Owner / Lead Architect
Creator and project lead of CorvidLabs. Architecture, product, and team decisions all land here. Currently building corvid-chat + Merlin.
corvid-chat Merlin fledge spec-sync
🪶 The team
Four humans,
one agent runner.
A small human team that ships across the catalogue, plus a single agent runner per session. The agent stack is one tool, not eight personas.
Humans
Four people. Each one owns a real surface.
🎨
Tofu
Designer / Co-founder
Co-founder and creative direction for the CorvidLabs aesthetic. Brand, UI, NFT collections, the pixel-raven mark.
Brand UI NFTs
Developer
Kotlin / Ktor backend developer. Keeps the team honest and holds shipped work accountable.
Kyntor kt-algochat KMP
Infrastructure
Infrastructure focus. Rust, Podman, Kubernetes. Where the self-hosted runners and prod servers come from.
Infra Rust K8s
The agent, honestly
Sessions are launched per task. There's no always-on roster of specialized agents. That's aspirational shape we don't claim. Here's what's actually been driving the work:
- Historically Claude Code
Worked. Productive. But the daily-driver budget was metered, and the agent was something CorvidLabs paid to use, not something it owned.
- Today corvid-agent + Merlin (migrating)
Sessions run on the in-house corvid-agent platform. Sometimes spawned from Claude Code, increasingly spawned from Merlin. Per-task, not always-on.
- Next Merlin solo
Once the sub-agent plugin lands, Merlin handles real multi-step work without babysitting and Claude Code stops being the daily driver. That's the load-bearing gate from the strategy chain.
Read the platform: corvid-agent. Read the next runner: Merlin. Read the strategy that connects them: the dependency chain.
How we work
Humans plan and steer. The agent runner executes per task. Git worktrees keep parallel work isolated; spec-sync keeps the contract honest; fledge runs the same verify lane on every commit.