Runtime
Runtime focuses on giving companies a shared runtime for coding agents so every team can run sandboxed, governed agents against real systems without building their own infrastructure. It plugs into existing coding agents such as Claude Code, Cursor, Copilot, Gemini CLI, Devin, and OpenCode, then layers on sandboxes, integrations, guardrails, and observability so agents can ship pull requests, tickets, and reports across the organization.
Make a decision about Runtime
- Already use it? Add Runtime to Stack Autopsy — check cost, overlap and safe cancellations.
- Thinking about buying it? Ask AI Advisor — compare fit, alternatives and trade-offs.
- Want to leave it? Find a replacement — see feature losses and migration risks.
Pricing
- Free: $0 per month; includes 500 credits, 1 session, Claude Code, Codex and OpenCode, base sandbox, live preview and terminal, GitHub import and export, and community support.
- Builder: $29 per month; includes 10 parallel sessions, all coding agents, standard sandbox, live preview and terminal, GitHub import and export, custom templates, BYOK, SDK/CLI/API access, and priority support.
- Teams: Starting at $99 per seat per month; includes unlimited sessions, all coding agents, standard sandbox, real-time collaboration, shared templates and secrets, activity dashboard, role-based access, spend controls, BYOK, SDK/CLI/API access, and priority support.
- Enterprise: Custom pricing; includes everything in Teams, self-hosted runtime, bring-your-own sandbox provider, environment templates, custom sandbox resources, dedicated infrastructure, compliance features, SSO/SAML/SCIM, and dedicated support engineer.
Features
- Multi‑agent coding runtime: Works with popular coding agents while Runtime supplies the environments, policies, and orchestration, so teams can swap models or tools without re‑plumbing everything.
- Sandboxed compute with snapshots: Spins up pre‑warmed VMs that mirror monorepos and microservices, with custom CLIs, APIs, and secrets baked in, so each session starts quickly and stays isolated from production.
- Background and interactive agents: Supports both interactive sessions and autonomous background agents that pick up tickets, issues, or Slack messages, write code, run tests, and return pull requests.
- Mission Control & observability: Central dashboard to monitor every agent session, including tool calls, chain of thought, file diffs, costs, and approval status, plus spend limits and allowlists.
- Deep SaaS and data integrations: Ships connectors for data warehouses, billing, HR, CRM, support, alerting, and engineering tools, and can call anything reachable via API, CLI, SDK, or MCP.
- Self‑hostable and open source pieces: Can run fully inside a company’s cloud with its own models and storage, backed by open source components for the CLI, API worker, and templates.
Use cases
- Platform & DevOps Teams: Centralizing agent infra, sandboxes, and policies so other departments can adopt agents safely.
- Engineering & Product Teams: Letting coding agents fix bugs, implement features, and turn PRDs into working prototypes.
- Customer Support & Success: Running support triage agents that read tickets, query data sources, and draft responses.
- Finance & Operations: Automating reconciliations, dashboards, and data pulls from billing and ERP systems.
- Design & Marketing Teams: Iterating on live pages, campaign copy, and assets using sandboxed agents pointed at web properties.
- Uncommon Use Cases: Used by internal audit and risk teams for continuous control checks; adopted by forward‑deployed engineering or professional services groups to deliver customer‑specific automations without one‑off scripts.