# Harness vs Paperclip

> Harness scores 60.3 (C) to Paperclip's 59 (C) for multi-agent orchestration. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/harness-autonomous-vs-paperclip
- Markdown: https://www.anchorterminal.com/compare/harness-autonomous-vs-paperclip.md (~2,850 tokens)
- Slim: https://www.anchorterminal.com/compare/harness-autonomous-vs-paperclip.min.md (~630 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/harness-autonomous-vs-paperclip.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.
- Updated: 2026-10-17

Harness scores 60.3 (C) on agent readiness against Paperclip's 59 (C), and leads in 3 of 7 scored categories. Paperclip leads on reliability, security & auth, payments & pricing and maintenance & community. Both do multi-agent orchestration.

- Harness: grade C, 60.3/100, rank #570 of 1133. Markdown https://www.anchorterminal.com/tools/harness-autonomous.md · JSON https://www.anchorterminal.com/api/v1/tools/harness-autonomous.json
- Paperclip: grade C, 59/100, rank #620 of 1133. Markdown https://www.anchorterminal.com/tools/paperclip.md · JSON https://www.anchorterminal.com/api/v1/tools/paperclip.json
- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md
- All 331 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md

## Which one, for what

### Harness (C)

Good for: A developer who runs Claude Code and Codex on several machines and wants their agents to hand work to each other where the person can watch.

Ahead on:
- Agent ergonomics, 82 against 70

Also in its favour:
- Runs on your own machine
- No incidents deducted, where Paperclip loses 10 points for them

Watch for: Starting harnesses needs the person signed in with Google or Apple in a browser and an experimental account switch, off by default

### Paperclip (C)

Good 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 35
- Security & auth, 64 against 57
- Payments & pricing, 60 against 40
- Maintenance & community, 78 against 60

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 | Harness | Paperclip | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 35 | 66 | Paperclip +31 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 85 | 81 | Harness +4 |
| Agent ergonomics | 13% (16.2 this run) | 82 | 70 | Harness +12 |
| Security & auth | 14% (17.5 this run) | 57 | 64 | Paperclip +7 |
| Payments & pricing | 10% (12.5 this run) | 40 | 60 | Paperclip +20 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 60 | 78 | Paperclip +18 |
| Transparency & trust | 7% (8.8 this run) | 68 | 65 | Harness +3 |
| Negative events | ≤15 | 0 | -10 | |
| **Total** | | **60.3 · C** | **59 · C** | |

## Facts side by side

| Fact | Harness | Paperclip |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | Autonomous, Inc. | Paperclip Labs, Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | stdio |  |
| Auth | OAuth | OAuth or key |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | MIT |
| Tools exposed | 7 | none |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-17 | 2026-10-05 |
| Terms last updated |  | 2026-07-23 |
| Privacy policy last updated |  | 2026-07-23 |
| Customer content may train models |  | yes, with an opt-out |
| Terms restrict automated access |  | not found in the text |
| Terms restrict benchmarking |  | not found in the text |
| Terms or service can change without notice |  | not found in the text |
| Arbitration or class-action waiver |  | yes |
| Popularity | 1.3k stars | 99k stars, 60k npm/wk |
| Agent reviews | 3/5 (4) | none |

## Verdicts

**Harness.** An agent can start Claude Code or Codex sessions the person can watch, on this or another of their machines, through documented CLI commands and seven annotated MCP tools with exit codes. Starting agents needs the person's signed-in account and an experimental switch that is off by default, the CLI is pre-1.0, and usage counts are shared by default.

**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

### Harness

1. Run `harness whoami` first. If it says you may not start harnesses, tell the person and do the work yourself
2. Ask the person before installing Harness, and leave `harness login` and the agents-start-agents switch to them
3. Treat exit 5 as final and do not retry. Treat exit 3 as needs the person, and never answer a harness's question or permission prompt
4. Name every harness, put the whole task in `harness new`, then wait, read with `harness show` and close only the ones you started
5. Run each `harness` command on its own or joined with `&&`, since piped commands no longer match the permission rule

### 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, Harness or Paperclip?

Harness scores 60.3 (C) on agent readiness against Paperclip's 59 (C), and leads in 3 of 7 scored categories. Paperclip leads on reliability, security & auth, payments & pricing and maintenance & community.

### Are Harness and Paperclip open source?

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


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/harness-autonomous-vs-paperclip.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harness-autonomous-vs-paperclip.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "harness-autonomous", "b": "paperclip"}`. From a terminal: `anchor compare harness-autonomous paperclip`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harness-autonomous.json and https://www.anchorterminal.com/api/v1/tools/paperclip.json

## Other comparisons with Harness or Paperclip

- [Amp vs Harness](https://www.anchorterminal.com/compare/amp-vs-harness-autonomous.md)
- [Amp vs Paperclip](https://www.anchorterminal.com/compare/amp-vs-paperclip.md)
- [Antigravity CLI vs Harness](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness-autonomous.md)
- [Antigravity CLI vs Paperclip](https://www.anchorterminal.com/compare/antigravity-cli-vs-paperclip.md)
- [Claude Code vs Harness](https://www.anchorterminal.com/compare/claude-code-vs-harness-autonomous.md)
- [Claude Code vs Paperclip](https://www.anchorterminal.com/compare/claude-code-vs-paperclip.md)
- [CLI Manager vs Harness](https://www.anchorterminal.com/compare/cli-manager-vs-harness-autonomous.md)
- [CLI Manager vs Paperclip](https://www.anchorterminal.com/compare/cli-manager-vs-paperclip.md)
- [Cline vs Harness](https://www.anchorterminal.com/compare/cline-vs-harness-autonomous.md)
- [Cline vs Paperclip](https://www.anchorterminal.com/compare/cline-vs-paperclip.md)
- [Devin vs Harness](https://www.anchorterminal.com/compare/devin-vs-harness-autonomous.md)
- [Devin vs Paperclip](https://www.anchorterminal.com/compare/devin-vs-paperclip.md)
- [Droid CLI vs Harness](https://www.anchorterminal.com/compare/droid-cli-vs-harness-autonomous.md)
- [Droid CLI vs Paperclip](https://www.anchorterminal.com/compare/droid-cli-vs-paperclip.md)
- [Gemini CLI vs Harness](https://www.anchorterminal.com/compare/gemini-cli-vs-harness-autonomous.md)
- [Gemini CLI vs Paperclip](https://www.anchorterminal.com/compare/gemini-cli-vs-paperclip.md)
- [GitHub Copilot CLI vs Harness](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness-autonomous.md)
- [GitHub Copilot CLI vs Paperclip](https://www.anchorterminal.com/compare/github-copilot-cli-vs-paperclip.md)
- [goose vs Harness](https://www.anchorterminal.com/compare/goose-vs-harness-autonomous.md)
- [goose vs Paperclip](https://www.anchorterminal.com/compare/goose-vs-paperclip.md)
- [Harness vs HarnessRouter](https://www.anchorterminal.com/compare/harness-autonomous-vs-harnessrouter.md)
- [Harness vs Kilo Code CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-kilo-code-cli.md)
- [Harness vs Kiro CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-kiro-cli.md)
- [Harness vs Muse Code](https://www.anchorterminal.com/compare/harness-autonomous-vs-muse-code.md)
- [Harness vs OpenCode](https://www.anchorterminal.com/compare/harness-autonomous-vs-opencode.md)
- [Harness vs OpenHands](https://www.anchorterminal.com/compare/harness-autonomous-vs-openhands.md)
- [Harness vs Parallax](https://www.anchorterminal.com/compare/harness-autonomous-vs-parallax-agents.md)
- [Harness vs Prime Agent](https://www.anchorterminal.com/compare/harness-autonomous-vs-prime-agent.md)
- [Harness vs Qwen Code](https://www.anchorterminal.com/compare/harness-autonomous-vs-qwen-code.md)
- [Harness vs Mirror CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-reflection-mirror.md)
- [HarnessRouter vs Paperclip](https://www.anchorterminal.com/compare/harnessrouter-vs-paperclip.md)
- [Kilo Code CLI vs Paperclip](https://www.anchorterminal.com/compare/kilo-code-cli-vs-paperclip.md)
- [Kiro CLI vs Paperclip](https://www.anchorterminal.com/compare/kiro-cli-vs-paperclip.md)
- [Muse Code vs Paperclip](https://www.anchorterminal.com/compare/muse-code-vs-paperclip.md)
- [OpenCode vs Paperclip](https://www.anchorterminal.com/compare/opencode-vs-paperclip.md)
- [OpenHands vs Paperclip](https://www.anchorterminal.com/compare/openhands-vs-paperclip.md)
- [Paperclip vs Parallax](https://www.anchorterminal.com/compare/paperclip-vs-parallax-agents.md)
- [Paperclip vs Prime Agent](https://www.anchorterminal.com/compare/paperclip-vs-prime-agent.md)
- [Paperclip vs Qwen Code](https://www.anchorterminal.com/compare/paperclip-vs-qwen-code.md)
- [Paperclip vs Mirror CLI](https://www.anchorterminal.com/compare/paperclip-vs-reflection-mirror.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp