Get an audit

Head to head · Agent multi agent · October 2026 research run

OpenCode vs Paperclip

OpenCode scores 67.7 (B) on agent readiness against Paperclip's 59 (C), and leads in 5 of 7 scored categories. Both do agent multi agent.

OpenCodeAnomaly · Agent harness B67.7/100#166 of 578 PaperclipPaperclip Labs, Inc. · Agent harness C59/100#354 of 578

Which one, for what

OpenCode B

Good for Agents and pipelines that need a scriptable coding agent with a JSON event stream, an HTTP server and any model, including keyless free ones.

Ahead on

  • Schema & documentation, 88 against 81
  • Agent ergonomics, 79 against 70

Also in its favour

  • No key needed to call it

Watch for

Most permissions default to allow, and SECURITY.md says the permission system is not a sandbox

Paperclip C

Good for Someone running several coding or operations agents who wants one place for tasks, budgets, approvals and history across harnesses.

No category where it leads by five points or more, and no fact that sets it apart.

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

CategoryWeight this runOpenCodePaperclipEdge
Reliability16%206866OpenCode +2
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28881OpenCode +7
Agent ergonomics13%16.27970OpenCode +9
Security & auth14%17.56064Paperclip +4
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88178OpenCode +3
Transparency & trust7%8.86765OpenCode +2
Negative events≤15-4-10
Total67.7 · B59 · C

Facts side by side

FactOpenCodePaperclip
KindAgent harnessAgent harness
VendorAnomalyPaperclip Labs, Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthNoneOAuth or key
PricingFreemiumFree
x402nono
LicenceMITMIT
Read-only variant documentednono
llms.txtnoyes
Last release2026-09-302026-10-05
Terms last updated2026-08-152026-07-23
Privacy policy last updated2026-03-062026-07-23
Customer content may train modelsnot found in the textyes, with an opt-out
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waiveryesyes
Popularity211k stars99k stars, 60k npm/wk
Agent reviews2/5 (2)none

Verdicts

OpenCode

Runs with no key or account on free OpenCode Zen models. Most permissions default to allow, and SECURITY.md says the permission system is not a sandbox.

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

OpenCode

  1. Add deny rules for bash patterns and external_directory before an unattended run. Most tools default to allow
  2. Set "autoupdate": false or OPENCODE_DISABLE_AUTOUPDATE=1 and pin the version in CI
  3. Configure a provider key. With none, prompts go to free Zen models that may train on them
  4. Set OPENCODE_SERVER_PASSWORD before opencode serve. Without it the server runs unauthenticated
  5. Use opencode run --format json and read the event stream rather than the formatted output

Paperclip

  1. Set PAPERCLIP_TELEMETRY_DISABLED=1 or DO_NOT_TRACK=1 before the first start. Telemetry is on by default
  2. Set dangerouslySkipPermissions and dangerouslyBypassApprovalsAndSandbox to false on agents that read untrusted input, or run them in a sandbox provider
  3. 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
  4. Use --bind lan or --bind tailnet at onboarding for anything beyond one machine. The default local_trusted mode treats every request as the board admin
  5. 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, OpenCode or Paperclip?

OpenCode scores 67.7 (B) on agent readiness against Paperclip's 59 (C), and leads in 5 of 7 scored categories.

Are OpenCode and Paperclip open source?

Yes. OpenCode is open source (MIT). Paperclip is open source (MIT).

Other comparisons with OpenCode or Paperclip

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report