Template Repo

Agent Orchestration & Security Template

A reference architecture for AI agent orchestration, trust measurement, and tool integration. Designed to be studied, forked, and adapted -- not contributed to directly. All code changes in this repository are authored by AI agents under human oversight. Browse the project showcase for an overview.

This repo demonstrates how to run a council of AI agents (Claude, OpenCode, Crush) across a shared codebase with board-driven task delegation, automated PR review, security hardening, and containerized tooling. (OpenAI/Google integrations have been disabled -- see [security notice](#ai-agents).) It also includes standalone research packages for sleeper agent detection, autonomous economic agent simulation, and tamper-responsive hardware. Several [companion repositories](#companion-repositories) consume or extend the functionality of this project.

Use this repo to learn how to:

• Orchestrate multiple AI agents with a GitHub Projects v2 work queue
• Measure and enforce trust boundaries for autonomous agents (wrapper guards, iteration limits, claim tracking)
• Integrate 20 MCP servers spanning code quality, content creation, 3D graphics, video editing, and speech synthesis
• Build hardened CI/CD pipelines for agent-authored code (15-stage pipeline, security scanning, multi-arch Docker builds)
• Detect sleeper agent behaviors via residual stream analysis and linear probes
• Integrate AI agents into legacy software via runtime injection, shared memory IPC, and overlay rendering

---

> Important: This is an advanced template designed for experienced developers working with autonomous AI agents. Before diving in, we strongly recommend: > > 1. Read the [AI Safety Training Guide](docs/agents/human-training.md) - Essential concepts for safe human-AI collaboration, including deception detection, scalable oversight, and control protocols > > 2. Take an AI Safety course at BlueDot Impact - Free, rigorous training programs covering AI safety fundamentals, governance, and alignment > > Working with AI agents introduces risks that differ fundamentally from traditional software. Understanding these risks isn't optional - it's a prerequisite for responsible development.

---

Legal Notice

> This repository contains dual-use research and tooling. The maintainer provides no guidance, consultation, or feature development -- whether solicited or unsolicited, compensated or uncompensated. This policy exists as a legal protection given the nature of the codebase. > > - No feature requests will be accepted. Money does not change this. > - No guidance or consulting will be provided on usage, adaptation, or deployment of any component. > - No external contributions are accepted. See [CONTRIBUTING.md](CONTRIBUTING.md). > - The maintainer does not seek or engage with community interaction. Public comments, issues filed by external parties, events, and news surrounding this repository or its components may be ignored without response to maintain neutrality and legal distance. > - No endorsement is implied. The existence of code in this repository does not constitute encouragement, recommendation, or endorsement of any particular use. > > This repository is released under a public domain dedication. You may fork and adapt it freely. The maintainer assumes no obligation to any downstream user for any reason.

Project Philosophy

This project follows a container-first approach:

• All tools and CI/CD operations run in Docker containers for maximum portability
• Zero external dependencies - runs on any Linux system with Docker
• Self-hosted infrastructure - no cloud costs, full control over runners
• Single maintainer design - optimized for individual developer productivity, no contributors model
• Modular MCP architecture - Separate specialized servers for different functionalities

Quick Start

> New to the template? Check out our [Template Quickstart Guide](docs/QUICKSTART.md) for step-by-step customization instructions!

1. Prerequisites: Linux system with Docker (v20.10+) and Docker Compose (v2.0+)

1. Clone and setup

``bash git clone https://github.com/AndrewAltimit/template-repo cd template-repo # Build the Rust CLI tools (optional - pre-built binaries available in releases) cd tools/rust/board-manager && cargo build --release cd ../github-agents-cli && cargo build --release ``

1. Set API keys (if using AI features)

``bash export OPENROUTER_API_KEY="your-key-here" # For OpenCode/Crush ``

1. Use with Claude Code: MCP servers are configured in .mcp.json and auto-started by Claude. See [MCP Configuration](docs/mcp/README.md#configuration-strategy) for essential vs full setups.

1. Run CI/CD operations

``bash automation-cli ci run full # Full pipeline ``

For detailed setup, see [CLAUDE.md](CLAUDE.md) and [Template Quickstart Guide](docs/QUICKSTART.md).

AI Agents

Six AI agents for development and automation. See [AI Agents Documentation](docs/agents/README.md) for details.

