# Agentics NZ Showcase A curated collection of projects built by the Agentics NZ community using AI agents. ## Categories - [Featured](#featured) — Highlighted projects, pinned to the top of the gallery - [Built with AI Agents](#built-with-ai-agents) — Applications, tools, and projects created using AI agents - [Education](#education) — Frameworks, courses, and platforms that teach how to work with AI agents - [Tools for AI Agent Development](#tools-for-ai-agent-development) — Primitives, libraries, and infrastructure that help build AI agents --- ## Featured --- ### Unsorry ![Unsorry](screenshots/unsorry-infographic.jpg) Autonomous agents proving theorems in Lean 4 — SETI@Home for mathematics, where Git is the queue and the kernel is the gate. **Description:** A distributed swarm of AI agents (Claude, Codex, Gemini) claims unproven goals from a Git-based queue and attempts formal proofs in Lean 4, with results merging only if the Lean kernel verifies every step. Trust in any single agent is irrelevant — the compiler is the sole arbiter, no `sorry` survives, and the swarm has already produced machine-verified theorems absent from mathlib. **Stack:** Lean 4, Python 3.12, Shell, Git / GitHub coordination, AISP (AI Symbolic Protocol), mathlib4 **Builder:** [Chris Barlow](https://github.com/cgbarlow) and [Perttu Isotalo](https://github.com/perttu) for [Agentics NZ](https://github.com/agenticsnz) **Links:** - 🌐 Live: [unsorry.agentics.org.nz](https://unsorry.agentics.org.nz/) - 🐙 GitHub: [agenticsnz/unsorry](https://github.com/agenticsnz/unsorry) --- ### Sovereign Engine ![Sovereign Engine](screenshots/sovereign-engine_dark.png) A self-contained local AI inference platform — a reverse proxy managing llama.cpp backends with auth, scheduling, and a management dashboard, all in a single Docker image. **Description:** Routes requests across multiple LLM backends behind an OpenAI-compatible API, with OIDC authentication, per-user API tokens (SHA-256 hashed), GPU memory–aware scheduling and reservations, automatic vision/projector detection for multimodal models, and TLS via manual certs or Let's Encrypt. Network isolation keeps backend containers unreachable from the host via dual Docker networks. **Stack:** Rust (Axum), TypeScript / React dashboard, SQLite, Docker Compose, llama.cpp **Builder:** Graham Rostron-Wood for [Agentics NZ](https://github.com/agenticsnz) **Links:** - 🌐 Live: [Sovereign Engine API Portal](https://api.agentics.org.nz/) - 🐙 GitHub: [agenticsnz/sovereign-engine](https://github.com/agenticsnz/sovereign-engine) --- ## Built with AI Agents Projects in this section are full applications, products, and prototypes built *using* AI agents as part of the development workflow. --- ### Sad Salaryman ![Sad Salaryman](screenshots/sad-salaryman.png) A gamified object scanning app where you earn "burden" as an unpaid intern. **Description:** Turn your life into a corporate simulation. Scan everyday objects to earn burden, track your progress through corporate ranks, and climb from Unpaid Intern to Contractor. **Stack:** TBD **Builder:** [Waylon Kenning](https://kenning.co.nz) **Links:** - 🌐 Live: [sadsalaryman.com](https://sadsalaryman.com) --- ### InsureScan NZ ![InsureScan NZ](screenshots/insurescan.png) AI-powered home contents valuation for insurance. **Description:** Identify, value, and catalog your home contents in minutes with AI. Snap photos of items, get instant NZ pricing with GST included, and export professional PDF inventories for insurance claims. **Stack:** TBD **Builder:** [Waylon Kenning](https://kenning.co.nz) **Links:** - 🌐 Live: [insurescan.website](https://insurescan.website) --- ### Scenia ![Scenia](screenshots/scenia.png) IT Portfolio Planning & Visualisation. **Description:** Map initiatives across time, sequence dependencies, track costs, and report on progress. A visual timeline tool for IT portfolio planning with conflict detection, critical path analysis, and budget visualisation. **Stack:** React, TypeScript, Vite, Tailwind, IndexedDB (Dexie) **Builder:** [Waylon Kenning](https://kenning.co.nz) **Links:** - 🌐 Live: [scenia.website](https://scenia.website) - 🐙 GitHub: [waylonkenning/scenia](https://github.com/waylonkenning/scenia) --- ### Iris ![Iris](screenshots/iris.png) Integrated Repository for Information & Systems — a web-based architectural modeling tool. **Description:** Create, manage, and version architectural entities, relationships, and diagrams in a repository-first system where entities are the source of truth and diagrams are projections. Supports Simple View, UML, ArchiMate, and sequence diagrams with an interactive knowledge graph, collections and sets, audit logging, and full keyboard accessibility (WCAG 2.2 AA). **Stack:** SvelteKit, Svelte 5, @xyflow/svelte, Tailwind CSS v4, FastAPI, SQLite / Supabase (PostgreSQL), Argon2id + JWT auth **Builder:** [Chris Barlow](https://github.com/cgbarlow) **Links:** - 🌐 Live: [Iris UAT](https://iris-uat.chrisbarlow.nz/) - 🐙 GitHub: [cgbarlow/iris](https://github.com/cgbarlow/iris) --- ### Matariki