Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
OpenClaw: Autonomous Treasury Agent
See how to build an AI-operable treasury agent using OpenClaw and MCP. Learn to design safe financial AI, integrate multisig accounts, and implement autonomous monitoring.
In this demo, I’ll show how I transformed a stablecoin-based treasury system into an AI-operable financial agent using OpenClaw and MCP (Model Context Protocol).
Instead of dashboards and manual workflows, an OpenClaw agent:
Checks USDC balances
Analyzes transaction history
Generates cash flow reports
Drafts multisig payment proposals
Monitors KYC status
Runs heartbeat-based treasury oversight
I’ll walk through:
How I designed an MCP skill for financial operations
How OpenClaw loads and executes structured tools
How I enforced guardrails so AI can draft payments but never execute them
How multisig Safe accounts integrate with AI-generated proposals
How autonomous monitoring runs via heartbeat routines
- OpenClaw RuntimeA modern C++17 reimplementation of the 1997 Monolith Productions engine designed to run Captain Claw natively on Linux, Windows, and macOS.OpenClaw replaces the aging DirectX 5 codebase with a portable SDL2-based runtime that loads original .WAP and .PID game files without modification. It eliminates legacy hardware bottlenecks (supporting 4K resolutions and 144Hz displays) while maintaining the precise physics of the original side-scroller. Developers can leverage the modular C++ architecture to extend gameplay features or port the title to new platforms while preserving the core 1990s experience.
- 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 .
- NextNext.js is the full-stack React framework: it delivers high-performance web applications via hybrid rendering and powerful, Rust-based tooling.This is the React Framework for production: Next.js enables you to build full-stack web applications with zero configuration and maximum efficiency. It supports a hybrid rendering approach (Server-Side Rendering, Static Site Generation, and Incremental Static Regeneration) for optimal speed and SEO performance. Key features include React Server Components, Server Actions for running server code directly, and the App Router for advanced routing and nested layouts. Developed by Vercel, it leverages Rust-based tools like Turbopack and the Speedy Web Compiler for the fastest possible builds and a superior developer experience.
- ERC-4337ERC-4337 enables account abstraction on Ethereum without consensus-layer changes, turning wallets into programmable smart contracts.This standard introduces a higher-level mempool to replace traditional EOAs (Externally Owned Accounts) with smart accounts. By routing UserOperations through a decentralized Bundler network, users gain access to critical features like gasless transactions (Paymasters), multi-signature security, and social recovery. It eliminates the need for users to hold ETH for transaction fees or manage complex seed phrases. Major players like Safe and Polygon are already leveraging this infrastructure to bridge the UX gap between Web2 and Web3 (specifically through automated recurring payments and session keys).
- PostgreSQLPostgreSQL (Postgres): The world's most advanced, open-source object-relational database (ORDBMS), built for reliability and extensibility.PostgreSQL is the premier open-source ORDBMS, proven over 35+ years of active development. It adheres strictly to ACID properties (Atomicity, Consistency, Isolation, Durability), ensuring data integrity for mission-critical workloads. Key features include robust SQL compliance, Multi-Version Concurrency Control (MVCC), and superior extensibility (e.g., custom data types, functions in multiple languages). Advanced capabilities like native JSON/JSONB support and the PostGIS extension (geospatial data) make it a powerful, flexible choice for complex enterprise applications.
Related projects
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…
Collaborator: Lobster-powered critical thinkig partner
New York City
Discover open-source tools that transform an OpenClaw agent into a thinking partner. Explore Seedvault for knowledge syncing, Reflection…
Building a Digital Supermax: Architecting Air-Gapped Runtimes for Untrusted Agents
DC
Learn how to build secure, air-gapped runtimes for AI agents like OpenClaw. This talk explores network infrastructure and…
What's behind OpenClaw - The innards of my AI assistant!
Toronto
Explore the inner workings of a persistent AI assistant. This talk details its architecture, memory, and core capabilities…
What If Humans and Agents Had a Portable Cryptographically-Chained Ledger (Single source of truth)
New York City
Explore a cryptographically-chained ledger for product development context, integrating Claude Code, Cursor, and voice agents for efficient team…
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…