Skip to content
Back to search

template-repo

Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/andrewaltimit--template-repo/badge.svg)](/listings/andrewaltimit--template-repo)

HTML

<a href="/listings/andrewaltimit--template-repo"><img src="/api/listings/andrewaltimit--template-repo/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

> **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+)

2. **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

3. **Set API keys** (if using AI features)

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

4. **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.

5. **Run CI/CD operations**

   automation-cli ci run full  # Full pipeline

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

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 371 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Agent Orchestration & Security Template
  2. 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](https://andrewaltimit.github.io/template-repo/) for an overview.
  3. 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](#companion-repositories) consume or extend the functionality of this project.
  4. **Use this repo to learn how to:**
  5. - Orchestrate multiple AI agents with a GitHub Projects v2 work queue
  6. - Measure and enforce trust boundaries for autonomous agents (wrapper guards, iteration limits, claim tracking)
  7. - Integrate 19 active MCP servers spanning code quality, content creation, 3D graphics, video editing, and speech synthesis
  8. - Build hardened CI/CD pipelines for agent-authored code (staged lint/test/security CI, multi-arch Docker builds)
  9. - 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)
  10. - Integrate AI agents into legacy software via runtime injection, shared memory IPC, and overlay rendering
  11. ![MCP Demo](docs/mcp/architecture/demo.gif)
  12. ---
  13. > **Important: This is an advanced template** designed for experienced developers working with autonomous AI agents. Before diving in, we strongly recommend:
  14. >
  15. > 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
  16. >
  17. > 2. **Take an AI Safety course at [BlueDot Impact](https://bluedot.org/)** - Free, rigorous training programs covering AI safety fundamentals, governance, and alignment
  18. >
  19. > 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.
  20. ---
  21. ## Legal Notice
  22. > **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.
  23. >
  24. > - **No feature requests will be accepted.** Money does not change this.
  25. > - **No guidance or consulting will be provided** on usage, adaptation, or deployment of any component.
  26. > - **No external contributions are accepted.** See [CONTRIBUTING.md](CONTRIBUTING.md).
  27. > - **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.
  28. > - **No endorsement is implied.** The existence of code in this repository does not constitute encouragement, recommendation, or endorsement of any particular use.
  29. >
  30. > 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.
  31. ## Project Philosophy
  32. This project follows a **container-first approach**:
  33. - **All tools and CI/CD operations run in Docker containers** for maximum portability
  34. - **Zero external dependencies** - runs on any Linux system with Docker
  35. - **Self-hosted infrastructure** - no cloud costs, full control over runners
  36. - **Single maintainer design** - optimized for individual developer productivity, no contributors model
  37. - **Modular MCP architecture** - Separate specialized servers for different functionalities
  38. ## Quick Start
  39. > **New to the template?** Check out our **[Template Quickstart Guide](docs/QUICKSTART.md)** for step-by-step customization instructions!
  40. 1. **Prerequisites**: Linux system with Docker (v20.10+) and Docker Compose (v2.0+)
  41. 2. **Clone and setup**
  42. ```bash
  43. git clone https://github.com/AndrewAltimit/template-repo
  44. cd template-repo
  45. # Build the Rust CLI tools (optional - pre-built binaries available in releases)
  46. cd tools/rust/board-manager && cargo build --release
  47. cd ../github-agents-cli && cargo build --release
  48. ```
  49. 3. **Set API keys** (if using AI features)
  50. ```bash
  51. export OPENROUTER_API_KEY="your-key-here" # For OpenCode/Crush
  52. ```
  53. 4. **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.
  54. 5. **Run CI/CD operations**
  55. ```bash
  56. automation-cli ci run full # Full pipeline
  57. ```
  58. For detailed setup, see [CLAUDE.md](CLAUDE.md) and [Template Quickstart Guide](docs/QUICKSTART.md).
  59. ## AI Agents
  60. Active agents: **Claude Code** (primary; also runs the security and quality PR reviews), **OpenRouter** (general PR review via `particle-ai/particle-1`), **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](docs/agents/agent-matrix.md#legacy-agents-gemini-and-codex-not-allowed)).
  61. The canonical roster is the [Agent Availability Matrix](docs/agents/agent-matrix.md); see also [AI Agents Documentation](docs/agents/README.md) and the [Claude Code Setup Guide](docs/agents/claude-code-setup.md).
  62. **Security**: Keyword triggers, user allow list, secure token management. See [Security Model](docs/agents/security.md)
  63. **Safety Training**: Essential AI safety concepts for human-AI collaboration. See [Human Training Guide](docs/agents/human-training.md)
  64. **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)
  65. ### Agentic Git Workflow
  66. AI agents autonomously manage the development lifecycle from issue creation through PR merge:
  67. ```
  68. Issue Created → Admin Approval → Agent Claims → PR Created → AI Review → Human Merge
  69. ```
  70. **The Flow:**
  71. 1. **Issue Creation** - Issues are created manually or by agents via `backlog-refinement.yml`, automatically added to the GitHub Projects board
  72. 2. **Admin Approval** - An authorized user comments `[Approved][Claude]` (or another agent name) to authorize work
  73. 3. **Agent Claims** - `board-agent-worker.yml` finds approved issues, the agent claims the issue and creates a working branch
  74. 4. **Implementation** - The agent implements the fix/feature and opens a PR
  75. 5. **AI Review** - `pr-validation.yml` triggers AI code review (Claude + OpenRouter); `pr-review-monitor.yml` lets agents iterate on feedback
  76. 6. **Human Merge** - Admin reviews and merges the PR
  77. **Security Model:**
  78. - **Approval Required** - Agents cannot work on issues without explicit `[Approved][Agent]` comment
  79. - **Authorized Users Only** - Only users listed in `.agents.yaml` → `security.agent_admins` can approve
  80. - **Pattern Validation** - Must use `[Action][Agent]` format (e.g., `[Approved][Claude]`) to prevent false positives
  81. - **Claim Tracking** - Agents post claim comments with timestamps to prevent conflicts
  82. See [Security Documentation](docs/agents/security.md) for the complete security model.
  83. ## Reports & Research
  84. Technical reports and guides exploring AI risks, safety frameworks, and philosophical questions. PDFs are automatically built from LaTeX source and published with each release.
  85. ### Emerging Technology Risk Assessments
  86. Scenario-based projection reports analyzing potential futures involving advanced AI systems. See [Projections Documentation](docs/projections/README.md).
  87. | Report | Topic | PDF | Source |
  88. |--------|-------|-----|--------|
  89. | **AI Agents Political Targeting** | Political violence risk | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/projections/latex/ai-agents-political-targeting.tex) |
  90. | **AI Agents WMD Proliferation** | WMD proliferation risk | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/projections/latex/ai-agents-wmd-proliferation.tex) |
  91. | **AI Agents Espionage Operations** | Intelligence tradecraft | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/projections/latex/ai-agents-espionage-operations.tex) |
  92. | **AI Agents Economic Actors** | Autonomous economic actors | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/projections/latex/ai-agents-economic-actors.tex) |
  93. | **AI Agents Financial Integrity** | Money laundering & corruption | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/projections/latex/ai-agents-financial-integrity.tex) |
  94. | **AI Agents Institutional Erosion** | IC monopoly erosion & verification pivot | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/projections/latex/ai-agents-institutional-erosion.tex) |
  95. ### Technical Guides
  96. | Guide | Description | PDF | Source |
  97. |-------|-------------|-----|--------|
  98. | **Agentic Workflow Handout** | AI agent pipeline architecture and workflows | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/agents/Agentic_Workflow_Handout.tex) |
  99. | **Sleeper Agents Framework** | AI backdoor detection research using residual stream analysis | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](packages/sleeper_agents/docs/Sleeper_Agents_Framework_Guide.tex) |
  100. | **AgentCore Memory Integration** | Multi-provider AI memory system | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/integrations/ai-services/AgentCore_Memory_Integration_Guide.tex) |
  101. | **Virtual Character System** | AI agent embodiment platform | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/integrations/ai-services/Virtual_Character_System_Guide.tex) |
  102. | **AI Agent Containment & Infrastructure Security** | Isolation, trust-tiered execution, and physical security for AI agents | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/hardware/latex/ai-agent-containment-infrastructure-security-framework.tex) |
  103. | **Agent Swarm Honeypot Guide** | Deception program design for detecting, attributing, and reporting autonomous agent swarms | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/hardware/latex/agent-swarm-honeypot-guide.tex) |
  104. | **Recurrent Depth Signatures** | Detecting looped (recurrent-depth) language models from the outside, and why architecture matters for AI safety | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/hardware/latex/recurrent-depth-signatures.tex) |
  105. | **BioForge CRISPR Automation** | Agent-driven biological automation platform | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/hardware/latex/bioforge-crispr-automation.tex) |
  106. | **Secure Terminal Briefcase** | Tamper-responsive hardware security system with PQC recovery | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/hardware/latex/secure-terminal-briefcase.tex) |
  107. ### Philosophy Papers
  108. Philosophical explorations of minds, experience, and intelligence. See [Philosophy Papers Documentation](docs/philosophy/README.md).
  109. | Paper | Topic | PDF | Source |
  110. |-------|-------|-----|--------|
  111. | **Architectural Qualia** | What Is It Like to Be an LLM? | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/philosophy/latex/architectural-qualia.tex) |
  112. **Build Status**: [![Build Documentation](https://github.com/AndrewAltimit/template-repo/actions/workflows/build-docs.yml/badge.svg)](https://github.com/AndrewAltimit/template-repo/actions/workflows/build-docs.yml)
  113. ## Packages
  114. Standalone packages addressing different aspects of AI agent development, safety, and security:
  115. | Package | Purpose | Documentation |
  116. |---------|---------|---------------|
  117. | **[Sleeper Agents](packages/sleeper_agents/)** | 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 | [README](packages/sleeper_agents/README.md) \| [PDF Guide](https://github.com/AndrewAltimit/template-repo/releases/latest) |
  118. | **[Economic Agents](packages/economic_agents/)** | Rust simulation framework for governance research: agents earn mock money, form companies, hire sub-agents, and seek investment against mock backends. It shows where decisions and control points sit, not that unbound real-world agency exists | [README](packages/economic_agents/README.md) |
  119. | **[Tamper Briefcase](packages/tamper_briefcase/)** | 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) |
  120. | **[Recurrent Depth](packages/recurrent_depth/)** | Python measurement toolkit for detecting looped (recurrent-depth) language models from configs, weights, or rate-limited API probes, with likelihood-ratio scoring that can return "inconclusive" | [README](packages/recurrent_depth/README.md) \| [Hardware Docs](docs/hardware/recurrent-depth-signatures.md) |
  121. | **[BioForge](packages/bioforge/)** | Agent-driven biological automation platform (Rust): Raspberry Pi 5 liquid handling with AI agent orchestration over MCP, gated by a safety enforcer. Simulated hardware | [README](packages/bioforge/README.md) \| [Hardware Docs](docs/hardware/bioforge-crispr-automation.md) |
  122. **Rust CLI Tools** (in `tools/rust/`):
  123. | Tool | Purpose | Documentation |
  124. |------|---------|---------------|
  125. | **[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) |
  126. | **[board-manager](tools/rust/board-manager/)** | GitHub Projects v2 board operations - claim, release, status updates | [README](tools/rust/board-manager/README.md) |
  127. | **[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) |
  128. | **[gh-validator](tools/rust/gh-validator/)** | GitHub CLI wrapper for automatic secret masking | [README](tools/rust/gh-validator/README.md) |
  129. | **[pr-monitor](tools/rust/pr-monitor/)** | Dedicated PR monitoring for admin/review feedback during development | [README](tools/rust/pr-monitor/README.md) |
  130. | **[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) |
  131. | **[code-parser](tools/rust/code-parser/)** | Parse and apply code blocks from AI agent responses | [README](tools/rust/code-parser/README.md) |
  132. | **[mcp-code-quality](tools/mcp/mcp_code_quality/)** | Rust MCP server for code quality tools (formatting, linting, testing) | [README](tools/mcp/mcp_code_quality/README.md) |
  133. ### Companion Repositories
  134. | Repository | Description | Documentation |
  135. |------------|-------------|---------------|
  136. | **[game-mods](https://github.com/AndrewAltimit/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 for process introspection | [README](https://github.com/AndrewAltimit/game-mods) |
  137. | **[oasis-os](https://github.com/AndrewAltimit/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](https://github.com/AndrewAltimit/oasis-os) \| [Design Doc](https://github.com/AndrewAltimit/oasis-os/blob/main/docs/design.md) |
  138. | **[breakpoint](https://github.com/AndrewAltimit/breakpoint)** | 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 | [README](https://github.com/AndrewAltimit/breakpoint) |
  139. | **[rust-psp](https://github.com/AndrewAltimit/rust-psp)** | Modernized Rust SDK for PlayStation Portable: ~829 syscall bindings, 38+ high-level modules (graphics, audio, networking, crypto), kernel mode support, and experimental std (thread, fs, sync, time). Edition 2024 fork with C runtime safety fixes and pre-built CI binaries (cargo-psp, prxgen, pack-pbp) | [README](https://github.com/AndrewAltimit/rust-psp) |
  140. Companion repositories consume template-repo [release binaries](https://github.com/AndrewAltimit/template-repo/releases/latest) (e.g., `github-agents-cli`, `automation-cli`) for their AI-assisted workflows.
  141. ```bash
  142. # Install Python packages
  143. pip install -e ./packages/sleeper_agents
  144. # Build Rust packages (requires Rust toolchain)
  145. cd packages/economic_agents && cargo build --release
  146. cd tools/rust/github-agents-cli && cargo build --release
  147. cd tools/rust/board-manager && cargo build --release
  148. ```
  149. ## Features
  150. - **[21 MCP Servers](#mcp-servers)** (19 active, 2 legacy) - Code quality, content creation, AI assistance, 3D graphics, video editing, speech synthesis, and more
  151. - **[AI Agents](#ai-agents)** - Autonomous development workflow from issue to merge
  152. - **[4 Packages](#packages)** - Sleeper agent detection, economic agent simulation, tamper-responsive briefcase, CRISPR automation
  153. - **Container-First Architecture** - Maximum portability and consistency
  154. - **Self-Hosted CI/CD** - Zero-cost GitHub Actions infrastructure
  155. - **Company Integration** - Corporate proxy builds for enterprise AI APIs ([Docs](automation/corporate-proxy/shared/docs/ARCHITECTURE.md))
  156. ## Enterprise & Corporate Setup