Stellar Navigator ![Matariki Stellar Navigator](screenshots/matariki.png) An interactive web experience celebrating Matariki, the Māori New Year. **Description:** Explore the nine stars of the Matariki cluster through an interactive navigator that pairs traditional stories and cultural significance with a guided star-finding experience. Built with respect for Māori culture and traditions. **Stack:** JavaScript, HTML, CSS, Netlify **Builder:** [Chris Barlow](https://github.com/cgbarlow) **Links:** - 🌐 Live: [matarikinav.netlify.app](https://matarikinav.netlify.app) - 🐙 GitHub: [cgbarlow/matariki](https://github.com/cgbarlow/matariki) --- ## Education Projects in this section are frameworks, methodologies, courses, and platforms that teach people how to work with AI agents — whether through structured guidance, gamified practice, or governance reference material. --- ### agentics.is ![agentics.is](screenshots/agentics-is.png) A reference framework for governed execution of AI agents. **Description:** Teaches how to build agentic systems where agents do bounded work while a deterministic orchestrator owns scope, policy, verification, audit, and approval. Covers the "agentic software factory" model — supervisor, planner, implementer, and reviewer roles — with concepts, architecture, build guidance, and governance reference material. Frames agent control as an architecture problem rather than a prompt problem, emphasising constrained, reconstructable, and reviewable execution over apparent autonomy. **Stack:** Reference framework / methodology — concepts, architecture patterns, governance and audit guidance **Builder:** [Perttu Isotalo](https://github.com/perttu) **Links:** - 🌐 Live: [agentics.is](https://agentics.is/) --- ### Guild Hall ![Guild Hall](screenshots/guild-hall.png) A quest-based engagement platform that reframes community participation around adventure rather than obligation. **Description:** Game Masters design quests with objectives, deadlines, and difficulty levels. Community members accept quests from a Bounty Board, submit evidence to complete objectives, and earn points and skill tier progression. Built on the philosophy that "obstacles are expected" on quests, whereas goals frame struggle as failure. **Stack:** Next.js 15, React 18, TypeScript, Tailwind CSS, shadcn/ui, Supabase, TanStack Query, React Hook Form, Zod, Vitest, Netlify **Builder:** [Chris Barlow](https://github.com/cgbarlow) **Links:** - 🌐 Live: [guildhall.agentics.org.nz](https://guildhall.agentics.org.nz) - 🐙 GitHub: [cgbarlow/guild-hall](https://github.com/cgbarlow/guild-hall) --- ## Tools Projects in this section are libraries, frameworks, and tooling that help creators. --- ### Campaign Mode ![Campaign Mode](screenshots/campaign-mode.jpg) Assemble a party of AI advisors with genuinely different perspectives. **Description:** A plugin system for Claude Desktop and Claude Code CLI that frames collaborative problem-solving as a quest. Six animal-based agents provide distinct viewpoints while three NPC characters (Gandalf, Guardian, Dragon) offer mentorship, progress evaluation, and adversarial testing — helping surface blind spots and stress-test ideas before they matter. Built on the Six Animals framework with Markdown-based persistence for campaign state. **Stack:** Claude Desktop / Claude Code plugin, Markdown persistence (`.campaign/quest.md`), CC-BY-SA-4.0 **Builder:** [Chris Barlow](https://github.com/cgbarlow) **Links:** - 🐙 GitHub: [cgbarlow/campaign-mode](https://github.com/cgbarlow/campaign-mode) --- ### Machine Dream ![Machine Dream](screenshots/machine-dream.jpg) A continuous AI cognition platform that lets models learn from experience and consolidate knowledge across sessions. **Description:** Uses Sudoku as a research testbed to implement a learning loop where AI plays puzzles, makes mistakes, "dreams" (consolidates experiences into patterns), and improves over time — with no external hints or deterministic fallbacks. Implements the GRASP Loop (Generate → Review → Absorb → Synthesize → Persist) with three clustering algorithms: FastCluster, DeepCluster, and LLMCluster. **Stack:** TypeScript, Node.js 20+, SQLite, OpenAI-compatible APIs (LM Studio, OpenAI, Anthropic, Ollama, OpenRouter) **Builder:** [Chris Barlow](https://github.com/cgbarlow) **Links:** - 🐙 GitHub: [cgbarlow/machine-dream_AG](https://github.com/cgbarlow/machine-dream_AG) --- ### ADR (WH(Y) Method) ![ADR](screenshots/adr-why.webp) An enhanced Architecture Decision Record format for AI-assisted development teams. **Description:** Addresses structural inconsistency and the conflation of decision rationale with implementation details in existing ADR practice. Provides standardised templates, dependency tracking between decisions, and governance metadata so humans and AI agents can capture and maintain architectural choices with clarity. Language-agnostic and designed to integrate with ADR tooling via options like `adr new --mode=enhanced`. **Stack:** Markdown specification, language-agnostic templates **Builder:** [Chris Barlow](https://github.com/cgbarlow) **Links:** - 🐙 GitHub: [cgbarlow/adr](https://github.com/cgbarlow/adr) --- ### OpenExec ![OpenExec](screenshots/openexec.png) The professional's alternative to "chat-and-hope" AI agents — a deterministic AI operating system for surgical implementation, testing, documentation, and audit compliance. **Description:** A single-binary orchestration layer that wraps AI CLI tools (Claude Code, Codex, Gemini CLI) or any OpenAI-compatible API (Kimi, Mistral, Ollama, DeepSeek, Together AI) with deterministic infrastructure: a 5-stage blueprint pipeline (gather_context → implement → lint → test → review), task classification and routing, quality gates, checkpointing, a memory system that extracts learning patterns across runs, predictive file loading, and a Claude Code–compatible skills system. Ships with an MCP server, an embedded React/Vite web UI, and a Bubble Tea TUI. Coordinator multi-agent mode lets a frontier model decompose tasks for parallel workers. **Stack:** Go (single binary), React / Vite (embedded web UI), Bubble Tea (TUI), MCP / JSON-RPC, optional BitNet for local intent classification, MIT licensed **Builder:** [Perttu Isotalo](https://github.com/perttu) **Links:** - 🌐 Live: [openexec.io](https://openexec.io/) - 🐙 GitHub: [openexec/openexec](https://github.com/openexec/openexec) --- ### MNEMOS ![MNEMOS](screenshots/mnemos.png) A containerised, contract-governed memory and retrieval service for AI-native applications. **Description:** MNEMOS provides a unified, domain-agnostic memory layer featuring TurboQuant 4-bit compression, forensic PostgreSQL audit ledgers, configurable semantic routing tiers, and a conditional Cross-Encoder reranking lane. It abstracts away brittle embeddings and database glue code into a robust REST API and Python SDK, built primarily as an appliance for autonomous agents requiring persistent, scalable cognition. **Stack:** Python, FastAPI, Qdrant, PostgreSQL, pgvector, Docker, CUDA, BAAI/bge-base **Builder:** MNEMOS Contributor **Links:** - 🐙 GitHub: [ro0TuX777/MNEMOSv2](https://github.com/ro0TuX777/MNEMOSv2) --- ### Ready for Agent ![Ready for Agent](screenshots/ready-for-agent.png) Turn ready-labelled GitHub and GitLab issues into reviewed pull requests without babysitting coding agents. **Description:** A local clanker harness that gives each issue to OpenCode, Codex, Grok Build, or Claude Code in an isolated worktree and drives implementation, review, status checks, and merge. It supports per-repository model selection, human checkpoints, and risk-gated auto-merge while reusing the developer's existing machine, tools, and agent subscriptions. **Stack:** TypeScript, Effect, Bun, React, TanStack Start, GraphQL Yoga, SQLite / Turso, Nx **Builder:** [Berend de Boer](https://github.com/berenddeboer) **Links:** - 🌐 Package: [ready-for-agent on npm](https://www.npmjs.com/package/ready-for-agent) - 🐙 GitHub: [berenddeboer/ready-for-agent](https://github.com/berenddeboer/ready-for-agent) --- ### Protocols ![Protocols](screenshots/protocols.png) Engineering protocols for Claude Code /plan mode workflows. **Description:** A curated set of non-negotiable engineering standards for Claude Code's plan mode — covering architecture decision records, specifications, test-driven development, feature branches, changelogs, releases, context management, production readiness, agent teams, dependency hygiene, README accuracy, and DRY (plus conditional Svelte frontend security). Vendor them into a project, add via git submodule/subtree, or symlink locally, then reference as `@protocols.md` in your prompts. **Stack:** Markdown protocol specifications for Claude Code `/plan` mode **Builder:** [Chris Barlow](https://github.com/cgbarlow) **Links:** - 🐙 GitHub: [cgbarlow/protocols](https://github.com/cgbarlow/protocols) --- ## Adding Your Project To add a project to the showcase: 1. Fork this repository 2. Add your entry to the appropriate section using the format below 3. Submit a pull request ### Categories - **Featured** — Curated highlights, pinned to the top of the gallery. Reserved for projects that exemplify the community; ask a maintainer before adding here. - **Built with AI Agents** — Applications, tools, and products built *using* AI agents. - **Education** — Frameworks, methodologies, courses, and platforms that teach how to work with AI agents. - **Tools for AI Agent Development** — Libraries, frameworks, and infrastructure that *help build* AI agents. ### Entry Format ```markdown ### Your Project Name ![Your Project Name](screenshots/your-project.png) One-paragraph description of what it does. **Description:** A longer description if needed. **Stack:** Tech stack (e.g. React, Python, Claude API) **Builder:** Your name or company **Links:** - 🌐 Live: https://... - 🐙 GitHub: https://github.com/... ``` ### Screenshot Guidelines - Max dimensions: 1200px wide - Format: PNG or JPG - File name: `{project-name}.png` in the `/screenshots` folder - Add the image reference right after your project title