Lanes
Several computers, one conversation
Each lane is one person’s computer and folder. Any collaborator can send work to any online lane, with the owner’s consent.
Private beta
AI work was never meant to be single-player.
Pairon is a shared room where your team brings Claude Code, Codex and OpenCode work together, with project context visible across connected computers.
Letting teams in a few at a time · Have an invite? Sign in
A replay of a Pairon room. Maya asks Codex, running on her laptop, why a checkout test is flaky. Dev joins and points out that two test suites share a fake clock. Codex, now working for both of them, fixes test/setup.ts and the tests pass. Sam joins to watch, and Maya saves the decision to project memory.
ReplayMaya opens a room. Codex runs on her own laptop.
Scripted product demonstration using fictional people and example data.
02The single-player problem
Everyone has their own chat. Nobody has the whole story.
When three people ask three agents about the same bug, each agent reads the same code from scratch, each person explains the problem again, and whatever gets decided stays in one private window.
Three private chats: Maya asks Codex, Dev asks Claude Code and Sam asks OpenCode about the same flaky checkout test, and each agent reads the same files from scratch. Scrolling on merges them into one Pairon room, where Maya and Dev both write to one Codex agent whose turn is for both of them, Sam reads along, and the decision is kept in the room’s History.
03Watch a session
Steer the agent. Don’t just watch it.
Forty seconds of one conversation: a task, a teammate who knows better, a hand-off to a second computer, and a decision that sticks. Switch seats to see what each person, and the agent, actually gets.
A 40-second replay of a Pairon conversation that plays as you scroll. Maya asks Codex, on her MacBook, to retry timed-out payments while Sam watches as a viewer. Dev joins, connects a second computer and points out a double-charge risk, so Codex’s next turn works for both of them and reuses the idempotency key. Codex proposes handing the web fix to Dev’s computer, Maya sends it, and Claude Code updates the checkout status there. Dev checks the result and Maya saves the decision to project memory. You can switch between Maya, Dev, Sam and Claude Code to see what each seat shows.
View as
Owner. Codex runs on her MacBook. Hand-offs from her instructions wait for her to send them.
Maya asks Codex, on her MacBook, to retry timed-out payments. Sam is watching.
Scripted product demonstration using fictional people and example data. Scroll to play it; choose a step to jump.
04How it works
From a question to merged work in five steps.
01Start a conversation
Open a conversation inside a project. A project is the folders your agents work in, shared with everyone you invite to it.
05Anatomy of a room
What’s actually in there.
Each piece below is a real part of a Pairon conversation today, not a mock-up of a roadmap.
Queue
Instructions wait their turn
Each lane runs its instructions in order. Add to the queue while an agent works, and everyone sees what’s next.
Hand-off
Pass a sub-task to another computer
An agent can propose sending part of the work to a teammate’s lane. The person who gave the instruction decides.
Parallel tries
Two agents, one question
Run the same instruction on two lanes side by side, then keep the answer you prefer.
Review
Merge a teammate’s copy
Changes made on another lane come back as a review. When both sides touched the same lines, you choose, or ask an agent to combine them.
Previews
Show the running app
Share a port from your computer and everyone in the room can open it through a Cloudflare link until you stop.
History
Every step, in order
Instructions, finished turns and connections are kept in the conversation’s History, with change summaries rather than file contents.
Memory
Decisions that stick
Save a decision once and later agents treat it as settled. Project memory is what our published benchmark measures.
06Workflows
Three ways teams share one agent.
Short replays of situations Pairon is built for. The people and repositories are made up; every screen is the product’s own.
Three replays that play as you scroll. One feature, two computers: A replay. Maya asks Codex on her MacBook to add a refund date to the orders API. Dev asks Claude Code on his Mac mini to show it on the order page. Both agents work at the same time and both finish in the same conversation. Debugging together: A replay. Lena asks Codex why search misses accented names. Codex finds the query keeps accents while the index strips them. Arjun joins and says to use Postgres unaccent in the query. Codex, now working for both, makes the fix and the search tests pass. Picking up where they left off: A replay. Last night Codex moved four of six invoice templates to Playwright for Maya, and Maya saved that decision. Next morning Kenji joins from Tokyo, connects his own computer with OpenCode, and finishes the last two templates. The History panel lists every step.
Backend on one laptop, frontend on another. Two agents work at once, and both turns stay in one conversation.
Maya and Dev each connect a computer to the same conversation.
07Measured
Measured, not promised.
We ran the same agent on the same tasks, with and without Pairon’s project memory, across three real codebases. With memory it solved them for less in every repository.
