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.
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers
星數
133
工具
—
可用率
—
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. It also includes standalone research packages for sleeper agent detection, autonomous economic agent simulation, tamper-responsive hardware, and lab automation. Several 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 19 active MCP servers spanning code quality, content creation, 3D graphics, video editing, and speech synthesis
Train sleeper-agent model organisms and probe them with residual stream analysis and linear probes (known-trigger backdoors are confirmed and localized; detecting an unknown backdoor is not yet demonstrated)
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:
Read the AI Safety Training Guide - Essential concepts for safe human-AI collaboration, including deception detection, scalable oversight, and control protocols
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.
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 for step-by-step customization instructions!
Prerequisites: Linux system with Docker (v20.10+) and Docker Compose (v2.0+)
Clone and setup
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
Set API keys (if using AI features)
export OPENROUTER_API_KEY="your-key-here" # For OpenCode/Crush
Use with Claude Code: MCP servers are configured in .mcp.json and auto-started by Claude. See MCP Configuration for essential vs full setups.
Active agents: Claude Code (primary; also runs the security and quality PR reviews), OpenRouter (general PR review via qwen/qwen3.7-max), OpenCode and Crush (code generation via OpenRouter), and GitHub Copilot (PR suggestions). Gemini and Codex code remains in the repo but is legacy / not allowed (why).
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.
Python + Rust research framework for evaluating hidden backdoors in LLMs (confirms and localizes backdoors with a known trigger; unknown-backdoor detection is not yet demonstrated), based on Anthropic's research on deceptive AI that persists through safety training
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
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
Agent-driven biological automation platform (Rust): Raspberry Pi 5 liquid handling with AI agent orchestration over MCP, gated by a safety enforcer. Simulated hardware
Injection toolkit for AI agent integration with legacy software: DLL injection (Windows), LD_PRELOAD (Linux), shared memory IPC, overlay rendering, and MCP memory explorer for process introspection
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
Browser-based multiplayer gaming platform for agentic office hours: Rust/WASM games (mini-golf, platform racer, laser tag) with an alert overlay that surfaces agent activity, CI failures, and decision points directly into the shared session. WSS on port 443 for corporate networks
# Run CI operations via automation-cli
automation-cli ci run format # Check formatting
automation-cli ci run lint-basic # Basic linting
automation-cli ci run test # Run tests
automation-cli ci run full # Full CI pipeline
# Run specific tests
docker compose run --rm python-ci pytest tests/test_basic.py -v
GitHub Actions
Pull Request Validation - Automatic AI review via Claude (security + quality) and OpenRouter
This project is released under the Unlicense (public domain dedication).
For jurisdictions that do not recognize public domain: As a fallback, this project is also available under the MIT License.
Disclaimer
This repository and all associated documentation, code, research papers, and tools are provided as-is with no warranty of any kind. The maintainer makes no representations regarding the suitability, legality, or safety of any component for any purpose. Users assume all responsibility for their use of this material.
The maintainer is not responsible for any use or misuse of the contents of this repository. No advisory, consulting, support, or guidance relationship is created by the publication of this code. The maintainer expressly disclaims any obligation to respond to inquiries, feature requests, bug reports, or other communications from any party.
Portions of this repository contain dual-use security research and tooling. Publication of this material is for defensive research, education, and policy analysis purposes. The maintainer does not endorse, encourage, or facilitate any unlawful use.
T
Template Repo
AndrewAltimit·133 顆星·
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers