AI Dispatch
agent · coding assistant

Project Oscar

ThinFewer than 12 fields evidenced — this vendor discloses little, or we have read little of it

9 fields evidenced · 46 with no public information. Every value below links to the document it came from and the date we checked it.

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.

Runtime governance
0/3

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

No public evidence found. The page checked describes an experimental contributor-assistance prototype and publishes no enforced run-time limit on scope, spend, or authority.

How this gap gets closed →
Audit trail
0/3

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

No public evidence found. The page checked describes indexing and analysis of issues, CLs and discussions, but no tamper-evident or customer-reviewable record of the agent's own actions.

How this gap gets closed →
Compliance
0/3

Are compliance obligations attached per engagement?

No public evidence found. The page checked names no certification, auditor, or regulatory framework.

How this gap gets closed →
Outcome settlement
0/3

Does payment depend on a verified result?

No public evidence found of payment linked to a verified outcome. The page describes a non-commercial open-source project ("Oscar is very much an experiment"); no payment is taken.

How this gap gets closed →
Insurance & indemnity
0/3

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

No public evidence found. The page checked names no carrier, cover, limit, or customer indemnity.

How this gap gets closed →

Assurance

Insurance available
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Insurance carriers
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Coverage limits
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Indemnification
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Liability cap
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Audit trail
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Tamper-evident log
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Explainability
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Runtime governance
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Permission scopes
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Compliance certifications
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Regulatory alignment
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Outcome-based pricing
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Settlement mechanism
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Dispute process
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
SLA terms
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Evaluation coverage
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this

Agency

Autonomy level
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Human oversight
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Goal complexity
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Action space
read, write
Indexing and surfacing related project context during contributor interactions. Using natural language to control deterministic tools. Analyzing issue reports, CLs/PRs and group discussions, to help improve them in real time during or shortly after submission, and to label and route them appropriately.
go.googlesource.com · checked Aug 3, 2026
Operating environment
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Initiative
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this

Safety

Safety evaluations
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Red teaming
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Safety policy
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Usage restrictions
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Model or system card
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Incident reporting
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Third-party evaluations
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Data handling
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this

Practicality

Pricing model
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Price point
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Availability
research preview
Oscar is very much an experiment. We don't know yet where it will go or what we will learn.
go.googlesource.com · checked Aug 3, 2026
Deployment options
SaaS, local
Our current prototype runs on GCP Cloud Run using Google’s Gemini LLM, with Google Cloud Firestore serving as both the key-value storage and vector database. However, as demonstrated in our initial proof-of-concept, Gaby can also function on local workstation using Pebble and an in-memory vector database.
go.googlesource.com · checked Aug 3, 2026
Integrations
GitHub, go.dev, Gerrit, Google Groups
Gaby indexes content from various sources: Go issues: GitHub issues for the Go projects. Go documentation: Official documentation on go.dev . Code reviews: Reviews from Gerrit . Discussions: discussions for the Go project and golang-nuts Google Group.
go.googlesource.com · checked Aug 3, 2026
Supported regions
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Support model
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this

Foundation models

Base models
Gemini LLM
Our current prototype runs on GCP Cloud Run using Google’s Gemini LLM
go.googlesource.com · checked Aug 3, 2026
Model provider
Google
Our current prototype runs on GCP Cloud Run using Google’s Gemini LLM
go.googlesource.com · checked Aug 3, 2026
Model swappable
yes
Gaby‘s structure makes it easy to run on any kind of hosting service, using any LLM, any storage layer, and any vector database.
go.googlesource.com · checked Aug 3, 2026
Open weights
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Fine-tuning
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Context window
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this

Ecosystem

Protocols supported
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Tool use
natural language to control deterministic tools
Using natural language to control deterministic tools.
go.googlesource.com · checked Aug 3, 2026
Multi-agent
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
API access
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

go.googlesource.com · checked Aug 3, 2026
Open source
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

go.googlesource.com · checked Aug 3, 2026
Marketplace presence
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this

Impact

User base
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Deployment scale
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Target sectors
open-source software development
Oscar is a project aiming to improve open-source software development
go.googlesource.com · checked Aug 3, 2026
High-risk domains
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this
Documented incidents
no public information
go.googlesource.com · checked Aug 3, 2026 · source did not state this

Compared with

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