Experiment: OpenClaw
OpenClaw is not my project. It is a widely adopted open-source agent framework, built by others, that provides the base layer for autonomous agents: tool use, memory and multi-agent collaboration. I explored it to understand how a general-purpose agent runtime is put together, and why enterprises hesitate to give such agents access to real data and tools — the gap NVIDIA's NemoClaw later targeted. It is listed here as an experiment with someone else's tool, not as something I built.
Built in public to learn something or prove a pattern. Some are published packages, some are demos that live on this site.
Experiment: OpenClaw
- ▸Understanding how a general-purpose agent runtime structures tools, memory and orchestration
- ▸Why enterprises hesitate to give autonomous agents access to data and tools
- ▸Explored its plugin model for tools, memory and reasoning
- ▸Looked at its options for sequential, parallel and hierarchical agents
A first-hand look at the architecture of a popular agent framework
JobJam.io — AI Job Search & Application Platform
AI-powered job search platform: discover roles, evaluate fit, tailor applications, and close skill gaps. One-time pricing, no subscriptions.
Fathohm — Comprehension-Debt System of Record
See how much of your codebase no human understands. A treemap of your repo colored by human comprehension score, with a tracked, assignable metric for 'who understands what' in an AI-native codebase.
Grenz — Firewall for AI Agents
A local firewall for AI agents: scoped, revocable, observable permissions instead of your full GitHub token. Deny-by-default, MIT licensed, live at grenz.dev.