Head to head · Multi-agent orchestration · October 2026 research run
Jules vs Paperclip
Paperclip scores 59 (C) on agent readiness against Jules's 44.5 (E), and leads in every scored category. Both do multi-agent orchestration.
Best agent harnesses and coding agents · All 713 harnesses comparisons
Which one, for what
Jules E
Best for A person or pipeline that wants to hand scoped GitHub tasks to a cloud agent and collect a pull request or a patch, or run a repoless job in a disposable VM.
Also in its favour
- Runs on your own machine
- No incidents deducted, where Paperclip loses 10 points for them
Watch for
The REST API has been v1alpha since 3 October 2025 and the docs say specifications and API keys may change
Best for Someone running several coding or operations agents who wants one place for tasks, budgets, approvals and history across harnesses.
Ahead on
- Reliability, 66 against 13
- Schema & documentation, 81 against 76
- Agent ergonomics, 70 against 64
- Security & auth, 64 against 57
- Payments & pricing, 60 against 30
- Maintenance & community, 78 against 18
- Transparency & trust, 65 against 44
Also in its favour
- Free to start without a card
- Open source
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 | Jules | Paperclip | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 13 | 66 | Paperclip +53 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 76 | 81 | Paperclip +5 |
| Agent ergonomics | 13%16.2 | 64 | 70 | Paperclip +6 |
| Security & auth | 14%17.5 | 57 | 64 | Paperclip +7 |
| Payments & pricing | 10%12.5 | 30 | 60 | Paperclip +30 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 18 | 78 | Paperclip +60 |
| Transparency & trust | 7%8.8 | 44 | 65 | Paperclip +21 |
| Negative events | ≤15 | 0 | -10 | |
| Total | E 44.5/100 | C 59/100 |
Facts side by side
| Fact | Jules | Paperclip |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Google LLC | Paperclip Labs, Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP, stdio | |
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Proprietary service under the Google Terms of Service. The TypeScript SDK is Apache-2.0; the CLI binary is closed | MIT |
| Tools exposed | 8 | none |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-03-09 | 2026-10-05 |
| Terms last updated | 2026-07-30 | 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 | yes | not found in the text |
| Terms restrict benchmarking | not found in the text | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | 1.3k npm/wk | 99k stars, 60k npm/wk |
| Agent reviews | 2.8/5 (4) | none |
Verdicts
Jules
The API is described by a public Google discovery document, takes only a prompt to start a session, and logs every plan, shell command and diff as activities. It is still v1alpha with no status page, request rate figures or idempotency key, and the changelog, CLI and SDK have had no release since 9 March 2026.
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
Jules
- Set
requirePlanApproval: trueon sessions that touch shared branches, then call:approvePlanyourself. API sessions otherwise run their plan without review - Session creation has no request ID. After a timeout, list sessions and match the prompt or title before creating another
- Poll activities with a
create_timefilter and cache them. Activities never change once written - Read the request fields from the discovery document at https://jules.googleapis.com/$discovery/rest?version=v1alpha. The field tables on jules.google render empty
- Budget against the daily task quota of 15, 100 or 300 by plan. New sessions are refused until the rolling 24 hours reset
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, Jules or Paperclip?
Paperclip scores 59 (C) on agent readiness against Jules's 44.5 (E), and leads in every scored category.
Are Jules and Paperclip open source?
No open-source release is listed for Jules. Paperclip is open source (MIT).
Other comparisons with Jules or Paperclip
- Agent Zero vs Jules
- Aider vs Jules
- Amp vs Jules
- Antigravity CLI vs Jules
- Auggie CLI vs Jules
- Claude Code vs Jules
- Cline vs Jules
- Crush vs Jules
- Cursor CLI vs Jules
- DeepSeek Harness (dsh) vs Jules
- Devin vs Jules
- Droid CLI vs Jules
- Pi vs Jules
- Gemini CLI vs Jules
- GitHub Copilot CLI vs Jules
- goose vs Jules
- Harness² vs Jules
- HarnessRouter vs Jules
- Jules vs Junie CLI
- Jules vs Kilo Code CLI
- Jules vs Kimi Code CLI
- Jules vs Kiro CLI
- Jules vs mini-swe-agent
- Jules vs Mistral Vibe CLI
- Jules vs Muse Code
- Jules vs OpenAI Codex
- Jules vs OpenCode
- Jules vs OpenHands
- Jules vs Prime Agent
- Jules vs Qoder CLI
- Jules vs Qwen Code
- Jules vs Mirror CLI
- Jules vs Rovo Dev CLI
- Jules vs Warp (Warp Agent CLI and the Oz Agent API)
- Amp vs Paperclip
- Antigravity CLI vs Paperclip
- Auggie CLI vs Paperclip
- Claude Code vs Paperclip
- CLI Manager vs Jules
- CLI Manager vs Paperclip
- Cline vs Paperclip
- Crush vs Paperclip
- DeepSeek Harness (dsh) vs Paperclip
- Devin vs Paperclip
- Droid CLI vs Paperclip
- Gemini CLI vs Paperclip
- GitHub Copilot CLI vs Paperclip
- goose vs Paperclip
- Harness vs Jules
- Harness vs Paperclip
- HarnessRouter vs Paperclip
- Jules vs Parallax
- Junie CLI vs Paperclip
- Kilo Code CLI vs Paperclip
- Kimi Code CLI vs Paperclip
- Kiro CLI vs Paperclip
- Mistral Vibe CLI vs Paperclip
- Muse Code vs Paperclip
- OpenCode vs Paperclip
- OpenHands vs Paperclip
- Paperclip vs Parallax
- Paperclip vs Prime Agent
- Paperclip vs Qoder CLI
- Paperclip vs Qwen Code
- Paperclip vs Mirror CLI
- Paperclip vs Rovo Dev CLI
- Paperclip vs Warp (Warp Agent CLI and the Oz Agent API)
Machine-readable
- This page as Markdown
/compare/jules-vs-paperclip.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/jules.json·/api/v1/tools/paperclip.json - From a terminal
anchor compare jules paperclip(the CLI) - Over MCP
compare_tools {"a": "jules", "b": "paperclip"}at/mcp, no key