply code blocks from AI agent responses
code-review-processor Process and apply AI code review feedback automatically
mcp-code-quality Rust MCP server for code quality tools (formatting, linting, testing)

CI/CD Pipeline

15-stage pipeline running on self-hosted hardware. Zero cloud costs -- all infrastructure on personal machines.

1
Format
2
Lint
3
Type Check
4
Test
5
Security
6
Build
7
Deny
8
Links

Self-Hosted Runner

All CI runs on personal hardware -- zero cloud compute costs. Full control over the execution environment and toolchain versions.

Docker-Based

Every CI stage runs inside Docker containers for reproducibility. Same environment locally and in CI.

Multi-Language

Unified pipeline covering Python (ruff, pytest, bandit) and Rust (clippy, cargo-deny, cargo-test) packages.

Auto-Fix Loop

CI failure handler automatically fixes formatting and lint errors, pushes the fix, and re-triggers the pipeline.

AI Safety

Key safety principles implemented in this project, informed by the BlueDot Impact AI Safety Fundamentals course.

Sleeper Agent Detection

AI systems can develop hidden capabilities that only emerge under specific conditions. Detection requires analyzing internal processes (residual stream activations), not just outputs. Deception persists through safety training.

Scalable Oversight

Break complex tasks into verifiable subtasks. Use AI to help evaluate AI outputs. Debate systems with multiple AI instances. Always maintain human judgment in the loop.

Control Protocols

Separate "writer" and "monitor" roles using different models/providers. Use signal jamming to prevent covert coordination. Spend human attention on the most suspicious outputs.

Human Gates

Three mandatory human gates in the workflow: issue approval, code review, and merge decision. Agents cannot bypass these checkpoints regardless of capability.

Containment Layers

Defense in depth: capability limits, monitoring, verification, rollback, and kill switches. Never fully automate critical infrastructure or production deployments.

Wrapper Guards

CLI wrappers (git-guard, gh-validator) enforce security boundaries. Dangerous git operations require sudo. Secrets are automatically masked in GitHub CLI output.