Watch a Governed Multi-Agent System Block, Verify, and Replay AI Code — Live | Montreal .
Cities (232) ▾

Members-Only

Recent Talks & Demos are for members only

Exclusive feed

You must be an AI Tinkerers active member to view these talks and demos.

Sign in View FAQ
June 17, 2026 · Montreal

aming-claw: Governed Multi-Agent Systems

See a live demo of aming-claw, a system that lets AI agents write code under enforced contracts, including file fences and observer reviews, for safe parallel development.

aming-claw MCP Python git worktrees Codex
Overview

aming-claw — a system that lets AI agents write your code without you having to trust them. AI agents do all the implementation, but under enforced contracts: each task carries a route context (allowed/blocked actions, a file fence, required evidence), a gate physically refuses any write outside it, a separate observer reviews instead of implementing, and every step lands in a replayable timeline.

This is a live demo, not slides. I’ll show the real running system: a worker attempting an out-of-fence write and the gate returning a hard 422; a task refused at close because it has no timeline evidence; multiple commit-bound workers running in parallel from a single prompt; and the timeline replayed afterward. To make it concrete, I’m running it on a real product I’m currently building — an AI video-generation tool (auto-script + voice from on-screen content) — so you watch one prompt fan out to parallel AI workers and land an actual commit of a real codebase.

Links
Tech stack
  • aming-claw
    A secure, lightweight alternative to OpenClaw designed to run autonomous AI agents inside isolated containers.
    NanoClaw is an open-source, MIT-licensed AI agent harness designed to run autonomous workflows securely inside isolated containers. Built as a lightweight alternative to OpenClaw, it prevents sensitive API keys and local data from directly touching external models, solving the critical security and privacy concerns of running local AI agents. It connects seamlessly to daily communication tools like WhatsApp and Telegram, allowing users to trigger multi-step tasks, manage local files, and build a dynamic personal knowledge base from any device.
  • MCP
    MCP is the open-source standard for securely connecting AI agents (like LLMs) to external tools, data, and enterprise workflows.
    The Model Context Protocol (MCP) functions as a standardized integration layer: think of it as a USB-C port for AI applications. Developed and open-sourced by Anthropic, this protocol allows large language models (LLMs) to access real-time context and execute actions via external tools like GitHub, Jira, or proprietary databases . It uses a simple JSON-RPC interface to define tools, schemas, and endpoints, which enables AI agents to perform complex, state-changing tasks—such as creating a GitHub issue or running a test script—rather than just generating text . MCP is essential for building agentic AI systems that can autonomously pursue goals and operate within defined safety and permission boundaries .
  • Python
    Python: The high-level, general-purpose language built for readability, powering everything from web backends to advanced machine learning models.
    Python is the high-level, general-purpose language prioritizing clear, readable syntax (via significant indentation), ensuring rapid development for any team . Its ecosystem is massive: use it for robust web development with frameworks like Django and Flask, or leverage its power in data science with libraries such as Pandas and NumPy . The Python Package Index (PyPI) provides thousands of community-contributed modules, offering immediate solutions for tasks from network programming to GUI creation . The language is actively maintained by the Python Software Foundation (PSF), with the stable release currently at Python 3.14.0 (as of November 2025) .
  • git worktrees
    Manage multiple linked working trees from a single repository to handle concurrent tasks without switching branches.
    Git worktrees eliminate the overhead of stashing or cloning duplicate repos when context switching. By running 'git worktree add ../hotfix master', you check out a specific branch into a separate directory while sharing the same .git history. This setup allows you to run long-duration test suites in one folder while actively refactoring code in another. It is the professional standard for managing urgent patches (hotfixes) and complex code reviews simultaneously without disrupting your primary development environment.
  • Codex
    Codex is OpenAI's autonomous AI software engineering agent: it executes full development tasks in a sandboxed cloud environment.
    Codex is the advanced, cloud-based software engineering agent from OpenAI, built on a specialized model like `codex-1` (a fine-tuned version of `o3`). It operates on an asynchronous delegation model, allowing developers to assign complete tasks—not just receive suggestions—via the ChatGPT interface. The agent works independently in a secure, isolated cloud container provisioned with the user's GitHub repository and environment. It reads code, writes new features, fixes bugs, runs tests, and drafts Pull Requests (PRs) for review, significantly accelerating the development lifecycle. Access is provided through ChatGPT Plus, Pro, and Enterprise plans.
Events Gallery FAQ Sponsor