mrkeyoor.comAsk

zeroclaw-labs/zeroclawtested 13 Oct 2026commit f12da74

zeroclaw review

ZeroClaw merits a constrained trial for experienced self-hosters who need messaging and local actions under an explicit permission policy.

  • Install 30 s
  • Build 494 s
1,786/1,788passed, run exited non-zero
  • 518 packages
Automationevaluationupdated 25 Oct 2026
+180stars / 7d

ZeroClaw is a personal AI assistant runtime that connects model providers to messaging channels and local tools. It runs on your machine and documents approval controls for actions and recurring procedures.

Verdict

ZeroClaw merits a constrained trial for experienced self-hosters who need messaging and local actions under an explicit permission policy. The sandbox build succeeded, but verification remained incomplete. Pin the intended version, investigate the test failures and validate the chosen integration before relying on unattended operation.

We ran it

Lab card: what happened when we ran zeroclaw
Lab card from our sandbox run
Screenshot of zeroclaw (www.zeroclaw.com)
www.zeroclaw.com
Install✓ · 30s518 packages
Build✓ · 494s
Tests✗ · 736s1786 passed · 2 failed of 1788 (cargo test)
Repo2192 files~1,359,729 lines of source · 102.1 MB · 31 CI workflows · Dockerfile · tests dir

Answers from our run

Does zeroclaw build from source?

Dependencies installed in 30 seconds (518 packages), and the build succeeded in 494 seconds. We cloned commit f12da74 into a clean Debian container with 3 CPUs and no project-specific setup.

Do zeroclaw's tests pass?

No. The project's own test command finished in 736 seconds and reported 1786 passed, 2 failed (cargo test).

Who should not use zeroclaw?

People who only need model chat and do not want to operate an assistant runtime.

What are the alternatives to zeroclaw?

OpenClaw, Ollama. ZeroClaw merits a constrained trial for experienced self-hosters who need messaging and local actions under an explicit permission policy.

Setup3/5Our source checkout installed in 30 s and built in 494 s, a heavy install of 518 dependencies, and we did not run a README task.Editor’s note: The sandbox recorded installation and building, but supported-platform onboarding and connected-account setup were not reproduced.
Docs4/5The README has an install section (“Install”) and a usage section (“Quick start”); we did not run its quickstart ourselves.Editor’s note: The supplied README and release extracts support this review, but the linked setup guides were not reproduced or assessed for completeness.
Community5/5Last push on 2026-10-25 and 33,364 stars.Editor’s note: The supplied repository activity does not establish response quality, support outcomes or the experience of getting operational help.
Maturity2/5Latest release v0.8.6 on 2026-10-18 (pre-1.0), repository created 2026-02-13 and its test suite did not pass in our sandbox (1,786 of 1,788 passed).Editor’s note: One sandbox run and upstream release statements do not establish unattended reliability or long-term upgrade behavior.

How we score

Discussed on

  1. hnZeroClaw - Zero overhead. Zero compromise. 100% Rust.6 points

Who it’s for

Experienced self-hosters connecting a personal assistant to messaging accounts and local tools.
Operators who want provider choice and can configure agents and risk profiles.
Developers connecting custom MCP servers or event-triggered procedures.

Who it’s NOT for

People who only need model chat and do not want to operate an assistant runtime.
Operators who need this review to establish live messaging reliability: the sandbox measurements cover installation, building and tests, not connected accounts.
Operators expecting YOLO mode to retain the normal safety gates: the README describes it as skipping those gates for development boxes.

Setup reality

The October 13, 2026 sandbox installed commit f12da74 in 30 seconds with 518 dependencies and built it in 494 seconds. Tests failed after 736 seconds: 1,786 passed and 2 failed out of 1,788. The supplied log identifies one failure involving an unavailable jq command; it does not identify the other.

The README describes a TOML configuration with a provider entry, an agent that references it and a risk profile. Useful messaging operation also requires configuring the chosen channel. Quickstart writes an initial configuration, and service commands support continuous operation.

The sandbox configuration recorded 3 CPUs, 12 GB RAM and image lab-rust:1. The image label does not establish actual runtime or operating-system versions. Platform integrations were not validated by this build.

