
Introducing Replicas V1, the background coding agent built for you. Replicas is a background coding agent that: - Lives in its own sandbox - Runs your codebase locally - Accessible from anywhere (PR reviews, Linear, Slack, API) @tryreplicas
Replicas
45 posts

@tryreplicas
Delegate tasks to coding agents in isolated workspaces.

Introducing Replicas V1, the background coding agent built for you. Replicas is a background coding agent that: - Lives in its own sandbox - Runs your codebase locally - Accessible from anywhere (PR reviews, Linear, Slack, API) @tryreplicas



Added Skills for your Replicas workspaces! In Environments, search and enable anything in the skills.sh directory, like @vercel's agent-browser. For skills with auth, like @arlanr's Nia, you can configure environment variables in the same menu:


At Stripe we have a tool called "minions" -- it lets us kick off async agents built right in our dev environment to one-shot bugs, features, and more e2e. I have team, project, and personal channels dedicated just to working with minions. I like to think of it as a new type of pair programming -- "pair prompting." Read more --> stripe.dev/blog/minions-s…

We hit a real milestone today. 5% of all PRs merged now come from our in-house background agents. Last year we built an agentic harness: a Slack-native framework with the same tools and context as our engineers. Tag the agent in any thread → it plans, debugs, and ships a PR. Started as “Claudebot” (Anthropic pls don’t be mad 💙). We had one vision. Built by two Superbuilders. Boom. Think it. Plan it. Build it. PS - def taking suggestions for a new name 😀




Plan Mode is finally live in Replicas! - trigger plans from linear, github, slack, or dashboard - agent sends a link there to review plan - useable with claude code or codex Have found higher quality code on medium-large tasks using this :)


We cut our background agent boot time by 90% (click → ready in <3 seconds) Replicas is now powered by @daytonaio sandboxes! Inspired by @tryramp's "speed of thought" approach to Inspect, this is our first step in making background agents completely frictionless to spawn. Since migrating over I've started spawning tasks the second I have an idea from the dashboard - because it feels as fast as prompting locally. Video is not sped up 👇


The craft of engineering is rapidly changing. At @tryramp, we built our own background coding agent to accelerate faster. We call it Inspect. It wrote 30% of merged frontend + backend PRs in the past week. It’s powered by @opencode, @modal and @CloudflareDev. It runs fully in the cloud, and starts in seconds, letting every builder work at the speed of thought, no setup required. Today, we’re open sourcing the full blueprint so anybody can build their own Inspect. Just give our spec to your current coding agent, and let it build your new favourite.
