AI DispatchJSON API
agent · Gaming

Voyager

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

13 fields evidenced · 42 with no public information. Every value below links to the document it came from and the date we checked it.

These scores are automated. They measure how many fields this entry answers with a citation — not what those answers say. No one has scored this entry against the rubric yet.

Runtime governance
unscored

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

Audit trail
2/3 auto

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

Scored from 2 evidenced field(s): audit_trail, explainability. Automated score; capped at 2 pending review.

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
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Insurance carriers
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Coverage limits
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Indemnification
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Liability cap
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Audit trail
Yes (feedback, errors, and self-verification logged implicitly)
iterative prompting mechanism that incorporates environment feedback, execution errors, and self-verification for program improvement
voyager.minedojo.org · checked Aug 1, 2026
Tamper-evident log
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Explainability
Yes (skills are interpretable and compositional code)
skills developed by Voyager are temporally extended, interpretable, and compositional
voyager.minedojo.org · checked Aug 1, 2026
Runtime governance
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Permission scopes
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Compliance certifications
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Regulatory alignment
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Outcome-based pricing
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Settlement mechanism
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Dispute process
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
SLA terms
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Evaluation coverage
Yes (evaluated against multiple baselines)
We systematically evaluate Voyager and baselines on their exploration performance, tech tree mastery, map coverage, and zero-shot generalization capability to novel tasks in a new world.
voyager.minedojo.org · checked Aug 1, 2026

Agency

Autonomy level
5 (acts unsupervised)
Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention.
voyager.minedojo.org · checked Aug 1, 2026
Human oversight
No human oversight required
without human intervention
voyager.minedojo.org · checked Aug 1, 2026
Goal complexity
open-ended
open-ended
voyager.minedojo.org · checked Aug 1, 2026
Action space
execute
We opt to use code as the action space instead of low-level motor commands because programs can naturally represent temporally extended and compositional actions
voyager.minedojo.org · checked Aug 1, 2026
Operating environment
game environment (Minecraft)
in Minecraft
voyager.minedojo.org · checked Aug 1, 2026
Initiative
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this

Safety

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

Practicality

Pricing model
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Price point
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Availability
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Deployment options
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Integrations
GPT-4
interacts with GPT-4 via blackbox queries
voyager.minedojo.org · checked Aug 1, 2026
Supported regions
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Support model
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this

Foundation models

Base models
GPT-4
GPT-4
voyager.minedojo.org · checked Aug 1, 2026
Model provider
OpenAI
interacts with GPT-4 via blackbox queries
voyager.minedojo.org · checked Aug 1, 2026
Model swappable
No (only GPT-4 used via blackbox API)
We opt to use code as the action space instead of low-level motor commands because programs can naturally represent temporally extended and compositional actions, which are essential for many long-horizon tasks in Minecraft. Voyager interacts with a blackbox LLM (GPT-4) through prompting and in-context learning. Our approach bypasses the need for model parameter access and explicit gradient-based training or finetuning.
voyager.minedojo.org · checked Aug 1, 2026
Open weights
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Fine-tuning
Not supported
bypasses the need for model parameter fine-tuning
voyager.minedojo.org · checked Aug 1, 2026
Context window
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this

Ecosystem

Protocols supported
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Tool use
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Multi-agent
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
API access
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Open source
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Marketplace presence
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this

Impact

User base
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Deployment scale
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Target sectors
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
High-risk domains
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this
Documented incidents
no public information
voyager.minedojo.org · checked Aug 1, 2026 · source did not state this