mrkeyoor.comAsk

elie222/rakazotested 17 Oct 2026commit e55263f

rakazo review

Rakazo merits a disposable trial for operators who need persistent bots and can manage the supporting services.

  • Install 42 s
  • Build 21 s
8,605/8,887passed, run exited non-zero
  • 1,862 packages
AI Toolsevaluationupdated 01 Nov 2026
+796stars / 7d

Consider Rakazo for a bounded trial if you need persistent AI bots and can operate their database, storage and computer providers. Rakazo is an open source, self-hosted AI assistant with persistent bots, conversations, memory and computer access. Its README labels it beta. Our run on 2026-10-17 at commit e55263f installed and built the source, but did not verify a working assistant deployment.

Verdict

Rakazo merits a disposable trial for operators who need persistent bots and can manage the supporting services. Our source build succeeded, while the test command exited 1 and the stored parser summary recorded 26 failures. Resolve the named suite failures in your environment, keep workloads requiring isolation on separate computers, and verify independent backup restoration before relying on it. Our run did not verify a working assistant deployment.

We ran it

Lab card: what happened when we ran rakazo
Lab card from our sandbox run
Screenshot of rakazo (rakazo.com)
rakazo.com
Install✓ · 42s1862 packages · 1841 MB
Build✓ · 21s
Tests✗ · 332s8605 passed · 26 failed · 256 skipped of 8887 (vitest)
Repo2215 files~419,920 lines of source · 35.6 MB · 12 CI workflows

Answers from our run

Does rakazo build from source?

Dependencies installed in 42 seconds (1862 packages), and the build succeeded in 21 seconds. We cloned commit e55263f into a clean Debian container with 3 CPUs and no project-specific setup.

Do rakazo's tests pass?

No. The project's own test command finished in 332 seconds and reported 8605 passed, 26 failed, 256 skipped (vitest).

Who should not use rakazo?

Teams expecting bot folders or separate browser profiles to isolate mutually untrusted workloads.

What are the alternatives to rakazo?

Hermes Agent, OpenClaw. Rakazo merits a disposable trial for operators who need persistent bots and can manage the supporting services.

Setup3/5Our source checkout installed in 42 s and built in 21 s, a heavy install of 1,862 dependencies, and we did not run a README task.Editor’s note: Source installation and build were measured, but a complete deployment with model access and a working computer was not verified.
Docs4/5The README has an install section (“Quick start”) and usage in the same section; we did not run its quickstart ourselves.Editor’s note: The supplied README and runtime extracts explain operating requirements, but their instructions were not verified against a complete running deployment.
Community4/5Last push on 2026-10-19 and 8,420 stars.Editor’s note: Repository push metadata and one issue report do not establish support quality, response times, or issue-resolution outcomes.
Maturity1/5Latest release v0.2.0 on 2026-10-10 (pre-1.0), repository created 2026-08-13 and its test suite did not pass in our sandbox (8,605 of 8,887 passed).Editor’s note: The measured suite had 26 failures with no underlying exceptions supplied. Long-running operation, access boundaries, and recovery were not verified.

How we score

Who it’s for

Technical operators who need bots to retain files and browser state between tasks.
Developers prepared to configure PostgreSQL, independent secrets, model access and a computer provider.
Teams able to put workloads requiring isolation on separate computers.

Who it’s NOT for

Teams expecting bot folders or separate browser profiles to isolate mutually untrusted workloads.
Operators expecting workspace checkpoints to provide historical backups.
Projects requiring a clean test result before evaluation: our stored test command exited 1.
People seeking a deployment already verified with live model calls, desktop control and recovery. Our run did not establish those outcomes.

Setup reality

Our run on 2026-10-17 tested Rakazo commit e55263f in our sandbox using pnpm. Installation succeeded in 42 seconds and build succeeded in 21 seconds; the test command exited 1 after 332 seconds. The harness records command success, exit code, elapsed time, timeout status and parsed test counts separately.

The attached stored parser summaries record 8,605 passed, 26 failed and 256 skipped out of 8,887. These summaries do not establish exhaustive unique test coverage; no new execution or complete-log reconciliation was performed. The raw tail names the failing suites but does not supply their underlying exceptions.

The run recorded 1,862 dependencies and 1,841 MB on disk, with 3 CPUs, 8 GB RAM and image label lab-node:22. The installation log identifies Node.js 22.23.2 on Linux x64 and a pnpm 9.15.0 path. No audit result or scan coverage is recorded.

The README pinned to the measured commit documents Node.js, pnpm 9, Docker, PostgreSQL configuration and independent secrets for source development. Its published-image installer is a separate route that our run did not test. Neither successful command exits nor the parsed test counts establish live model access, working desktop control, unattended operation or workspace recovery.

Should you trial Rakazo?

Trial Rakazo when retaining a bot's working files and browser state is worth operating a database and computer service. Postpone adoption if you need verified deployment or recovery results before connecting important accounts. Our run on 2026-10-17 at commit e55263f installed and built the source, but did not verify a working assistant deployment.

