AgentSidekick

open-code-review vs gentle-ai

open-code-review is an agent skill from alibaba (Apache-2.0 licence, 55k GitHub stars, last push 2026-11-21); gentle-ai is an agent skill from Gentleman-Programming (MIT licence, 9.4k GitHub stars, last push 2026-11-21). They share 1 of 2 capabilities and integrations identified for either (overlap 0.50); only gentle-ai covers Agent Memory. Figures as of 2026-11-21. DER

open-code-review profilegentle-ai profileOpen in the compare tool

Side-by-side facts

5 of 16 rows differ (marked). Unknown means no source we track states it.

Fieldopen-code-reviewgentle-ai
TypeAgent skill · skill-md SRCAgent skill · skill-md SRC
Publisher · differsalibaba SRCGentleman-Programming SRC
Licence · differsApache-2.0 SRCMIT SRC
Open sourceYes DERYes DER
Pricing modelUnknownUnknown
HostingUnknownUnknown
Latest versionUnknownUnknown
Languagesgo SRCgo SRC
GitHub stars · differs55k (54,922) SRC9.4k (9,446) SRC
Forks · differs4.5k SRC904 SRC
Last push2026-11-21 SRC2026-11-21 SRC
ArchivedNo SRCNo SRC
First published · differs2026-05-18 SRC2026-02-27 SRC
Versions recordedUnknownUnknown
VerificationAuto-discovered; type inferred from repository topics HEUAuto-discovered; type inferred from repository topics HEU
Last verifiedUnknownUnknown

Shared and unique capabilitiesDER

Capabilities are assigned by keyword rules from each description unless a researcher set them; integrations are services named in the description or package metadata.

Both (1)

Only open-code-review (0)

None identified.

Only gentle-ai (1)

Platform compatibility

Status per platform from the evidence we hold. No pairing has been tested by AgentSidekick.

Platformopen-code-reviewgentle-ai
OpenClawProtocol-levelProtocol-level
OpenCode · differsProtocol-levelVendor claimed
Claude Code · differsProtocol-levelVendor claimed
Codex · differsProtocol-levelVendor claimed
Gemini CLIProtocol-levelProtocol-level
OpenHandsProtocol-levelProtocol-level
WarpProtocol-levelProtocol-level
gooseProtocol-levelProtocol-level
Bolt (bolt.new)Protocol-levelProtocol-level
KiroProtocol-levelProtocol-level
AmpProtocol-levelProtocol-level
Apps in ChatGPT / Apps SDK (now ChatGPT Plugins)Protocol-levelProtocol-level
ChatGPTProtocol-levelProtocol-level
Claude (claude.ai apps)Protocol-levelProtocol-level
Claude DesktopProtocol-levelProtocol-level
Cursor · differsProtocol-levelVendor claimed
DevinProtocol-levelProtocol-level
Devin Desktop (formerly Windsurf)Protocol-levelProtocol-level
Factory (Droid)Protocol-levelProtocol-level
Gemini (app)Protocol-levelProtocol-level
GitHub CopilotProtocol-levelProtocol-level
GitHub Copilot cloud agent (formerly Copilot coding agent)Protocol-levelProtocol-level
Google AntigravityProtocol-levelProtocol-level
JunieProtocol-levelProtocol-level
Replit AgentProtocol-levelProtocol-level
TabnineProtocol-levelProtocol-level

21 other platform(s): Unknown or Platform discontinued for both.

Maintenance

Repository activity read from the GitHub API. Activity is not quality.

Measureopen-code-reviewgentle-ai
StatusActive DERActive DER
Days since last push0 DER0 DER
Open issues139 SRC264 SRC
Latest GitHub releasev1.14.0 · 2026-11-21 SRCv4.6.0 · 2026-11-18 SRC
Newest registry versionUnknownUnknown

Evaluation dimensions

Separate signals with their evidence; there is no overall score. Hover or focus a status for its evidence.

Dimensionopen-code-reviewgentle-ai
Source authorityAuto-discoveredAuto-discovered
Publisher verificationOrganisation accountOrganisation account
Maintenance activityActiveActive
Licence clarity · differsApache-2.0MIT
Installation clarityUnknownUnknown
DocumentationRepository / website onlyRepository / website only
Compatibility evidence · differsProtocol-level onlyVendor claimed
Security reviewNot reviewedNot reviewed

Which fits which requirementDER

Derived from the differences above, one rule per line. Nothing here says either product is better; check the requirement against your own needs.

Choose open-code-review if…

  • you weigh adoption: 55k vs 9.4k GitHub stars (popularity, not quality)

Choose gentle-ai if…

  • you need Agent Memory (classified for gentle-ai only)
  • you need a publisher statement naming Claude Code, Cursor, Codex (vendor claim, not tested)

Sources

Report incorrect information

Page data last updated .