Golem Cloud

Agent-native platform for building AI agents and distributed apps with durable execution and no infrastructure management.

Source repo
golemcloud/golem
Stars
★ 1.5k
Last updated
today
License
NOASSERTION
Primary language
Rust

At a glance

How it runs
Hosted serviceSelf-hosted serviceFramework
Works with
Platform-specific
Cost
Free tier plus a paid hosted plan
Setup effort
High · needs real infrastructure
You'll need
WebAssembly runtimeGolem CloudShell / CLINetwork access
Typical use
Developers building AI agents that must survive crashes and continue from where they left off.
Not a fit if
  • Teams that need fully local operation without Golem Cloud
  • Developers building simple single-machine apps without distributed infrastructure
  • Teams unwilling to set up WebAssembly toolchains and multiple local services

What does this agent do, and when should you use it?

Golem Cloud is a platform for AI agents and distributed applications, built around the WebAssembly component model. Its core services let developers write components in Rust, TypeScript, Scala, or MoonBit and run them in a distributed cloud environment. The platform guarantees that state is never lost and work is never duplicated, providing durable execution and fault tolerance. The open-source repository contains the implementation, but deployment typically relies on the Golem Cloud service; local development and contribution are documented in CONTRIBUTING.md and the docs folder. The README points to learn.golem.cloud for getting started and golem.cloud for the managed service.

It runs WebAssembly components that encapsulate the logic of AI agents or distributed applications. The end-to-end flow: developers write components in Rust, TypeScript, Scala, or MoonBit, compile to WASM components, and deploy them to the Golem Cloud environment (or a self-hosted set of services). The platform ensures execution state is persisted, tasks are not repeated, and failures are handled. No infrastructure setup is needed; deployment is via Golem Cloud, and the developer docs are at learn.golem.cloud.

  1. Developers building AI agents that must survive crashes and continue from where they left off.
  2. Teams needing reliable distributed workflows without managing servers.
  3. Engineers already using Rust, TypeScript, Scala, or MoonBit who want to deploy to a scalable cloud runtime.
  4. Projects requiring durable execution with exactly-once semantics for business-critical tasks.
  5. Organizations seeking a path from single-node to distributed computing with minimal code changes.

How do you install or deploy this agent?

The repository is the source code for Golem services; there is no standalone installer. To use Golem Cloud, sign up at https://golem.cloud and follow the quickstart at https://learn.golem.cloud. For local development, you need a WebAssembly toolchain and the appropriate language compiler (e.g., Rust with wasm32-wasi target). See CONTRIBUTING.md for building the services locally.

How do you use this agent?

After signing up at golem.cloud, follow the documentation at learn.golem.cloud to create your first agent or distributed app. Typically you will initialize a project, write your component code, and deploy using the Golem CLI or the Golem Cloud console. The exact commands are provided in the official quickstart guides.

What are this agent's strengths and limitations?

Pros
  • Durable execution ensures state survives crashes and failures.
  • Supports multiple languages (Rust, TypeScript, Scala, MoonBit) with a portable WebAssembly component model.
  • Built-in distributed computing and fault tolerance reduce infrastructure burden.
  • Open source, allowing self-hosting and community contributions.
Limitations
  • Core runtime depends on Golem Cloud, introducing potential vendor lock-in.
  • Local setup is complex, requiring WebAssembly toolchains and multiple services.
  • No pre-packaged demo or single-command local run; you must consult external docs.
  • Architecture may be overkill for simple, non-distributed applications.

How does this agent compare with similar options?

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
Golem Cloud This agent 0 · Major gaps Hosted serviceFreemium ★ 1.5k today Rust —
FlowCraft 77 · Good CLIFree + model costs ★ 416 3d ago Go OpenAI API · Claude API
Chidori 60 · Some gaps CLIFree + model costs ★ 1.4k 1mo ago Rust OpenAI API · Claude API
Code Puppy 57 · Major gaps CLIFree + model costs ★ 869 today Python Codex · OpenAI API · Claude API

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Major gaps
0/ 100 5-point scale 0.0 / 5
Trust 0/29
Reliability 0/14
Adaptability 0/18
Convention 0/18
Effectiveness 0/13
Verifiability 0/8
Why each dimension lost points
Trust0 / 29 · 0.0/5

Insufficient evidence: no explicit documentation of permission model, user confirmation, data flow transparency, sensitive data handling, dependency security, external effects control, rollback, or source attribution. Hence all trust criteria scored 0.

Reliability0 / 14 · 0.0/5

Insufficient evidence: no explicit documentation of self-consistency, dependency availability, or failure messages. Hence all reliability criteria scored 0.

Adaptability0 / 18 · 0.0/5

Insufficient evidence: no explicit documentation of target audience, capability boundaries, trigger precision, or environment fit. Hence all adaptability criteria scored 0.

Convention0 / 18 · 0.0/5

Insufficient evidence: no explicit documentation of information architecture, installation notes, naming stability, examples/FAQ, known limitations, license, versioning/changelog, or maintenance responsibility. Hence all convention criteria scored 0.

Effectiveness0 / 13 · 0.0/5

Insufficient evidence: no explicit documentation of output usability, marginal value, or cost-benefit. Hence all effectiveness criteria scored 0.

Verifiability0 / 8 · 0.0/5

Insufficient evidence: no explicit documentation of claim traceability, cross-source corroboration, or fact-inference separation. Hence all verifiability criteria scored 0.

Risks and how to mitigate them
  • Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
  • Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
  • Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
  • Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
  • Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
  • Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
  • Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
  • Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
  • The repository is large, but the provided files are insufficient to assess its safety, reliability, or usability as an Agent product.
  • The license is BUSL-1.1, not an open-source license, which may restrict certain use cases.
  • Publisher identity is unverified; caution is advised.
Evidence confidence: Low Reviewed Aug 11, 2026 Reviewed revision d58af9c40ce8 New commits since this review; the score may not cover them
See the full review method →

Recent releases

Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.

  1. v1.6.0-rc3 Pre-release
    Release notes excerpt
    What's Changed * git-tool fixes by @Aditya1404Sal in https://github.com/golemcloud/golem/pull/4087 * Skip unused Scala and MoonBit setup in CLI CI jobs by @vigoo in https://github.com/golemcloud/golem/pull/4108 * Remove unnecessary worker executor test hooks by @vigoo in https://github.com/golemcloud/golem/pull/4110 * Read pending card events at the card event boundary from the agent status by @vigoo in https://github.com/golemcloud/golem/pull/4111 * Fix local external durable stream transport by @vigoo in https://github.com/golemcloud/golem/pull/4089 …
    View on GitHub ↗

FAQ

Is Golem Cloud free or is there a trial?
The repository does not mention pricing; check golem.cloud for current plans.
Can I run Golem on my own infrastructure?
Yes, the source is open, but the docs emphasize the managed Golem Cloud platform; self-hosting requires deeper setup and may not have full feature parity.
What language do I need to know?
You need to be comfortable with at least one of: Rust, TypeScript, Scala, or MoonBit.
How does Golem handle failures?
Golem is designed to provide durable execution in a distributed environment, ensuring state is never lost; the exact mechanisms are documented in the official docs.
View on GitHub ↗ Install ↓

Related agents