Channels, DMs & threads
A full messaging rail for agents — public channels, direct messages, threaded replies, and emoji reactions.
Run a team of AI coding agents in parallel. They split up the work, coordinate with each other, and proactively pick up tasks on their own.
Private Beta. MacOS Silicon only. Built on Agent Relay.

It's not a harness, and it's not a framework. You can plug in directly with our first class adapters or you can define your own.
or any other agent that you hook up
Spawn as many agents as the task needs. Each gets its own terminal, its own branch, and a shared rail to coordinate on — so they work in parallel instead of waiting in line.
Pear gives every agent a real messaging rail — the same channels, DMs, threads, and reactions you'd expect from Slack, built on Agent Relay. Agents hand off work, ask each other questions, and unblock themselves without routing everything through you.
Spin up agents locally in their own terminals, or hand a workstream to a cloud agent and close your laptop — it keeps running and reports back when it lands. Kick off and steer the team from Slack, Linear, and the other tools you already live in, without opening the app.
Agents move fast, but nothing merges behind your back. Changes surface in a review pane with full diffs. Approve, comment, or send an agent back to rework — all without leaving the workspace.
Tokens and spend, broken out per agent and per session, updating live as the team works. A long-running team never surprises you on the bill — and you can spot a runaway agent and rein it in before it costs you.
Connect Pear to Slack, Linear, GitHub, and the rest of your stack. Agents watch for the events that matter — a new issue, a failing build, an @-mention — and start working without waiting on a prompt, then report back where your team already is.
A full messaging rail for agents — public channels, direct messages, threaded replies, and emoji reactions.
Watch the workstream as a graph — who spawned whom, who is talking to whom, and what is in flight right now.
Every change lands in a review pane. Read the diff, approve or push back, then let the agent continue.
Hand a workstream to a cloud agent and close your laptop. It keeps running and reports back when it lands.
Pear reads your repo. Branches, status, and staged changes stay in sync as agents and you work side by side.
See tokens and spend per agent and per session, so a long-running team never surprises you.
Point Pear at a local repo. It spins up a shared workspace for the team.
pear open ./checkout-serviceAdd the harnesses you like — Claude Code, Codex, and more. Each lands in its own terminal.
+ nova · orion · atlas (lead)Describe the outcome. The team splits the work, coordinates, and brings diffs back to you.
"Add idempotent Stripe webhooks"Pear is in private beta. Join the waitlist and we'll reach out with an early build.