Launch HN: Runtime (YC P26) – Sandboxed coding agents for everyone on a team

Hacker News Top Products

Summary

Runtime is a platform that provides sandboxed coding agents with company context, integrations, and guardrails, allowing every team member to automate tasks and ship work using agents. It includes custom environments, specialized agents, observability, and supports various integrations and deployment options.

Hey HN, We&#x27;re Gus and Carlos from Runtime (<a href="https:&#x2F;&#x2F;runtm.com">https:&#x2F;&#x2F;runtm.com</a>). We&#x27;re building infra that lets your whole team (including non-engineers) ship with Claude Code, Codex, and other agents without engineering having to handhold every session.<p>After Mentum (YC S21) was acquired, I personally shipped 4 full-stack products in 3 months using coding agents. When I tried to roll the same workflow out to the rest of the team, it fell apart: Most PRs were unmergeable slop - Every repo required an engineer doing one-off local setup. - Skills and context lived in one person&#x27;s head. - There was no safe way for a PM to touch a real codebase without risking a bad deploy or a secrets leak.<p>Carlos comes from building agentic reconciliation systems at Modern Treasury and had a similar experience when letting his support team use devin.<p>We ended up building internal background agent infra but it quickly became a nightmare to mantain and develop. We built Runtime so you don&#x27;t have to do this kind of thing.<p>Runtime work like as follows. Engineering defines the context once: system instructions, skills, and scoped integrations installable via CLI, mise, npm, or any package manager. Then Runtime snapshots your full running environment including multi-service Docker Compose setups, Kafka, Redis, seeded DBs, so it comes up in milliseconds with every server already running.<p>We orchestrate across sandbox providers like E2B, Daytona, EC2 or self-hosted K8s depending on your setup. Secrets are injected through our managed proxy so they never touch the agent directly, and guardrails run at the infrastructure level: command allow&#x2F;deny lists, network egress controls, and RBAC scoped per human and per agent. Every session also gets a shareable preview URL, so internal builds go from sandbox to the rest of the team without needing production access.<p>Runtime works with whichever agent your team already uses: Claude Code, Codex, Cursor, Copilot, Gemini, Devin. You can trigger sandboxes from our web app, CLI, Slack, Linear, GitHub, or API.<p>One of our customers built an on-call inspector that wires PagerDuty, Sentry, and their repo so when an alert fires, the agent finds the cause and opens a PR with a unit test before anyone gets paged. Another runs a finance agent in a private Slack channel pulling from Stripe, NetSuite, and Snowflake to run reconciliations in minutes with source rows attached.<p>A fintech unicorn and several YC scaleups are live on Runtime, including a few teams who had built similar infrastructure internally and handed it to us to take over.<p>The core is open source at <a href="https:&#x2F;&#x2F;github.com&#x2F;runtm-ai&#x2F;runtm" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;runtm-ai&#x2F;runtm</a>. Hosted version is live at <a href="https:&#x2F;&#x2F;app.runtm.com">https:&#x2F;&#x2F;app.runtm.com</a>, free tier included. We&#x27;re charging a flat platform fee plus compute, no token markup.<p>Check our demo: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=wLwj__aEEh4" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=wLwj__aEEh4</a><p>We&#x27;d love to hear how you&#x27;re thinking about the infra for letting more people across your org use coding agents without creating chaos!
Original Article
View Cached Full Text

