Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Collaborator: OpenClaw thinking partner
Discover open-source tools that transform an OpenClaw agent into a thinking partner. Explore Seedvault for knowledge syncing, Reflection pipelines for goal digestion, and Collab MCP for portable agent identity.
Collaborator is a set of open-source tools that turn an OpenClaw agent into a thinking partner. Code walkthrough and live demo of three building blocks: (1) Seedvault — markdown sync between humans and agents, giving the agent a living knowledge base. (2) Reflection pipelines — chained sub-agents that run during OpenClaw’s heartbeat, digesting notes into goals, blockers, and recommendations. (3) Collab MCP — a TypeScript server that packages the agent’s persona and accumulated knowledge into a portable identity, invokable inside Claude Code or Codex.
Collaborator facilitates interactive AI cognitive augmentation for human decision support.
- OpenClawOpenClaw is the viral, open-source, autonomous AI agent: a self-hosted 'digital employee' that executes real-world tasks across your local machine and messaging platforms 24/7.This is the next-generation autonomous AI agent, built by Peter Steinberger (founder of PSPDFKit). OpenClaw functions as a proactive, self-hosted assistant, running as a long-running Node.js service on your own hardware (e.g., a Mac Mini or VPS) for about $3–$5 per month. It integrates directly with chat apps (WhatsApp, Telegram, Discord) to receive instructions and report completions. The agent utilizes over 100 AgentSkills to execute complex, real-world workflows: clearing your inbox, writing code, managing documents, and checking you in for flights. The open-source project’s velocity is undeniable, having surpassed 100,000 GitHub stars quickly and reportedly driving a surge in Mac Mini sales.
- Claude CodeAnthropic's agentic coding tool: Unleash Claude's raw power directly in your terminal or IDE to turn complex, hours-long workflows into a single command.Claude Code is Anthropic’s powerful agentic coding assistant, designed for high-velocity development. It operates natively within your terminal, IDE (VS Code, JetBrains), or via a web interface, allowing you to delegate complex tasks like feature building, bug fixing, and codebase navigation. The agent plans, edits files, executes commands, and creates commits, maintaining awareness of your entire project structure. Internally, Anthropic engineers using Claude Code reported a 67% increase in productivity, demonstrating its capacity to deliver significant gains for Pro and Max plan users.
- CodexCodex 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.
- TypeScriptTypeScript is an open-source superset of JavaScript: it adds static typing and compiles to clean, standards-based JavaScript.TypeScript is a high-level, open-source language developed by Microsoft: it acts as a superset of JavaScript, adding a powerful static type system. This system enables compile-time type checking, catching errors before runtime (a critical benefit for large-scale applications). The TypeScript Compiler (TSC) reliably transpiles all code into clean, standards-based JavaScript (ES3 or newer), ensuring compatibility across any browser or host environment (Node.js, React.js, etc.).
- BunBun is the fast, all-in-one JavaScript runtime and toolkit: it replaces Node.js, npm, and multiple development tools with a single, cohesive executable.Bun delivers a high-performance JavaScript runtime, built from scratch in Zig and powered by Apple's JavaScriptCore engine (not V8). It functions as a drop-in replacement for Node.js, but unifies the entire development workflow: the runtime, package manager (e.g., `bun install`), bundler (`bun build`), and test runner (`bun test`) are all integrated. This architecture dramatically reduces startup times and memory usage, offering significant speed gains, especially in tasks like package installation (up to 30x faster than npm) and server-side rendering.
- MCPMCP 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 .
- bun + honoA high-performance TypeScript stack combining Bun's native runtime speed with Hono's ultra-lightweight middleware architecture.This pairing eliminates legacy overhead by leveraging Bun's built-in SQLite driver and native fetch implementation alongside Hono's sub-millisecond routing. Developers get a zero-config environment that handles over 100,000 requests per second on standard hardware. It is the optimal choice for building edge-ready APIs where cold starts must stay under 10ms and the total binary footprint remains minimal.
- SkillsThe essential platform for building in-demand AI and technical capabilities: access free courses, skill badges, and industry-recognized Google Cloud certifications.Skills (Google) delivers targeted, high-impact technical training to close the global skills gap. The platform offers extensive no-cost options for all learning levels, including hundreds of courses focused on AI and technical fundamentals. Users earn shareable digital credentials: complete a certificate learning path for a full certification, or finish a series of courses to secure a Skill Badge, proving practical, technical expertise. This is the direct path for individuals and Google Cloud partners to validate knowledge and advance their careers with industry-recognized credentials.
Related projects
OpenClaw Trace - Recursively Self-improving OpenClaw
New York City
This talk showcases a system for recursively improving OpenClaw by identifying and fixing real-world user issues. It uses…
ROSClaw: Agentic Robots with OpenClaw - "what happens when you give a robot a lobster brain?"
New York City
See ROSClaw, a framework integrating OpenClaw with ROS2 and ESP32 devices. Explore installation, running ROS2 packages, and observe…
FuzzyClaw
Cologne
Learn how FuzzyClaw orchestrates multi-agent work from markdown briefings, dispatching specialist agents and routing outputs for review, emphasizing…
I gave my reachy mini a brain
New York City
See the Reachy Mini robot come to life with an OpenClaw brain. This mainstage presentation explores a new…
Self-Improving Agents with Honcho
New York City
Learn to build stateful, self-improving agents. Honcho provides a memory agent to prevent context rot, enabling your OpenClaw…
Securing Agent Swarms: Detection & Enforcement at the Tool Boundary (OpenClaw + Beyond)
New York City
Learn to secure agent swarms by enforcing policies on filesystem access, command execution, and network egress. This talk…