#002
Minimal Agent Framework (MAF)
Every AI agent framework is a maze of abstractions. You can't trace what happened, you can't replay a failed run, and when something breaks you're debugging the framework instead of your agent. You need something you can actually read.
Inside the Vault
- One runtime loop — the entire agent core fits in your head
- Four typed tools: shell.exec, fs, http.fetch, kv — with JSON schema validation
- Full JSONL traces on every run — replay any execution deterministically
Plus step-by-step usage and direct repo access.
A practical field guide to running coding agents safely: scope, isolation, verification, and review.
A practical, execution-first guide to build, run, debug, and harden your first AI agent with tools, guardrails, and production checks. If you're deciding between this tutorial-first route and the architecture-first route, use /build-ai-agent as the lane map before you branch.
I built MAF — a minimal AI agent framework in Python with one core loop, typed tool schemas, and JSONL traces. If the architecture-first route is useful but you still need the broader start-here map, use /build-ai-agent before you commit.
A deep, command-level teardown of claudeagentsdk (#005): an open-source agent workspace built around the Anthropic Agent SDK, with a FastAPI backend, a Vite/React frontend, and an optional Vercel Sandbox runner for async, reproducible runs.
A command-level, evidence-first teardown of where OpenClaw fits in an ai developer tools stack: architecture, workflows, incidents, throughput, and adoption boundaries.
I built trustmrr-cli — a TypeScript CLI giving AI agents access to verified revenue data for 4,900+ startups. Here's the architecture, the API workarounds, and why agent-native CLI tools are the missing layer.
Want the full asset, steps, and repo access?
See the Vault