OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Infrastructure

Lightspeed

Lightspeed is open-source infrastructure for operating managed fleets of AI agents as durable workflows. Its Rust core runs on Temporal, stores production data in PostgreSQL with optional Amazon S3, and uses a TypeScript and React frontend.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Lightspeed — OpenViST project profile in Agent Infrastructure.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Lightspeed when agent execution needs persistence, orchestration, supervision, or extended operation rather than a short-lived single-agent interaction.

Who it is for

  • Teams building long-running autonomous-agent systems
  • Developers needing restart-resilient agent sessions
  • Organizations coordinating fleets of agents with attached VM or sandbox resources
  • Builders of assistants, software factories, operations agents, or research workflows

Documented uses

  • Run fleets of long-lived agents as durable workflows
  • Preserve agent context and session state across restarts
  • Attach operating-system resources only when an agent needs them
  • Coordinate sub-agents, bots, schedules, webhooks, and chat-driven work
  • Store durable workflow data in PostgreSQL with optional S3 support
Before you choose

Requirements & limits

The cited repository describes Lightspeed as open-source and is publicly visible. The documented source setup is self-hosted and requires the listed development dependencies and a model-provider API key.

  • The core runtime is written in Rust and runs on Temporal.
  • Agents can survive restarts and run for weeks or months according to the repository description.
  • Virtual filesystems provide persistent files without requiring an attached operating system.
  • VM or sandbox resources are attached to sessions when needed.
  • PostgreSQL is the production data store, with optional S3 support.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Lightspeed locally from source

Start the local Lightspeed product and prepare a first model-backed session.

Before you start

  • Rust toolchain selected by rust-toolchain.toml
  • Node.js 24 or newer
  • Docker with Compose
  • A native build toolchain with protoc
  • An API key for a supported model provider

Steps

  1. Run ./dev.sh from the repository root.

  2. Wait for the launcher’s readiness checks to pass, then open http://localhost:5173/app/.

  3. Sign in with the development account printed by the launcher.

  4. Select the Test universe, open Models → Add provider, connect an API key, choose a model, and start a session.

Expected outcome

A local Lightspeed instance is running with a configured model provider and a first session can be started.

Guide limitations

  • The documented setup is for local development from source.
  • The evidence does not provide a production deployment procedure.
  • The launcher’s defaults and settings may require the referenced environment-variable and local-development documentation for changes.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
LightspeedRun fleets of long-lived agents as durable workflowsSelf-hosted, ServerThe cited repository describes Lightspeed as open-source and is publicly visible. The documented source setup is self-hosted and requires the listed development dependencies and a model-provider API key.
Agentfm CoreRun a containerized agent in a Podman sandbox on a worker machineDesktop, Docker, Self-hostedThe README lists desktop installers for macOS and Linux; it says the Windows app is in progress. Its desktop quick start says the bundled node connects to the public mesh. The README notes that the v1 installers are unsigned and macOS may block the first launch.
PlanoRoute incoming requests to agents based on their declared roles.Self-hosted, ServerPlano is public source code under the Apache-2.0 license. The README describes hosted Plano models free of charge in the US-central region for a first-run developer experience; for production scale it points to running models locally or contacting the project for API keys.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
smartcomputer-ai/lightspeed · Official homepage title · retained in its source language
How we review sourcesSuggest a correction