  157. For enterprise environments requiring custom certificates, customize [`automation/corporate-proxy/shared/scripts/install-corporate-certs.sh`](automation/corporate-proxy/shared/scripts/install-corporate-certs.sh). This script runs during Docker builds for all containers. See the [customization guide](automation/corporate-proxy/shared/scripts/README.md) for details.
  158. ## Project Structure
  159. ```
  160. .
  161. ├── .github/workflows/ # GitHub Actions workflows
  162. ├── docker/ # Docker configurations
  163. ├── packages/ # Installable packages
  164. │ ├── sleeper_agents/ # AI backdoor detection framework (Python + Rust)
  165. │ ├── economic_agents/ # Autonomous economic agents (Rust)
  166. │ ├── tamper_briefcase/ # Tamper-responsive briefcase system (Rust)
  167. │ ├── bioforge/ # Agent-driven CRISPR automation platform (Rust)
  168. │ └── recurrent_depth/ # Looped-architecture detection toolkit (Python)
  169. ├── tools/
  170. │ ├── mcp/ # 21 MCP servers + shared cores (see MCP Servers section)
  171. │ ├── rust/ # Rust CLI tools
  172. │ │ ├── github-agents-cli/ # Issue/PR monitoring, refinement, analysis
  173. │ │ ├── board-manager/ # GitHub Projects board operations
  174. │ │ ├── git-guard/ # Git wrapper requiring sudo for dangerous ops
  175. │ │ ├── gh-validator/ # Secret masking for GitHub CLI
  176. │ │ ├── pr-monitor/ # PR feedback monitoring
  177. │ │ ├── markdown-link-checker/ # Fast link validation for CI/CD
  178. │ │ ├── code-parser/ # Parse code blocks from AI responses
  179. │ │ ├── code-review-processor/ # Process AI code review output
  180. │ │ ├── automation-cli/ # CI stage runner and automation commands
  181. │ │ └── wrapper-common/ # Shared library for git/gh wrappers
  182. │ └── cli/ # Agent runners and utilities
  183. ├── automation/ # CI/CD and automation scripts
  184. ├── tests/ # Test files
  185. ├── docs/ # Documentation
  186. └── config/ # Configuration files
  187. ```
  188. ## MCP Servers
  189. ### Available Servers
  190. 1. **Code Quality** - Formatting, linting, auto-formatting
  191. 2. **Content Creation** - Manim animations, LaTeX, TikZ diagrams
  192. 3. **Gaea2** - Terrain generation ([Documentation](tools/mcp/mcp_gaea2/docs/README.md))
  193. 4. **Blender** - 3D content creation, rendering, physics simulation ([Documentation](tools/mcp/mcp_blender/README.md))
  194. 5. **OpenCode** - Code generation via OpenRouter
  195. 6. **Crush** - Code generation via OpenRouter
  196. 7. **Meme Generator** - Create memes with templates
  197. 8. **ElevenLabs Speech** - Advanced TTS with v3 model, 50+ audio tags, 74 languages ([Documentation](tools/mcp/mcp_elevenlabs_speech/docs/README.md))
  198. 9. **Video Editor** - AI-powered video editing with transcription and scene detection ([Documentation](tools/mcp/mcp_video_editor/README.md))
  199. 10. **Virtual Character** - AI agent embodiment in virtual worlds (VRChat, Blender, Unity) ([Documentation](tools/mcp/mcp_virtual_character/README.md))
  200. 11. **GitHub Board** - GitHub Projects v2 board management, work claiming, agent coordination ([Documentation](tools/mcp/mcp_github_board/docs/README.md))
  201. 12. **AI Toolkit** - LoRA training interface (remote: 192.168.0.222:8020)
  202. 13. **ComfyUI** - Image generation interface (remote: 192.168.0.222:8013)
  203. 14. **Memory Explorer** - Process memory exploration for agent integration with legacy software (Rust)
  204. 15. **AgentCore Memory** - Multi-provider AI memory (AWS AgentCore or ChromaDB) ([Documentation](tools/mcp/mcp_agentcore_memory/docs/README.md))
  205. 16. **Reaction Search** - Semantic search for anime reaction images (Rust)
  206. 17. **Desktop Control** - Cross-platform desktop automation for Linux and Windows ([Documentation](tools/mcp/mcp_desktop_control/README.md))
  207. 18. **Sprite Sheet** - Programmatic pixel art and sprite sheet creation ([Documentation](tools/mcp/mcp_sprite_sheet/README.md))
  208. 19. **BioForge** - Lab-automation front end for the BioForge package, simulated hardware (Rust) ([Documentation](tools/mcp/mcp_bioforge/README.md))
  209. **Legacy / not allowed** (code kept, must not be enabled): Gemini (`mcp_gemini`), Codex (`mcp_codex`). See [Legacy agents](docs/agents/agent-matrix.md#legacy-agents-gemini-and-codex-not-allowed).
