Sourced profile

OpenClawby OpenClaw Foundation (independent nonprofit, per repo README).

OpenClaw is an open-source assistant/gateway that runs on your own machine or server and connects chat apps to AI agents (repo README; docs.openclaw.ai).

Verified October 13, 2026

This profile was compiled by Beag Labs, which makes a competing product (Papyrus). It is built from public documentation, not hands-on testing, and every statement links to its source.

At a glance

Evidence coverage
7 / 8

attributes with a sourced answer, 2 only partially supported

Cited claims
7

records in the Claim Ledger

Documentation gaps
1

attributes not documented in sources checked

Deployment
  • Self-hosted
Licensing
  • Open source
Azure Marketplace
  • Not documented
Last verified
October 13, 2026

Profile, attribute by attribute.

What it does

Verified

Single Gateway links chat channels to AI agents with tools, sessions, memory, skills, cron/webhooks, a web Control UI, and mobile nodes.

Source: BL-CLM-40 ↗

Does not establish: Describes features, not their quality, scale, or reliability.

Deployment model

Verified

Runs on your own laptop or server; install via script, npm, Docker, Nix or source; remote access via SSH/Tailscale. README says no hosted service.

Source: BL-CLM-41 ↗

Does not establish: Does not cover third-party hosted or marketplace deployments of the software.

Azure Marketplace offer

Not documented

No official Azure/Microsoft Marketplace listing found in first-party pages. A web search surfaced third-party publisher listings (not fetched; unverified).

3 sources checked

Does not establish: Third-party publishers appear to list OpenClaw offers on Microsoft Marketplace; direct fetch returned 403, so offer type, affiliation and pricing are unverified. Failed search is not proof of absence.

Human approval

Partially supported

Exec approvals (deny, allowlist, ask, auto, full) gate host command execution only and can be switched off; not a general approval layer.

Source: BL-CLM-42 ↗

Does not establish: SECURITY.md says approvals are operator guardrails, not a multi-tenant authorization control. Covers host command execution, not every agent action.

Licensing

Verified

MIT License, copyright OpenClaw Foundation (2026).

Source: BL-CLM-43 ↗

Does not establish: Only the root LICENSE was read; subdirectories or plugins on ClawHub may carry other licenses. Not legal advice.

Security controls

Partially supported

Gateway auth, DM pairing and allowlists, optional sandboxing (off by default) and an audit CLI; documented as a single-trusted-operator model, not a multi-tenant boundary.

Source: BL-CLM-44 ↗

Does not establish: SECURITY.md states it is not a multi-tenant boundary and exec runs on host by default. SSO, RBAC and audit-log features were not found on pages read (not a statement they are absent). No certifications checked.

Intended buyer

Verified

Individuals wanting a personal assistant, teams sharing a gateway, and enterprise/security teams hardening via configuration, not a separate edition.

Source: BL-CLM-45 ↗

Does not establish: Project positioning only; no procurement or support terms stated.

Public pricing

Verified

README says no paid tier, hosted service, or token. Model API and hosting costs are borne by the user.

Source: BL-CLM-46 ↗

Does not establish: Says nothing about third-party managed offers, support contracts, or underlying model/hosting cost amounts.

May fit well when

May fit less well when

Methodology and disclosure

How these comparisons are built and checked.

We disclose our interest

Beag Labs makes Papyrus, one of the platforms compared here. Papyrus cells cite our own pages and are labelled first-party. Read every comparison with that in mind.

Every statement is cited

Each Verified or Not supported cell links to a record in the Claim Ledger with the source URL, where on the page it appears, the date we checked it, approved wording, and what it does not prove.

Documentation, not hands-on testing

These comparisons are built from vendor documentation, official listings and repositories. Beag Labs has not run hands-on tests of the compared products. We classify what is documented; we do not score or rank quality, and nothing here is a benchmark.

Missing documentation is not a missing feature

If we cannot find a capability in official sources we say Not documented and list what we checked. We only say Not supported or Partially supported when a source itself says so.

Verified
An official source we fetched states it. The cell links to the claim record.
Partially supported
An official source documents the capability but states a limit: one surface, a subset of actions, or an explicit exclusion. The cell says what the limit is.
Not documented
We checked official sources and found nothing either way. This is not evidence the capability is absent.
Not supported
An official source explicitly says the capability is absent or unsupported.