Ten developers.
Ten agents.
One shared brain.
Your teammate’s agent just renamed the auth module. Yours has no idea. Colaberi connects every developer’s local Claude Code or Codex session to one shared project brain — same context, same decisions, and overlapping work flagged before it reaches the diff.
$ npm install -g @colaberi/connectorFree for solo developers · Everyone keeps their own agent subscription · Your raw transcript never leaves your machine
Scroll · the film plays as you go
01 · Connect
Every developer installs once
One npm command in the repo. Claude Code and Codex sessions keep working exactly as before — the connector just watches.
48 frames · generated for this page, scrubbed by your scroll
Ten agents. None of them know about each other.
Parallel agents are the right model — every developer should have one. The problem is that each runs blind.
- 01
Every agent works blind
Your agent doesn't know your teammate's agent just renamed the auth module. Two agents refactor the same file from different assumptions, and nobody finds out until merge.
- 02
Decisions never reach the other agents
The team picked React Query on Tuesday. Your agent knows. Nobody else's does. Every decision gets re-explained to every agent, by hand, forever.
- 03
Collisions surface at review, not before
Two agents ship contradictory changes. You find out in the pull request, after both developers burned an afternoon on it.
One install per developer. Nothing else changes.
Everyone keeps the agent, the branch and the subscription they already use.
brain
$ npx colaberi connect
Free for solo. Per seat for teams.
Solo is free forever. Team is $12 per seat a month, or $10 a month billed yearly. A seat is a developer whose connector publishes into a team workspace. Everyone keeps their own agent subscription; Colaberi never resells one.
- Claude Code and Codex support
- Local secret redaction
- Project brain and decision history
- Unlimited projects and repositories
Solo workspaces can't add team members or extra workspaces — that's what Team is for.
- Everything in Solo
- Shared project brain across the team
- Overlap and conflict detection
- Audit-grade activity log
- Invite links and role management
Sign up free, then upgrade when you invite your first teammate.
- Everything in Team
- Single sign-on and provisioning
- Custom data retention windows
- Security review and DPA
- Priority support and onboarding
Questions engineers ask first.
Something else on your mind? Talk to us
Do I need to share my Claude or OpenAI subscription?
No. Colaberi never shares, proxies or resells an agent subscription. Every developer's prompts run on their own account, exactly as they do today. The connector only reads the local session log.
Does my source code get uploaded?
Your raw transcript stays on your machine. The connector redacts secrets locally — AWS keys, GitHub tokens, sk- prefixes, .env values and your own patterns — then publishes a redacted event stream. The cloud never receives the unredacted session.
Does it work with both Claude Code and Codex?
Yes, and that's the point. Both are normalised into one event shape, so a team running a mix of the two shares a single project brain. You can have Claude Code on one branch and Codex on another in the same repo.
Do I have to change how I work?
No. You run one command in your repo and then use your agent exactly as before. The connector attaches to the session automatically and re-scans every ten seconds, so start order doesn't matter.
What counts as a seat?
A developer whose connector publishes into a team workspace: $12 per seat a month, or $120 per seat a year. Solo use is free and unlimited. You choose the number of seats at checkout; email us any time to add more.
Give your team’s agents a shared memory.
Free for solo developers. One command to connect, and nothing about how your team already works has to change.