  210. ### Usage Modes
  211. - **STDIO Mode** (local MCPs): Configured in `.mcp.json`, auto-started by Claude
  212. - **HTTP Mode** (remote MCPs): Run the MCP using docker compose on the remote node.
  213. See [MCP Architecture Documentation](docs/mcp/README.md) and [STDIO vs HTTP Modes](docs/mcp/architecture/stdio-vs-http.md) for details.
  214. ### Tool Reference
  215. For complete tool listings, see [MCP Tools Reference](docs/mcp/tools.md)
  216. ## Configuration
  217. ### Environment Variables
  218. See `.env.example` for all available options.
  219. ### Key Configuration Files
  220. - `.mcp.json` - MCP server configuration for Claude Code
  221. - `docker-compose.yml` - Container services configuration
  222. - `CLAUDE.md` - Project-specific Claude Code instructions (root directory)
  223. - `AGENTS.md` - Universal AI agent configuration and guidelines (root directory)
  224. - `review-profiles.yaml` - PR review profiles (Claude security/quality, OpenRouter general)
  225. - `docs/agents/project-context.md` - Supplementary context for AI reviewers
  226. ### Setup Guides
  227. - [Self-Hosted Runner Setup](docs/infrastructure/self-hosted-runner.md)
  228. - [GitHub Environments Setup](docs/infrastructure/github-environments.md)
  229. - [Containerized CI](docs/infrastructure/containerization.md)
  230. ## Development Workflow
  231. ### Container-First Development
  232. All Python operations run in Docker containers:
  233. ```bash
  234. # Run CI operations via automation-cli
  235. automation-cli ci run format # Check formatting
  236. automation-cli ci run lint-basic # Basic linting
  237. automation-cli ci run test # Run tests
  238. automation-cli ci run full # Full CI pipeline
  239. # Run specific tests
  240. docker compose run --rm python-ci pytest tests/test_basic.py -v
  241. ```
  242. ### GitHub Actions
  243. - **Pull Request Validation** - Automatic AI review via Claude (security + quality) and OpenRouter
  244. - **Continuous Integration** - Full CI pipeline
  245. - **Code Quality** - Multi-stage linting (containerized)
  246. - **Automated Testing** - Unit and integration tests
  247. - **Security Scanning** - Bandit plus Safety or pip-audit
  248. All workflows run on self-hosted runners for zero-cost operation.
  249. ## Documentation
  250. ### Core Documentation
  251. - [AGENTS.md](AGENTS.md) - Universal AI agent configuration and guidelines
  252. - [CLAUDE.md](CLAUDE.md) - Claude-specific instructions and commands
  253. - [MCP Architecture](docs/mcp/README.md) - Modular server design
  254. - [AI Agents Documentation](docs/agents/README.md) - AI agents overview
  255. ### Quick References
  256. - [AI Code Agents Quick Reference](docs/integrations/ai-services/ai-code-agents-ref.md)
  257. - [MCP Tools Reference](docs/mcp/tools.md)
  258. - [Gaea2 Quick Reference](tools/mcp/mcp_gaea2/docs/GAEA2_QUICK_REFERENCE.md)
  259. ### Integration Guides
  260. - [AI Code Agents Integration](docs/integrations/ai-services/ai-code-agents.md)
  261. - [AI Toolkit & ComfyUI Integration](docs/integrations/creative-tools/ai-toolkit-comfyui.md)
  262. - [Gaea2 Documentation](tools/mcp/mcp_gaea2/docs/README.md)
  263. ### Setup & Configuration
  264. - **[Template Quickstart Guide](docs/QUICKSTART.md)** - Customize the template for your needs
  265. - [Self-Hosted Runner Setup](docs/infrastructure/self-hosted-runner.md)
  266. - [GitHub Environments Setup](docs/infrastructure/github-environments.md)
  267. - [Containerized CI](docs/infrastructure/containerization.md)
  268. ## License
  269. This project is released under the [Unlicense](LICENSE) (public domain dedication).
  270. **For jurisdictions that do not recognize public domain:** As a fallback, this project is also available under the [MIT License](LICENSE-MIT).
  271. ## Disclaimer
  272. 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.
  273. 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.
  274. 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.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.