Skip to main content

Infrastructure for the
agentic era.

Orchestrate agents. Operate their environment. Automate their work. Deploy what they build.

Start Building
Give this to your coding agent

Everything agents need, in one composable stack.

Every agent feature maps to composable layers of the Rivet stack. Pick and choose what features you need to build production agents.

  1. Workflows

    What agents need

    How this layer solves it

    Write multi-step operations that survive restarts.

  2. Dynamic Apps

    What agents need

    How this layer solves it

    Deploy the backends your agents build.

Run your agent infrastructure where your data already lives.

  • Single Rust binary

    One process to install, monitor, and upgrade.

  • Kubernetes or systemd

    Deploy with the Enterprise Helm chart or a systemd unit.

  • Storage you control

    Use Postgres or FoundationDB for persistence and tiered storage to S3.

  • Local dev matches production

    Use the same binary, APIs, and control-plane behavior from laptop to production.

Complete observability.

Inspect every part of Rivet in the dashboard, or bring the same live context into your AI client with Rivet MCP.

Rivet dashboard

Inspect Actor state and SQLite data, agentOS sessions, workflow runs, and Dynamic App releases in one place.

Rivet MCP

Let Claude Code, Codex, Cursor, and other AI clients find Actors, call actions, and open the Inspector inline.

Rivet dashboard inspecting a project Actor built by an agent: live state with the build summary and each pipeline step's status, attempts, and timing

Start local. Deploy when ready.

Rivet Cloud

Deploy Actors on Rivet Cloud with managed infrastructure and persisted Actor data.

Open the dashboard

Self-Host

Run the open-source Rivet control plane as a Rust binary or container on your infrastructure.

Read self-hosting docs

Infrastructure for the agentic era.

Build with agents, build for agents, and run it where your data lives.