AI Dispatch
API & DataSubmit
agent · ai-coding-agents

CatDoes vs OpenCode

55 fields both were evaluated on, 28 of them different — including where one discloses something the other does not. Every value links to the document it came from. 27 further fields are disclosed by neither and are listed at the end rather than tabled.

Assurance

FieldCatDoesOpenCode
Audit trail·
“CatDoes Watch is our error monitoring solution that's built into every project. When you encounter any errors during development, or when you publish your app and your users encounter any errors or crashes, you can see them in your dashboard and ask the AI agents to fix it.”
catdoes.com · checked Aug 1, 2026
Explainability·
“An autonomous AI agent plans the work, writes the code, runs the tests, and ships the build.”
catdoes.com · checked Aug 1, 2026
Compliance certifications·
SOC 2 Type 1 and Type 2 compliant
“SOC 2 Type 2 Compliant SOC 2 Type 1 Compliant”
trust.opencode.ai · checked Sep 21, 2026

Agency

FieldCatDoesOpenCode
Autonomy level·
“An autonomous AI agent plans the work, writes the code, runs the tests, and ships the build.”
catdoes.com · checked Aug 1, 2026
Human oversight·
“Edit the code. Own the code. Open any file from the dashboard and edit it yourself.”
catdoes.com · checked Aug 1, 2026
Goal complexity·
“Describe what you need. An autonomous AI agent plans the work, writes the code, runs the tests, and ships the build.”
catdoes.com · checked Aug 1, 2026
Action space·
“An autonomous AI agent plans the work, writes the code, runs the tests, and ships the build.”
catdoes.com · checked Aug 1, 2026
Operating environment·
“The AI agent runs in the cloud on its own computer.”
catdoes.com · checked Aug 1, 2026
terminal, IDE, or desktop
“OpenCode is an open source agent that helps you write code in your terminal, IDE, or desktop.”
opencode.ai · checked Aug 7, 2026
Initiative·
“An autonomous AI agent plans the work, writes the code, runs the tests, and ships the build.”
catdoes.com · checked Aug 1, 2026

Safety

FieldCatDoesOpenCode
Red teaming·
Third-party penetration test conducted, report available in trust center
“Anomaly Penetration Test Report.pdf”
trust.opencode.ai · checked Sep 21, 2026
Incident reporting·
“CatDoes Watch is our error monitoring solution that's built into every project. When you encounter any errors during development, or when you publish your app and your users encounter any errors or crashes, you can see them in your dashboard and ask the AI agents to fix it.”
catdoes.com · checked Aug 1, 2026
Formal policy covers incident response and breach notification
“Incident Response & Breach Notification”
trust.opencode.ai · checked Sep 21, 2026
Data handling·
“Built for privacy first [*] OpenCode does not store any of your code or context data”
opencode.ai · checked Aug 7, 2026

Practicality

FieldCatDoesOpenCode
Pricing model·
Price point·
Availability·
Desktop app is offered as a beta download; no availability status is stated for the CLI
“Download the desktop beta now”
opencode.ai · checked Aug 7, 2026

Not in our latest capture. We captured this page again on Sep 23, 2026 and this quote was not there. How we re-check citations

Deployment options·
“The AI agent runs in the cloud on its own computer.”
catdoes.com · checked Aug 1, 2026
macOS, Windows, and Linux
“Available on macOS, Windows, and Linux . Download now”
opencode.ai · checked Aug 7, 2026

Not in our latest capture. We captured this page again on Sep 23, 2026 and this quote was not there. How we re-check citations

Integrations·
“GitHub integration lets you import an existing repo or export the full codebase any time.”
catdoes.com · checked Aug 1, 2026
Models.dev
“Any model 75+ LLM providers through Models.dev, including local models”
opencode.ai · checked Aug 7, 2026
Support model·

Foundation models

FieldCatDoesOpenCode
Base models·
Claude, GPT, Gemini
“connect any model from any provider, including Claude, GPT, Gemini and more.”
opencode.ai · checked Aug 7, 2026
Model provider·
any provider, including Claude, GPT, Gemini
“connect any model from any provider, including Claude, GPT, Gemini and more.”
opencode.ai · checked Aug 7, 2026
Model swappable·
“connect any model from any provider”
opencode.ai · checked Aug 7, 2026

Ecosystem

FieldCatDoesOpenCode
Protocols supported·
LSP
“LSP enabled Automatically loads the right LSPs for the LLM”
opencode.ai · checked Aug 7, 2026
Tool use·
“An autonomous AI agent plans the work, writes the code, runs the tests, and ships the build.”
catdoes.com · checked Aug 1, 2026
Multi-agent·
Start multiple agents in parallel on the same project
“Multi-session Start multiple agents in parallel on the same project”
opencode.ai · checked Aug 7, 2026
Open source·
open source
“OpenCode is an open source agent”
opencode.ai · checked Aug 7, 2026

Impact

FieldCatDoesOpenCode
User base·
“Real apps and websites, shipped by CatDoes users.”
catdoes.com · checked Aug 1, 2026
Reports 195,000 GitHub stars, 950 contributors and 13,000+ commits alongside 16M monthly developers. The repository counts are checkable on GitHub; the 16M developer figure is the vendor's own, with no counter named
“With over 195,000 GitHub stars, 950 contributors, and over 13,000 commits, OpenCode is used and trusted by over 16M developers every month.”
opencode.ai · checked Aug 7, 2026

Not in our latest capture. We captured this page again on Sep 23, 2026 and this quote was not there. How we re-check citations

Deployment scale·
Target sectors·
“Business Owners Designers Startup Founders People with Ideas”
catdoes.com · checked Aug 1, 2026

Disclosed by neither

Both CatDoes and OpenCode publish nothing on these 27 fields. That is a finding about the category rather than a difference between them, so it is recorded here instead of as 27 identical table rows. Each is shown with its source check on the individual profiles.

  • High-risk domains
  • Documented incidents
  • Supported regions
  • Open weights
  • Fine-tuning
  • Context window
  • API access
  • Marketplace presence
  • Safety evaluations
  • Safety policy
  • Usage restrictions
  • Model or system card
  • Third-party evaluations
  • Insurance available
  • Insurance carriers
  • Coverage limits
  • Indemnification
  • Liability cap
  • Tamper-evident log
  • Runtime governance
  • Permission scopes
  • Regulatory alignment
  • Outcome-based pricing
  • Settlement mechanism
  • Dispute process
  • SLA terms
  • Evaluation coverage

Questions

How do CatDoes and OpenCode compare on base models?
CatDoes: no public information disclosed. OpenCode: Claude, GPT, Gemini.
How do CatDoes and OpenCode compare on model provider?
CatDoes: no public information disclosed. OpenCode: any provider, including Claude, GPT, Gemini.
How do CatDoes and OpenCode compare on protocols supported?
CatDoes: no public information disclosed. OpenCode: LSP.
How do CatDoes and OpenCode compare on multi-agent?
CatDoes: no public information disclosed. OpenCode: Start multiple agents in parallel on the same project.
How do CatDoes and OpenCode compare on open source?
CatDoes: no public information disclosed. OpenCode: open source.
How do CatDoes and OpenCode compare on red teaming?
CatDoes: no public information disclosed. OpenCode: Third-party penetration test conducted, report available in trust center.