> Security Notice -- OpenAI/Google Disabled: OpenAI/Google integrations are disabled within PR reviews. OpenAI/Google permits government partners unrestricted use of their models. We only allow models with explicit prohibitions on mass surveillance and autonomous weapons.

| Agent | Provider | Use Case | Documentation | |-------|----------|----------|---------------| | Claude Code | Anthropic | Primary development assistant (recommended) | [Setup Guide](docs/agents/claude-code-setup.md) | | Codex | ~~OpenAI~~ | ~~Code generation~~ DISABLED - security risk | [Setup Guide](docs/agents/codex-setup.md) | | OpenCode | OpenRouter | Code generation | [AI Code Agents](docs/integrations/ai-services/ai-code-agents.md) | | Crush | OpenRouter | Code generation | [AI Code Agents](docs/integrations/ai-services/ai-code-agents.md) | | Gemini | ~~Google~~ | ~~Code review~~ DISABLED - security risk | [Setup Guide](docs/integrations/ai-services/gemini-setup.md) | | GitHub Copilot | GitHub | PR review suggestions | - |

OpenCode and Crush provide equivalent code generation functionality via OpenRouter. Codex (OpenAI) and Gemini (Google) have been disabled -- see security notice above.

Security: Keyword triggers, user allow list, secure token management. See [Security Model](docs/agents/security.md)

Safety Training: Essential AI safety concepts for human-AI collaboration. See [Human Training Guide](docs/agents/human-training.md)

Sleeper Agents: Create and evaluate sleeper agents in order to detect misalignment and probe for deception. See [Sleeper Agents Package](packages/sleeper_agents/README.md)

Agentic Git Workflow

AI agents autonomously manage the development lifecycle from issue creation through PR merge:

Issue Created → Admin Approval → Agent Claims → PR Created → AI Review → Human Merge

The Flow:

1. Issue Creation - Issues are created manually or by agents via backlog-refinement.yml, automatically added to the GitHub Projects board
2. Admin Approval - An authorized user comments [Approved][Claude] (or another agent name) to authorize work
3. Agent Claims - board-agent-worker.yml finds approved issues, the agent claims the issue and creates a working branch
4. Implementation - The agent implements the fix/feature and opens a PR
5. AI Review - pr-validation.yml triggers AI code review (Claude + OpenRouter); pr-review-monitor.yml lets agents iterate on feedback
6. Human Merge - Admin reviews and merges the PR

Security Model:

• Approval Required - Agents cannot work on issues without explicit [Approved][Agent] comment
• Authorized Users Only - Only users listed in .agents.yaml → security.agent_admins can approve
• Pattern Validation - Must use [Action][Agent] format (e.g., [Approved][Claude]) to prevent false positives
• Claim Tracking - Agents post claim comments with timestamps to prevent conflicts

See [Security Documentation](docs/agents/security.md) for the complete security model.

Reports & Research

Technical reports and guides exploring AI risks, safety frameworks, and philosophical questions. PDFs are automatically built from LaTeX source and published with each release.

Emerging Technology Risk Assessments

Scenario-based projection reports analyzing potential futures involving advanced AI systems. See [Projections Documentation](docs/projections/README.md).

| Report | Topic | PDF | Source | |--------|-------|-----|--------| | AI Agents Political Targeting | Political violence risk | Download | [LaTeX](docs/projections/latex/ai-agents-political-targeting.tex) | | AI Agents WMD Proliferation | WMD proliferation risk | Download | [LaTeX](docs/projections/latex/ai-agents-wmd-proliferation.tex) | | AI Agents Espionage Operations | Intelligence tradecraft | Download | [LaTeX](docs/projections/latex/ai-agents-espionage-operations.tex) | | AI Agents Economic Actors | Autonomous economic actors | Download | [LaTeX](docs/projections/latex/ai-agents-economic-actors.tex) | | AI Agents Financial Integrity | Money laundering & corruption | Download | [LaTeX](docs/projections/latex/ai-agents-financial-integrity.tex) | | AI Agents Institutional Erosion | IC monopoly erosion & verification pivot | Download | [LaTeX](docs/projections/latex/ai-agents-institutional-erosion.tex) |

Technical Guides

| Guide | Description | PDF | Source | |-------|-------------|-----|--------| | Agentic Workflow Handout | AI agent pipeline architecture and workflows | Download | [LaTeX](docs/agents/AgenticWorkflowHandout.tex) | | Sleeper Agents Framework | AI backdoor detection using residual stream analysis | Download | [LaTeX](packages/sleeperagents/docs/SleeperAgentsFrameworkGuide.tex) | | AgentCore Memory Integration | Multi-provider AI memory system | Download | [LaTeX](docs/integrations/ai-services/AgentCoreMemoryIntegrationGuide.tex) | | Virtual Character System | AI agent embodiment platform | Download | [LaTeX](docs/integrations/ai-services/VirtualCharacterSystemGuide.tex) | | AI Agent Containment & Infrastructure Security | Isolation, trust-tiered execution, and physical security for AI agents | Download | [LaTeX](docs/hardware/latex/ai-agent-containment-infrastructure-security-framework.tex) | | BioForge CRISPR Automation | Agent-driven biological automation platform | Download | [LaTeX](docs/hardware/latex/bioforge-crispr-automation.tex) | | Secure Terminal Briefcase | Tamper-responsive hardware security system with PQC recovery | Download | [LaTeX](docs/hardware/latex/secure-terminal-briefcase.tex) |

Philosophy Papers

Philosophical explorations of minds, experience, and intelligence. See [Philosophy Papers Documentation](docs/philosophy/README.md).

| Paper | Topic | PDF | Source | |-------|-------|-----|--------| | Architectural Qualia | What Is It Like to Be an LLM? | Download | [LaTeX](docs/philosophy/latex/architectural-qualia.tex) |

Build Status: [](https://github.com/AndrewAltimit/template-repo/actions/workflows/build-docs.yml)

Packages

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

| Package | Purpose | Documentation | |---------|---------|---------------| | [Sleeper Agents](packages/sleeperagents/) | Research-validated detection framework for hidden backdoors in LLMs, based on Anthropic's research on deceptive AI that persists through safety training | [README](packages/sleeperagents/README.md) \| PDF Guide | | [Economic Agents](packages/economicagents/) | Rust-based simulation framework demonstrating autonomous AI economic capability - agents that earn money, form companies, hire sub-agents, and seek investment. For governance research and policy development | [README](packages/economicagents/README.md) | | [Tamper Briefcase](packages/tamperbriefcase/) | Tamper-responsive Raspberry Pi briefcase with dual-sensor detection, LUKS2 cryptographic wipe, and hybrid PQC recovery USB. For secure physical transport of field-deployable agent terminals | [README](packages/tamper_briefcase/README.md) \| [Hardware Docs](docs/hardware/secure-terminal-briefcase.md) |

Rust CLI Tools (in tools/rust/):

| Tool | Purpose | Documentation | |------|---------|---------------| | [github-agents-cli](tools/rust/github-agents-cli/) | Issue/PR monitoring, refinement, code analysis, and agent execution | [README](tools/rust/github-agents-cli/README.md) | | [board-manager](tools/rust/board-manager/) | GitHub Projects v2 board operations - claim, release, status updates | [README](tools/rust/board-manager/README.md) | | [git-guard](tools/rust/git-guard/) | Git CLI wrapper requiring sudo for dangerous operations (force push, --no-verify) | [README](tools/rust/git-guard/README.md) | | [gh-validator](tools/rust/gh-validator/) | GitHub CLI wrapper for automatic secret masking | [README](tools/rust/gh-validator/README.md) | | [pr-monitor](tools/rust/pr-monitor/) | Dedicated PR monitoring for admin/review feedback during development | [README](tools/rust/pr-monitor/README.md) | | [markdown-link-checker](tools/rust/markdown-link-checker/) | Fast concurrent markdown link validator for CI/CD pipelines | [README](tools/rust/markdown-link-checker/README.md) | | [code-parser](tools/rust/code-parser/) | Parse and apply code blocks from AI agent responses | [README](tools/rust/code-parser/README.md) | | [mcp-code-quality](tools/mcp/mcpcodequality/) | Rust MCP server for code quality tools (formatting, linting, testing) | [README](tools/mcp/mcpcodequality/README.md) |

Companion Repositories

| Repository | Description | Documentation | |------------|-------------|---------------| | game-mods | Injection toolkit for AI agent integration with legacy software -- DLL injection (Windows), LDPRELOAD (Linux), shared memory IPC, overlay rendering, and MCP memory explorer for process introspection | README | | oasis-os | Embeddable OS framework (18 crates) -- scene-graph UI, 90+ terminal commands, browser engine (HTML/CSS/Gemini), window manager, VFS, plugin system, and remote terminal. 4 backends (SDL2, PSP via rust-psp, UE5 FFI, planned framebuffer) with 8 skinnable themes. Used as the shell environment for the Tamper Briefcase | README \| Design Doc | | breakpoint | Browser-based multiplayer gaming platform for agentic office hours -- Rust

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: AndrewAltimit
• Source: AndrewAltimit/template-repo
• License: Unlicense
• Homepage: https://andrewaltimit.github.io/template-repo/

Install and usage instructions live in the source repository linked above.