AI Dispatch
agent · personal assistant

ClawBox

Indexed12 or more fields evidenced; not yet scored by a human against the rubric

23 fields evidenced · 32 with no public information. Every value below links to the document it came from and the date we checked it.

23 of them are quoted but not yet interpreted: we hold the source sentence and the date we read it, but nobody has written the answer to the question yet. Those rows show the quote and say so rather than repeating it back as an answer. Why these exist

2 of those are flagged for review: our own check found language in the cited source that may address the field. An editor has not adjudicated them yet.

These scores are automated. A 1 or 2 counts how many fields this entry answers with a citation — not what those answers say. A 0 means every field for that dimension is recorded as undisclosed and none of the pages we captured mentions it. No one has scored this entry against the rubric yet.

Runtime governance
1/3 auto

Are scope, spend, and authority enforced while the agent runs?

Scored from 1 evidenced field(s): permission_scopes. Automated score; capped at 2 pending review.

Counts Permission scopes, each cited below.

Audit trail
unscored

Is there a tamper-evident record of what it actually did?

Compliance
unscored

Are compliance obligations attached per engagement?

Outcome settlement
unscored

Does payment depend on a verified result?

Insurance & indemnity
unscored

Can the deployment be insured, and is the customer indemnified?

Assurance

Insurance available
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Insurance carriers
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Coverage limits
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Indemnification
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Liability cap
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Audit trail
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Tamper-evident log
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Explainability
Ask something, it makes a plan, and it happens.
tryclawbox.com · checked Aug 1, 2026
Runtime governance
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Permission scopes
Define your OpenClaw’s personality, tone, expertise, and boundaries.
tryclawbox.com · checked Aug 1, 2026
Compliance certifications
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Regulatory alignment
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Outcome-based pricing
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Settlement mechanism
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Dispute process
Moneyback guarantee . No questions asked.
tryclawbox.com · checked Aug 1, 2026
SLA terms
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Evaluation coverage
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this

Agency

Autonomy level
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Human oversight
When it needs to log in somewhere, you step in directly — type your credentials yourself. OpenClaw hands off control and never sees what you enter.
tryclawbox.com · checked Aug 1, 2026
Goal complexity
Tell it what to do in plain language. It figures out the rest.
tryclawbox.com · checked Aug 1, 2026
Action space
It browses the web, sends emails, and runs tasks on a schedule.
tryclawbox.com · checked Aug 1, 2026
Operating environment
ClawBox deploys a private, secure OpenClaw instance on WhatsApp or Telegram. It browses the web, sends emails, and runs tasks on a schedule.
tryclawbox.com · checked Aug 1, 2026
Initiative
Set tasks to run on a schedule — every morning, every 30 minutes, every Friday. OpenClaw works while you don’t.
tryclawbox.com · checked Aug 1, 2026

Safety

Safety evaluations
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Red teaming
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Safety policy
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Usage restrictions
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Model or system card
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Incident reporting
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Third-party evaluations
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Data handling
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this

Practicality

Pricing model
Simple, transparent pricing No per-message charges, no overage fees, no surprises.
tryclawbox.com · checked Aug 1, 2026
Price point
$29/month for founders.
tryclawbox.com · checked Aug 1, 2026
Availability
Get OpenClaw deployed in 1 minute
tryclawbox.com · checked Aug 1, 2026
Deployment options
no public information

Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences

tryclawbox.com · checked Aug 1, 2026
Integrations
no public information

Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences

tryclawbox.com · checked Aug 1, 2026
Supported regions
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Support model
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this

Foundation models

Base models
Powered by Claude ChatGPT Gemini
tryclawbox.com · checked Aug 1, 2026
Model provider
Powered by Claude ChatGPT Gemini
tryclawbox.com · checked Aug 1, 2026
Model swappable
Running fully locally off MiniMax 2.1, doing all the tool parsing needed.
tryclawbox.com · checked Aug 1, 2026
Open weights
Built on OpenClaw · 189K+ GitHub stars
tryclawbox.com · checked Aug 1, 2026
Fine-tuning
Define your OpenClaw’s personality, tone, expertise, and boundaries. Make it sound like you. No code required.
tryclawbox.com · checked Aug 1, 2026
Context window
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this

Ecosystem

Protocols supported
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Tool use
OpenClaw created a skill on its own within Telegram chat.
tryclawbox.com · checked Aug 1, 2026
Multi-agent
Set it up with Obsidian notes and sub-agents.
tryclawbox.com · checked Aug 1, 2026
API access
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this
Open source
Built on OpenClaw · 189K+ GitHub stars
tryclawbox.com · checked Aug 1, 2026
Marketplace presence
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this

Impact

User base
189K+ GitHub stars. Thousands of daily users.
tryclawbox.com · checked Aug 1, 2026
Deployment scale
Thousands of daily users.
tryclawbox.com · checked Aug 1, 2026
Target sectors
Submitted health reimbursements, found doctor appointments, documents.
tryclawbox.com · checked Aug 1, 2026
High-risk domains
Submitted health reimbursements, found doctor appointments, documents.
tryclawbox.com · checked Aug 1, 2026
Documented incidents
no public information
tryclawbox.com · checked Aug 1, 2026 · source did not state this

Compared with

Side-by-side on the fields where ClawBox and the other entry are both on record and actually differ.