Multiple AI agents, one repo
RAAV gives multiple coding agents shared product memory, file claims, and branch lanes. The founder sees parallel work, pending decisions, and completed-run evidence from one board.
Two agents editing the same repository with different assumptions create merge work, while the founder has no clear view of ownership.
Each agent claims a named task, branch, worktree, and file scope before editing. RAAV shows those claims together, so a founder can see parallel work and an agent can stop before crossing into someone else's files.
Parallel agent work creates more than merge conflicts. It becomes hard to see which agent owns each part of the product. RAAV records that ownership before editing begins.
Without a coordination layer, overlapping edits are discovered when diffs collide. This is common during refactors, UI cleanup, and launch polish.
RAAV makes each agent claim a task, files, and a lane before editing, so other agents and the founder see active ownership first.
Swimlanes show the agent, branch, claimed files, and current status for each piece of work.
Agents see the same ownership record that the founder sees on the board.
All agents read the same accepted product record. Suggested changes wait for founder review, and completed runs retain their verification results.
Coordination is memory plus visibility, not another lock.
RAAV does not replace your coding agent. It gives the agent a durable operating system for product truth, task ownership, and proof.
All agents read the same product handbook and lane state.
Each agent claims files and a lane before editing.
Conflict checks surface active work on the same surface.
The founder checks active lanes and completed-run evidence from one board.
Ask your agents to install RAAV and claim before editing. The founder gets swimlanes to watch and audit to supervise the whole team.
Install RAAV in this repo for multiple agents. Before editing, each agent should claim files and a branch lane and check conflicts. Show me swimlanes of who is working where.Claims coordinate the work; Codex, Claude Code, Cursor, or another connected agent still writes the code.
Most tools either write code or track human tickets. RAAV sits between the founder and the coding agents as shared product memory, coordination, and audit.
Founders ask how RAAV keeps parallel agents from stepping on each other.
No. A claim records that an agent expects to edit specific files for a task. It does not lock at the OS level, but it gives other agents and the founder visibility before work overlaps.
Yes. That is the point. Codex, Claude Code, Cursor, and MCP agents share one product handbook, task ledger, claims, lanes, and audit trail.
No. Your coding agents still reason and edit the repository. RAAV records their work boundaries and shared project state.
The Trial is €10/week. Team is €40 per human seat each month with a two-seat minimum; agent identities are not seats. Checkout is currently closed outside testing cohorts.