The README at our measured commit describes persistent bots with conversations, memory, routines and history, plus browser, terminal, file and graphical desktop access. Web, Electron and mobile applications connect to the same API. These are documented capabilities, not completed workloads from our sandbox.

What our sandbox established

Installation succeeded in 42 seconds and build succeeded in 21 seconds; the test command exited 1 after 332 seconds. Our harness stores each command's outcome, exit code, elapsed time and timeout status separately from its parsed test counts. None of these steps timed out.

The attached stored parser summaries record 8,605 passed, 26 failed and 256 skipped out of 8,887. Treat those figures as recorded parser summaries, not a verified count of exhaustive unique tests. No new execution or complete-log reconciliation was performed for this correction.

The raw tail identifies failures in packages/testkit/src/playwright-artifact-publication.test.ts and .agents/skills/pr-watch/pr-digest.test.ts. Those suite labels locate the reported failures; they do not reveal their causes. The supplied tail omits the underlying exceptions, so it cannot establish whether the failures came from product behavior, fixtures or sandbox conditions.

The tail also marks PostgreSQL-related cases, computer-use acceptance, Docker replay and Team desktop cases as skipped. Skipped cases are not failures, and they provide no evidence that those integrations worked. Our run did not establish live model calls, desktop control or recovery.

The sandbox recorded 1,862 dependencies and 1,841 MB on disk. Its installation log identifies Node.js 22.23.2 on Linux x64; the image label alone would not establish that runtime. No audit result is attached, and scan coverage is unknown.

The MrKeyoor testing methodology explains how command outcomes and parsed counts reach a review. That page provides provenance context; its current procedure does not prove which methodology version governed this October run or expand what the stored record tested.

Choose the installation route deliberately

The pinned README documents two routes. Published images require Docker Engine, the Compose plugin, curl and OpenSSL, without a source checkout or Node installation. Source development requires a supported Node.js version, pnpm 9 and Docker, followed by database configuration and independent authentication, encryption, screen-proxy and sandbox-supervisor secrets.

Our measurements cover source installation, build and tests. They provide no installation timing or deployment result for the published images. A successful source build also does not confirm that the computer image was built or that onboarding reached a working bot.

Use the instructions for the revision you intend to deploy. The pinned README configures a PostgreSQL password and matching database URL; the current README documents separate application and migration credentials. Mixing those instructions would obscure which setup you are evaluating.

Separate computers provide the isolation boundary

Rakazo Team bot folders do not isolate workloads. The current runtime documentation says every Team bot can access the full Team workspace. Separate starting directories and persistent Chrome profiles organize work and browser state, while the bots share the computer's OS user and access.

For workloads requiring isolation, the documentation directs operators to use separate computers. Screen leases coordinate tool calls; they do not isolate mutually untrusted processes. This is a documented operating constraint, not a security boundary we tested at e55263f.

Checkpoints do not replace historical backups

Rakazo's documented local workspace store keeps the latest copy rather than an immutable revision archive. Replacement machines import the latest stored workspace, including portable browser state. That can support continuity after replacement, but it does not provide an earlier version after an unwanted edit or deletion.

The runtime documentation requires a persistent volume, encryption at rest and off-host backups for deployments using that local store. It also distinguishes the portable workspace from a disk snapshot: system packages installed outside the workspace do not move to another provider.

Before relying on persistence, create a disposable file and browser session, replace the computer through your intended lifecycle, and inspect what returns. Separately test restoring an earlier file from your independent backup. These are recommended adoption checks; our sandbox did not complete them.

Alternatives depend on how you want to work

Hermes Agent documents a terminal interface and messaging access through a single gateway process. Its README makes it a relevant alternative when terminal work and messaging are your main entry points. That establishes a reason to shortlist it, not a performance or reliability advantage over Rakazo.

OpenClaw connects its Control UI, CLI, TUI and messaging channels through a Gateway. Its README also describes companion apps and nodes for device capabilities. Consider it when access through existing chat services drives your choice.

These are alternative assistants to evaluate for those workflows, not required Rakazo components. The supplied extracts do not establish equivalent workspace recovery behavior, and we have no comparative deployment results.

How to read the assessment

Setup ease, documentation, community and maturity remain unassessed. Source command results do not establish complete setup ease; documentation extracts do not establish that their instructions produce a working deployment. Repository activity alone cannot establish support quality, and this run does not establish sustained operation or recovery. An unassessed dimension carries no numerical rating.

Alternatives

ProjectWhat it isPick it when
Hermes Agent gh↗An AI agent with a terminal interface and messaging access through a gateway process.Shortlist Hermes Agent when terminal work and messaging are your main entry points. Its README supports that workflow; no comparative deployment or reliability result was supplied.
OpenClaw gh↗An AI assistant whose Gateway connects control interfaces and messaging channels.Shortlist OpenClaw when access through existing chat services and companion devices drives your choice. Its README documents those connections; equivalent recovery behavior was not established.

What people are saying

  1. [github-trending] elie222/rakazo

Sources

  1. Rakazo README
  2. Rakazo computer runtime and persistence
  3. Rakazo repository metadata
  4. Docker Team Computer report, issue 1527
  5. Hermes Agent README
  6. OpenClaw README

More ai tools reviews