Turn coding agents into teammates anyone can use from Slack, Linear, CLI, API or your browser. Ship features, query data, build dashboards, automate workflows. All within your company's context, skills, integrations, and security guardrails.
Hey PH! Gus, co-founder of Runtime (runtm.com, YC P26).
Every company we talk to hits the same wall with coding agents: AI slop in PRs, the one "agent expert" whose setup nobody can reuse, compliance blocking Claude Code, and teams building their own internal orchestrator just to make it work.
Runtime is the layer that fixes this. Anyone on your team can package a specialized coding agent, install CLIs, write the skills, connect the tools, add guardrails, and the whole company uses it from where they already work (Slack, Linear, GitHub, the browser).
Here are some of the agents our customers have built:
- On-call inspector (PagerDuty + Sentry + repo): alert fires, agent finds the cause, posts a PR with a unit test before anyone gets paged
- GTM engineer (Salesforce + Gong + notes): growth ships landing pages or automates campaigns from Slack
- Finance agent in a private channel (Stripe + NetSuite + Snowflake): runs reconciliations in minutes with source rows attached
- Support triager in Zendesk: pulls the customer profile and drafts a reply with the SQL behind every claim.
Each runs in its own sandbox with full audit logs, hard spend caps, multi-agent support (Claude Code, Codex, Cursor CLI, Gemini), BYO keys or OAuth, and optional self-hosting in your VPC.
A fintech unicorn and several YC scaleups are already using us to let PMs, marketing, and support ship real product changes or automate workflows in hours.
For PH: We are giving out 500 credits for everyone to use.
Try it now: app.runtm.com
If you had Runtime today, what agent would your team build first?
Gus, Carlos, Manu and the Runtime team
The ephemeral sandbox handles execution isolation cleanly, but what happens to data that flows through the agent to external services it calls during a task? If a non-engineer asks the agent to "query the customers table and post a summary to Slack," the sandbox is destroyed after, but the data already left to Slack. Is Runtime enforcing data-path policies at the integration layer, or is the security boundary scoped to the execution environment itself?
Sandboxing agents is the right call - giving an agent full system access is a liability. Does it work for solo devs or is it built around team workflows with permissions and roles?
Love that list of integrations! Will forward this to my team
Insane product!! And insane ability to cook 🔥
Sow questions:
How does it work for deploying across multiple repos? (Modular / micro service architecture vs monolith)
And across multiple products? (Can we connect it to notion where we keep all the specs?)
Nice, congrats on the launch Gus!
The on-call inspector got me. Curious on how you think about trust as this scales. Once non-engineers are shipping real changes from Slack, what makes a team comfortable letting the agent run without someone reviewing every step?
Used Runtime as soon as it launched and it was super useful to get non-technical folks setup and contribute code to a mature codebase while having the right guardrails in place.
Very cool! Our company has dealt with the struggles of using coding agents across different teams
As a small bootstrapped company building a product that has many dependencies and environments, we found that over time, each engineer became very siloed on the part of the stack that they could work on because setting up the right dev environment on another computer took forever.
Runtime solves this issue for us and now every engineer can contribute pretty effortlessly at any part of the stack at a moments notice. Pretty game changing stuff going on here.
Honest question from a non-dev: what’s a realistic first use case for someone like me — a small business owner who wants to automate workflows but doesn’t code? Would love a concrete example
The context/guardrails layer is the challenge here: most teams aren't blocked on the AI quality, they're blocked on trust and auditability. Curious how you're handling state persistence across agent sessions, especially for teams with long-running content or doc workflows.
Interesting project! We solved this through unified rules and settings for the entire team, along with a shared toolset based on Claude Code. But your product sounds more convenient.
Thats really cool to see, ive also been working on a side project to help at work and I got inspired by ios and the way they sandbox and can agree this helps a lot with permissions and data leakage. Really cool to see others in this realm, i wasn't looking to make a product but rather just something to help with my team at work.
Just curious on the sandbox, do you just spin up some small alpine and run a vectored db on it or the agent lives within this sandbox as well, can sandboxes communicate to other sandboxes? I looked on the website and it might just be me but i didn't find too much info on that. If its proprietary then of course no prob at all as well :) . I work at a crypto company and keeping the data within the sandbox is a priority as employees have different rights and different private keys they can be granted to run automations on etc...
I will give it a try solo and if interesting ill introduce to the team. Inspiring stuff, good luck guys!
Can’t wait to try this tool out, especially through Slack! Could save so much time with my team!
Sandboxed coding agents inside Slack is a genuinely good idea for teams — keeps the agent close to where decisions actually happen. My main question is around state: if an agent starts a task in one channel and needs context from another, how does Runtime handle that? Isolation is great until it becomes a silo.
I've seen the shipping speed from this team and it's really something else. BYOK, self-hosted VPC, multi-runtime, and hard spend caps into a v1 launch is impressive. Have experienced this pain point across multiple teams so I know you're onto something big. Congrats Gus!
About Runtime on Product Hunt
“Sandboxed coding agents for everyone on your team”
Runtime launched on Product Hunt on May 20th, 2026 and earned 224 upvotes and 56 comments, placing #5 on the daily leaderboard. Turn coding agents into teammates anyone can use from Slack, Linear, CLI, API or your browser. Ship features, query data, build dashboards, automate workflows. All within your company's context, skills, integrations, and security guardrails.
Runtime was featured in Slack (72.2k followers), Developer Tools (512.7k followers) and Artificial Intelligence (468.9k followers) on Product Hunt. Together, these topics include over 164k products, making this a competitive space to launch in.
Who hunted Runtime?
Runtime was hunted by Garry Tan. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Runtime stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Garry Tan