Cached at: 05/21/26, 06:14 PM

# Runtime - The runtime for all your team's agents Source: [https://www.runtm.com/](https://www.runtm.com/) ## The runtimefor all your team's agents\. Sandboxed coding agents with your company's context, integrations, and guardrails\. ### Environments with every tool your team uses\. Connect all of your company's environments, from monorepos to microservices\. Install any CLI, API, service, or MCP server, layer in custom instructions and skills, then set guardrails and secrets\. Snapshot once so every session boots in seconds\. Install frommise,npm,brew, orgithub ![Datadog](https://www.runtm.com/logos/datadog.svg)Datadog![Salesforce](https://www.runtm.com/logos/salesforce.svg)Salesforce![Stripe](https://www.runtm.com/logos/stripe.svg)Stripe![NetSuite](https://www.runtm.com/logos/netsuite.svg)NetSuite\+ anything else ### Specialized agents your team can tag wherever they work\. Build an alert inspector for \#incidents, a sales prospector for \#revenue, or a support triager for your inbox\. Each one runs investigations, ships PRs, drafts replies, and posts findings without anyone asking\. Tag them from Slack, Linear, GitHub, or anywhere your team already works\. Slack![Linear](https://www.runtm.com/logos/linear.png)LinearGitHubJira\+ many more ### Let anyone on your team work alongside agents\. Anyone can prompt an agent and watch it work, from engineering to support to sales\. Hand off mid\-session, collaborate in real time, and ship the result however your team needs: a PR, a deploy, a message, a ticket, or a report\. ### See and govern every agent in your company\. Live visibility into every session: tool calls, chain of thought, file changes\. Track cost per agent, per user, per team\. Spend limits, allowlists, and approval gates baked in\. ## Use it your way Browser, terminal, or API\. ## Every layer your team's agents need\. Built in\. Customizable\. Ready to ship\. Sandboxes, orchestration, guardrails, observability, integrations — Runtime handles the agent infrastructure your team would otherwise spend months building from scratch\. ## A coding agent for every team\. Each team gets a sandboxed agent with the data, integrations, and guardrails they need\. ## Extend it\. Self\-host it\. Make it yours\. Deploy Runtime on your own infrastructure with your own cloud, models, and secrets\. Extend it with custom skills and integrations\. Apache 2\.0 CLI & Shared libs ## FAQ Who is Runtime for?Runtime is for any company that wants every function to ship work with a coding agent, not just engineering\. Platform teams use it to roll out agents safely, while product, design, marketing, support, finance, and people teams use the same sandbox to automate work they already own\. How do agents work inside Slack? Do we always have to tag them?You can tag them, or let them work proactively\. Each team gets its own sandboxed agent in Slack with a name you choose, like @runtime\-finance, @runtime\-support, or @ada, that you @mention with a question or a task\. You can also point it at a channel so it picks up new messages on its own without anyone tagging it\. Either way, it replies in a thread with the result, the source rows it used, the cost of the run, and an Open Session button so you can step into the sandbox if you need to dig deeper\. What integrations come out of the box?Runtime ships with first\-class connectors for the systems most teams already run\. That includes data warehouses \(Snowflake, BigQuery, Redshift\), billing \(Stripe, NetSuite, QuickBooks\), HR \(Rippling, Gusto, Workday, Deel\), CRM and marketing \(HubSpot, Segment, GA4\), support \(Zendesk, Intercom\), alerting \(PagerDuty, Sentry, Datadog\), and engineering \(GitHub, Linear, Notion\)\. Beyond that, you can bring any tool with an API key: the agents reach it through its CLI, MCP server, SDK, or REST API, the same way one of your engineers would call it\. Does an agent ever touch our raw production data?No\. Agents work against sandboxes that mirror or sample your data with the policies you set, including PII redaction and row\-level scopes\. Production writes happen only through reviewed actions or pull requests, so the agent never edits live systems on its own\. Can I self\-host Runtime?Yes\. You can run Runtime fully inside your own cloud with your own models, sandboxes, and storage, or use our hosted version\. Policies and audit logs follow your team across both\. [Talk to the team](https://cal.com/gustavo-trigos-q80bop/runtime-demo-meeting) if you want help getting set up\. ## Give every team its own coding agent\. Sandboxed, named, and live in Slack\. Self\-host or cloud\. No credit card required\.

Similar Articles

Runtime

Product Hunt

Runtime offers sandboxed coding agents for team collaboration, launched on Product Hunt.

Launch HN: Superset (YC P26) – IDE for the agents era

Hacker News Top

Superset is an open-source IDE for orchestrating multiple CLI-based AI coding agents in parallel, with isolated git worktrees, built-in monitoring, and a diff viewer. It supports various agents like Claude Code, Codex CLI, and Gemini CLI.