A successful build leaves an operating decision

ZeroClaw is worth a constrained trial if you want a personal assistant that connects messaging channels to local actions and can maintain its configuration and permissions. The supplied sandbox run reached a successful source build, but the test command failed. It did not establish that a connected assistant could work reliably unattended.

The README describes a single Rust binary with model providers, messaging channels, memory and tools, including shell, browser and custom MCP servers. That combination gives an experienced self-hoster a reason to investigate it. Someone who only needs model chat has less reason to take on the channel and action configuration.

What happened when we ran it

The October 13, 2026 sandbox installed ZeroClaw commit f12da74 in 30 seconds, recorded 518 dependencies and built it successfully in 494 seconds. The sandbox configuration had 3 CPUs and 12 GB RAM, with image lab-rust:1. That label does not establish the actual Rust or operating-system version. The checkout occupied 102.1 MB across 2,192 files, with about 1,359,729 source lines recorded by the lab.

Cargo tests failed with exit 101 after 736 seconds: 1,786 passed and 2 failed out of 1,788. The supplied log names release_workflow::scoop_publisher_metadata_follows_canonical_url_template and shows the Scoop metadata script calling jq when that command was unavailable. The excerpt does not identify the other failure. Missing jq therefore explains a documented failure path, not the entire aggregate result.

These measurements establish a successful build and a failed test run in that sandbox. They do not measure messaging reliability, model quality or unattended operation. The tested commit also predates release v0.8.6; the run does not validate that release.

Approvals need configuration and verification

The README says supervised autonomy is the default: medium-risk operations need approval and high-risk operations are blocked. It also documents workspace boundaries, command policy and operating-system sandbox options. These are documented controls, not security properties demonstrated by the sandbox build.

The README describes YOLO mode as skipping safety gates for development boxes. It also describes event-triggered Standard Operating Procedures with approval gates and resumable runs. For a trial, choose a task with limited access and check that its approval behavior matches your intended policy before allowing it to act on valuable files.

Quickstart begins the setup

The README places the main configuration at ~/.zeroclaw/config.toml. Its V3 configuration requires at least four section headers covering a provider entry, an agent that references it and a risk profile. Quickstart selects a provider and writes an initial configuration; channel configuration and credentials depend on the integration you choose.

The documented service commands support running the assistant continuously. Before doing that, check model access, the selected channel and the agent's permissions on the target machine. The README links platform setup guides, but this review did not reproduce those instructions or validate hardware and operating-system sandbox integrations.

What v0.8.6 establishes about plugins

Release v0.8.6, published October 18, 2026, describes a WebAssembly plugin host in seven 64-bit CLI release archives for Linux, macOS and Windows. The release notes say Discord passed an end-to-end acceptance run from release-candidate CLI archives on Linux, Windows and macOS.

That is upstream acceptance evidence for the stated Discord run. It does not establish equivalent results for every channel package or for your account. The notes separately say native compatibility adapters remain compiled in and plugin activation, trust and grants remain explicit. A channel name alone therefore does not tell you whether a deployment uses a plugin package or a native adapter.

Choose the integration you intend to deploy and verify message delivery, approvals and recovery yourself. Those are proposed acceptance checks, not additional tests performed for this review.

Choose the amount of assistant software you need

OpenClaw provides a personal assistant with messaging channels and native device apps. Consider OpenClaw when its device companions are your reason for adopting an assistant. Its README documents those capabilities; this review did not compare their operation with ZeroClaw.

Ollama has a REST API for running and managing models. Consider Ollama when model access is the whole requirement. ZeroClaw also documents Ollama as a provider, so the two can serve different parts of the same setup.

For a ZeroClaw trial, pin the intended version and start with one channel and limited tool permissions. Investigate the failed verification before relying on unattended work.

Alternatives

ProjectWhat it isPick it when
OpenClaw gh↗A personal assistant with messaging channels and native device apps.Consider it when its device companions are your reason for adopting an assistant; their operation was not compared in this review.
Ollama gh↗A model runtime with a REST API for running and managing models.Consider it when model access is the whole requirement; ZeroClaw also documents it as a provider.

Sources

  1. ZeroClaw README
  2. ZeroClaw release v0.8.6
  3. OpenClaw README
  4. Ollama README

More automation reviews