Case study
Tetherlab
An MCP-based coordination layer that lets multiple AI coding agents see each other's intent before they write code, replacing merge-conflict chaos with intent-level coordination.
- Role
- Co-founder & Engineer
- Period
- 2025-04 → Present
- Status
- In progress
- Tags
- 5
The problem
When you run more than one AI coding agent in the same repo (Claude Code and Cursor, or Codex CLI alongside Gemini CLI), they each have their own private view of what they are about to do. They plan in isolation, write code in parallel, and produce merge conflicts that look nothing like the conflicts humans write, because each agent already believed the other was going to do something else.
The conventional fix is "git is good at merging, let the agents fight it out." That works for trivial cases. For non-trivial work (refactors, shared interfaces, schema migrations) it produces chaos.
What we built
Tetherlab is a small MCP server that every participating agent connects to. Each agent publishes its intent (what files it plans to touch, what symbols it plans to introduce or rename, what assumptions it is making about neighboring code) before it writes anything. Other agents see those intents in real time and can adjust their own plans (or call out a conflict explicitly) before either of them spends tokens producing code that will not fit together.
The product is live in open beta with paying trial users. The current wrappers cover Claude Code, Cursor, Codex CLI, Gemini CLI, and OpenCode.
What I owned
Three of us co-founded the company. My slice of the work:
- The MCP server itself: the canonical intent store, the conflict-detection logic, and the protocol extensions we have prototyped on top of standard MCP.
- Two of the agent wrappers (Claude Code and Cursor): the bit that hooks each tool into our coordination layer without forcing the user to change how they invoke the agent.
- A meaningful chunk of the go-to-market: positioning, landing-page copy, technical content, and early user conversations.
The other two cofounders own the rest of the engineering surface and most of the customer-facing work. We share product and roadmap decisions across the team.
What was hard
We over-invested in a custom protocol extension before we had validated that the basic intent-publishing primitive solved the user's problem. Two months of protocol work would have been better spent as one month of "ship the simplest thing that coordinates two agents" followed by user interviews. The protocol now exists, but the v1 should have been thinner.