Agent-Native Companies Are Already Morphing
A follow-up on the Agent Taxonomy piece. Co-written with Will Chen for Idyllic Labs. Agent-native companies are already here — and they look nothing like what you expected.
Software engineer shipping AI agent infrastructure and Solana programs. Open source, always.
Worked with
CLI toolkit for agent-native organizations. Agent definitions in MDX, Unix-native execution, TUI and web UI.
nginx for AI agents. Cost budgets, rate limiting, circuit breakers, and a live dashboard for agent fleet management.
Decentralized protocol for creating and investing in on-chain index funds (ETFs) on Solana. Strategy builder, one-click deployment, and real-time portfolio tracking.
Personal AI operating system built on Claude Code. 19 slash commands, 30+ Python scripts, autonomous job search pipeline. Filesystem-native — fork it, make it yours, run your life on it.
Context-aware security layer for Model Context Protocol. Zero-trust proxy between AI agents and MCP tool servers — inspects JSON-RPC traffic, enforces least-privilege policies, detects plan injection attacks. B.Sc thesis project at UNILAG.
AI-powered security scanner for Solana programs. Finds vulnerabilities and generates proof-of-concept exploits automatically.
A follow-up on the Agent Taxonomy piece. Co-written with Will Chen for Idyllic Labs. Agent-native companies are already here — and they look nothing like what you expected.
A deep dive into Steven Yegge's Gas Town orchestrator and what it means for the future of agent infrastructure. Read this, then go read the behemoth launch post.
A classification system for understanding agent architectures based on who initiates action and when the process terminates. Four modes: Copilot, Daemon, Subagent, Workflow.
LLMs deadlock 95% of the time in simultaneous coordination. Communication makes it worse. The fix is not more intelligence — it's a 50-year-old CS primitive.
How scaffold engineering delivers 10x more improvement than model upgrades — and why 2026 is the year it becomes obvious.
Everyone's talking about 'Continuous AI.' Nobody's talking about the write-ahead log for agent actions that makes it safe.
Interested in working together or just want to say hi?