Gemini CLI vs Claude Code vs Codex
3 tools side by side on public signals only.
Updated : the last week a score, rank or safety result on this page changed.
- #1Gemini CLImaintenance 71 · adoption 69 · docs 6970Caution
- #4Claude Codemaintenance 77 · adoption 82 · docs 2065No dependencies scanned
- #6Codexmaintenance 74 · adoption 74 · docs 1058Caution
What this does not tell you
Scores are percentiles of public GitHub signals. Nobody here tested these tools hands-on, so the higher score is not a verdict on which suits your project. Yellow marks the higher value.
Which one fits you
From measured data and licences, not from testing.
Pick Gemini CLI if
- You rely on thorough README docs (docs 69 vs 20).
- You need a permissive open-source licence (Apache-2.0).
Pick Claude Code if
- Recent activity and releases matter most to you (maintenance 77).
- You want the more widely adopted option (adoption 82).
Pick Codex if
- You need a permissive open-source licence (Apache-2.0).
Safety side by side
Automated scan, 2 Nov 2026. Not a manual audit.
- CautionGemini CLI9 critical-severity known vulnerabilities in runtime dependencies (OSV). Agent file pipes a script into a shell
- No dependencies scannedClaude CodeCode checks clean, no lockfile to check
- CautionCodex4 critical-severity known vulnerabilities in runtime dependencies (OSV)
Why different labels?
A label partly reflects how much of each tool is visible and scannable, not only how risky it is. A tool without a lockfile cannot get a dependency check.
- Gemini CLI: 9 critical-severity known vulnerabilities in runtime dependencies (OSV); Skill/agent file instructs piping a remote script into a shell: .gemini/skills/agent-tui/SKILL.md — curl -fsSL https://raw.githubusercontent.com/pproenca/agent-tui/master/install.sh | sh
- Claude Code: code and instruction-file checks found nothing, but there is no runtime lockfile or manifest, so dependencies were not checked
- Codex: 4 critical-severity known vulnerabilities in runtime dependencies (OSV)
Repo facts
Yellow = the higher value, where higher is better.
| Fact | Gemini CLI | Claude Code | Codex |
|---|---|---|---|
| Score | 70 | 65 | 58 |
| Stars | 108,661 | 154,199 | 132,785 |
| Last push | 2 Nov | 1 Nov | 1 Nov |
| Releases, 90 days | 10+ | 10+ | 10+ |
| Licence | Apache-2.0 | Proprietary (Anthropic Commercial Terms) | Apache-2.0 |
| Open source | Open source | Proprietary | Open source |
| Language | TypeScript | TypeScript | Rust |
| Type | AI tool | AI tool | AI tool |
| Runs locally | yes | yes | yes |
| Hosted option | unknown | mentioned | mentioned |
“Runs locally” and “Hosted option” are read from each README automatically (or from the official docs where noted); “unknown” means no evidence was found, not that it is absent.
Questions about Gemini CLI vs Claude Code vs Codex
Answers use this week's StackGrade data.
Gemini CLI, Claude Code or Codex: which scores higher on StackGrade?
Highest to lowest in Week 45: Gemini CLI 70, Claude Code 65, Codex 58 out of 100. The score combines maintenance, adoption and docs (percentiles of public GitHub signals): Gemini CLI 71, 69 and 69; Claude Code 77, 82 and 20; Codex 74, 74 and 10. Community (20% weight) is not measured yet. It is not a hands-on test, so a higher score does not say which tool suits your project.
Is Gemini CLI, Claude Code or Codex safer to use?
Safety labels from the automated scan of 2 Nov 2026: Gemini CLI: Caution, 9 critical-severity known vulnerabilities in runtime dependencies (OSV); Claude Code: No dependencies scanned, code checks clean, no lockfile to check; Codex: Caution, 4 critical-severity known vulnerabilities in runtime dependencies (OSV). “No dependencies scanned” means the code checks were clean but there is no lockfile, so dependencies could not be checked; it is not a clean bill. It is an automated scan, not a manual audit.
Which is more widely used, Gemini CLI, Claude Code or Codex?
By GitHub stars: Claude Code 154,199, Codex 132,785, Gemini CLI 108,661. Adoption score (percentile among all 52 tracked tools): Gemini CLI 69, Claude Code 82, Codex 74. Stars are one public signal and do not measure real-world use.
Which licences do Gemini CLI, Claude Code and Codex use?
Gemini CLI: Apache-2.0; Claude Code: Proprietary (Anthropic Commercial Terms); Codex: Apache-2.0. Read each licence text before commercial use.
Should I pick Gemini CLI, Claude Code or Codex?
Pick Gemini CLI if you rely on thorough README docs (docs 69 vs 20); you need a permissive open-source licence (Apache-2.0). Pick Claude Code if recent activity and releases matter most to you (maintenance 77); you want the more widely adopted option (adoption 82). Pick Codex if you need a permissive open-source licence (Apache-2.0). This comes from measured public data and licences only, not from hands-on testing.
Full comparison table, every criterion
| Gemini CLIgoogle-gemini/gemini-cli | Claude Codeanthropics/claude-code | Codexopenai/codex | |
|---|---|---|---|
| Score | 70 | 65 | 58 |
| Rank | #4 overall · #1 in use case | #11 overall · #4 in use case | #16 overall · #6 in use case |
| Maintenance (30%) | 71 | 77 | 74 |
| Adoption (30%) | 69 | 82 | 74 |
| Docs (20%) | 69 | 20 | 10 |
| Community (20%) | not measured | not measured | not measured |
| Safety | Caution
| No dependencies scanned | Caution
|
| License | Apache-2.0 | Proprietary (Anthropic Commercial Terms) | Apache-2.0 |
| Open source | Open source | Proprietary | Open source |
| Language | TypeScript | TypeScript | Rust |
| Stars | 108,661 | 154,199 | 132,785 |
| Last push | |||
| Type | AI tool | AI tool | AI tool |
| Runs locally | yes (README: "npm install -g") | yes (README: "npm install -g") | yes (README: "brew install") |
| Hosted option | unknown | mentioned (official docs: code.claude.com/docs/en/claude-code-on-the-web) | mentioned (official docs: developers.openai.com/codex/cloud) |
Get the board every Monday
One email a week: the new top 10, the biggest score changes and every safety label that changed.
Free. Double opt-in: you confirm by email first, unsubscribe in one click.