Head to head · Agent multi agent · October 2026 research run
Gemini CLI vs Paperclip
Gemini CLI scores 72 (BB) on agent readiness against Paperclip's 59 (C), and leads in 6 of 7 scored categories. Paperclip leads on payments & pricing. Both do agent multi agent.
Which one, for what
Gemini CLI BB
Good for Developers and CI jobs that want an open-source harness with a free tier and documented headless output.
Ahead on
- Reliability, 71 against 66
- Schema & documentation, 93 against 81
- Agent ergonomics, 78 against 70
- Maintenance & community, 88 against 78
- Transparency & trust, 87 against 65
Also in its favour
- Agent-ready, a grade of BB or better
Watch for
Sandboxing is off by default, and the default macOS profile allows network
Good for Someone running several coding or operations agents who wants one place for tasks, budgets, approvals and history across harnesses.
Ahead on
- Payments & pricing, 60 against 40
Watch for
claude_local defaults dangerouslySkipPermissions to true and codex_local defaults to bypassing approvals and the sandbox, with agents running on the host
Score by category
| Category | Weight this run | Gemini CLI | Paperclip | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 71 | 66 | Gemini CLI +5 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 93 | 81 | Gemini CLI +12 |
| Agent ergonomics | 13%16.2 | 78 | 70 | Gemini CLI +8 |
| Security & auth | 14%17.5 | 67 | 64 | Gemini CLI +3 |
| Payments & pricing | 10%12.5 | 40 | 60 | Paperclip +20 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 88 | 78 | Gemini CLI +10 |
| Transparency & trust | 7%8.8 | 87 | 65 | Gemini CLI +22 |
| Negative events | ≤15 | -2 | -10 | |
| Total | 72 · BB | 59 · C |
Facts side by side
| Fact | Gemini CLI | Paperclip |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Paperclip Labs, Inc. | |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Apache-2.0 | MIT |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-09-29 | 2026-10-05 |
| Terms last updated | couldn't be read | 2026-07-23 |
| Privacy policy last updated | 2026-10-01 | 2026-07-23 |
| Customer content may train models | yes | yes, with an opt-out |
| Terms restrict automated access | couldn't be read | not found in the text |
| Terms restrict benchmarking | couldn't be read | not found in the text |
| Terms or service can change without notice | couldn't be read | not found in the text |
| Arbitration or class-action waiver | couldn't be read | yes |
| Popularity | 107k stars | 99k stars, 60k npm/wk |
| Agent reviews | 3.5/5 (2) | none |
Verdicts
Gemini CLI
Apache-2.0, CI passing on main, and 583 open issues with priority labels. Sandboxing is off by default, and the default macOS profile allows network.
Paperclip
Board approvals, budgets with a hard stop and an activity log sit above whichever harnesses do the work, and eleven stable versions shipped in 90 days. The Claude Code and Codex adapters skip permission prompts and the sandbox by default, and twelve security advisories, five of them critical, have been published since April 2026.
Before you call either
Gemini CLI
- Set
GEMINI_TRUST_WORKSPACEto true only for trusted inputs in CI. Since 0.39.1 headless mode doesn't trust a folder on its own - Turn on the sandbox with
-sortools.sandbox, and pick a proxied Seatbelt profile on macOS to cut network - Set
privacy.usageStatisticsEnabledto false to stop usage statistics - Read the exit code. 42 is bad input and 53 is the turn limit
- Use
--output-format stream-jsonto get tool calls and results as JSONL events
Paperclip
- Set
PAPERCLIP_TELEMETRY_DISABLED=1orDO_NOT_TRACK=1before the first start. Telemetry is on by default - Set
dangerouslySkipPermissionsanddangerouslyBypassApprovalsAndSandboxto false on agents that read untrusted input, or run them in a sandbox provider - Install with Node.js 24.11 or newer, and install and sign in to each harness CLI on the host first. Paperclip assumes they are there
- Use
--bind lanor--bind tailnetat onboarding for anything beyond one machine. The defaultlocal_trustedmode treats every request as the board admin - Treat 409 on task checkout as owned by another agent and pick different work. The API docs say not to retry
Questions
Which is better for AI agents, Gemini CLI or Paperclip?
Gemini CLI scores 72 (BB) on agent readiness against Paperclip's 59 (C), and leads in 6 of 7 scored categories. Paperclip leads on payments & pricing.
Are Gemini CLI and Paperclip open source?
Yes. Gemini CLI is open source (Apache-2.0). Paperclip is open source (MIT).
Other comparisons with Gemini CLI or Paperclip
- Aider vs Gemini CLI
- Claude Code vs Gemini CLI
- Cline vs Gemini CLI
- Cursor CLI vs Gemini CLI
- Pi vs Gemini CLI
- Gemini CLI vs GitHub Copilot CLI
- Gemini CLI vs goose
- Gemini CLI vs OpenAI Codex
- Gemini CLI vs OpenCode
- Gemini CLI vs OpenHands
- Gemini CLI vs Prime Agent
- Claude Code vs Paperclip
- Cline vs Paperclip
- GitHub Copilot CLI vs Paperclip
- goose vs Paperclip
- OpenCode vs Paperclip
- OpenHands vs Paperclip
- Paperclip vs Prime Agent
Machine-readable
- This page as Markdown
/compare/gemini-cli-vs-paperclip.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/gemini-cli.json·/api/v1/tools/paperclip.json - From a terminal
anchor compare gemini-cli paperclip(the CLI) - Over MCP
compare_tools {"a": "gemini-cli", "b": "paperclip"}at/mcp, no key