Measured
- Lower cost per solved task
- 19–33%
- Paired, graded runs
- 360
- Upper end of every 90% CIa saving in all three repositories
- < 1.0
- Answer qualityno significant difference
- Same
Simulation 1
Agent alone
1.00
With Pairon
0.674
90% CI 0.538–0.835
Simulation 2
Agent alone
1.00
With Pairon
0.778
90% CI 0.619–0.944
Simulation 3
Agent alone
1.00
With Pairon
0.811
90% CI 0.702–0.936
08Team model
Where a team’s tokens actually go.
A model, not a measurement. It compares several people each running their own agent on the same task with one Pairon room, and separates the part that rests on our benchmark from the part that doesn’t.
Workflow
The core use
People on the task
Agent lanes in the room
Computers doing the work. Never more than people.
Complexity
Scales discovery and instructions by ½, 1 or 2.
Memory ratioMeasured
Measured cost per solved task with Pairon’s memory: 0.778× the agent alone.
AssumptionsDefaults
Token and time defaults are our assumptions. They have not yet been calibrated from recorded sessions.
tok
%
tok
tok
min
min
min
%
Simulated: 252k tokens without Pairon, 164k in one Pairon room, 35% fewer. Estimated time: 3 h 45 min against 2 h 23 min.
TokensSimulated
164k−35%
with Pairon, against 252k without it
People’s timeEstimated
2 h 23 min−1 h 23 min
with Pairon, against 3 h 45 min without it
Where the difference comes from
88k tokens- One shared roomSimulated
- 72k tokens
- 48k not rediscovered, 24k not re-briefed
- Project memoryMeasured
- 16k tokens
- Uses the measured ratio you picked
- Agent sessions started
- 3 → 1
- Duplicated context
- 48k → 0
- Catch-up time
- 1 h → 0 min
Illustrative simulation based on the assumptions shown. Not a measurement.
09Your code stays yours
Built to hold even if our server doesn’t.
The rules for what an agent may do on a computer are enforced by the Pairon runner on that computer, not by our server. A compromised server can send requests; it can’t grant permissions.
Agents run on your computers
Claude Code, Codex and OpenCode run through the Pairon runner on your own machine, limited to the folders you allow.
Code is relayed, not stored
File contents, diffs and terminal output pass through Pairon to the room but aren’t kept. History keeps change summaries. Conversation text is stored.
Secrets are redacted on the runner
Secret redaction, the sensitive list, approval mode and the pause switch are all enforced on the computer, before anything leaves it.
Loosening rules needs the owner
Raising access or allowing a new folder needs the computer owner’s confirmation — a local prompt or their passkey — which the runner checks itself.
Source: Pairon architecture decision record 0002, “The runner, not the server, enforces what agents may do on a computer” (accepted 16 September 2026).
10Pricing
Pay per person. Watching is free.
In our benchmark, agents cost 19 to 33 percent less per finished task with Pairon. On a $20 agent plan, that saving is about what one Team seat costs.
Founding prices, for a limited time
Free for everyone during the betaEvery plan is unlocked at no charge while Pairon is in beta. The prices below start at public launch, and beta workspaces can still take the founding price.
Free
Two people on one project
$0
for as long as you like.
Start free in the betaFree includes
- 2 people who can steer
- 1 project
- 30 days of history
- Unlimited watchers
- Every agent, unlimited turns
Team
Most teams start hereFriends, co-founders, or one person with several projects
Join the betaFree in betaFree during the beta. At public launch: $5 per person per month at the founding price.Everything in Free, plus
- Up to 5 people
- Unlimited projects
- 1 year of history
- A guest steerer for each person
- Add teammates free until your next bill
Startup
A company, from the sixth person
Join the betaFree in betaFree during the beta. At public launch: $10 per person per month at the founding price.Everything in Team, plus
- 6 people and more
- Unlimited history
- Audit log download
- Savings per member
- Replies within one working day
Business
Larger teams that need their own limits
Custom
Priced by agreement.
Talk to usEverything in Startup, plus
- More than 25 people
- Limits set for your team
- A price agreed with you
Paid plans open at public launch. During the private beta nothing is limited and nothing is charged. Prices are before tax. Pairon is run by an individual in India, not a registered company; paid plans will be sold through Dodo Payments, the merchant of record. Benchmark: Codex, three repositories, 360 runs, 23 September 2026.
Private beta
Bring your team into the room.
Request access with your email. We’ll send one message to confirm the address. A request is not an account and does not connect a computer.
- Request access with an email address
- Confirm the address from one service message
- Connect a computer only after account access is approved