# Paperclip vs Prime Agent

> Prime Agent scores 60.5 (C) on agent readiness against Paperclip's 59 (C), and leads in 2 of 7 scored categories. Paperclip leads on schema & documentation and security & auth. Both do agent multi agent. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/paperclip-vs-prime-agent
- Markdown: https://www.anchorterminal.com/compare/paperclip-vs-prime-agent.md (~2,350 tokens)
- Slim: https://www.anchorterminal.com/compare/paperclip-vs-prime-agent.min.md (~580 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/paperclip-vs-prime-agent.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
- Updated: 2026-10-08

Prime Agent scores 60.5 (C) on agent readiness against Paperclip's 59 (C), and leads in 2 of 7 scored categories. Paperclip leads on schema & documentation and security & auth. Both do agent multi agent.

- Paperclip: grade C, 59/100, rank #441 of 722. Markdown https://www.anchorterminal.com/tools/paperclip.md · JSON https://www.anchorterminal.com/api/v1/tools/paperclip.json
- Prime Agent: grade C, 60.5/100, rank #399 of 722. Markdown https://www.anchorterminal.com/tools/prime-agent.md · JSON https://www.anchorterminal.com/api/v1/tools/prime-agent.json

## Which one, for what

### 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:
- Schema & documentation, 81 against 42
- Security & auth, 64 against 50

Watch for: `claude_local` defaults `dangerouslySkipPermissions` to true and `codex_local` defaults to bypassing approvals and the sandbox, with agents running on the host

### Prime Agent (C)

Good for: Long-running research and coding work where one model drives subagents, schedules and goals from code, and where the owner can isolate the machine.

Also in its favour:
- No key needed to call it
- No incidents deducted, where Paperclip loses 10 points for them

Watch for: No approval prompts and no sandbox. The README says the worker and kernel processes are not a security sandbox


## Score by category

| Category | Weight | Paperclip | Prime Agent | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 66 | 65 | Paperclip +1 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 81 | 42 | Paperclip +39 |
| Agent ergonomics | 13% (16.2 this run) | 70 | 73 | Prime Agent +3 |
| Security & auth | 14% (17.5 this run) | 64 | 50 | Paperclip +14 |
| Payments & pricing | 10% (12.5 this run) | 60 | 60 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 78 | 79 | Prime Agent +1 |
| Transparency & trust | 7% (8.8 this run) | 65 | 64 | Paperclip +1 |
| Negative events | ≤15 | -10 | 0 | |
| **Total** | | **59 · C** | **60.5 · C** | |

## Facts side by side

| Fact | Paperclip | Prime Agent |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | Paperclip Labs, Inc. | Prime Intellect |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | OAuth or key | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | MIT |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-05 | 2026-10-07 |
| Terms last updated | 2026-07-23 | no date given |
| Privacy policy last updated | 2026-07-23 | no date given |
| Customer content may train models | yes, with an opt-out | not found in the text |
| Terms restrict automated access | not found in the text | yes |
| Terms restrict benchmarking | not found in the text | yes |
| Terms or service can change without notice | not found in the text | yes |
| Arbitration or class-action waiver | yes | yes |
| Popularity | 99k stars, 60k npm/wk | 22k stars |

## Verdicts

**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.

**Prime Agent.** Budgets for turns, tokens and time bound an autonomous run, and sessions survive a closed terminal through a supervising daemon. Model-written Python and shell commands run with the user's rights, with no approval step and no sandbox, and the Rust build on the main branch ships only as nightly betas.

## Before you call either

### 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

### Prime Agent

1. Run it in a disposable clone, container or VM. It executes model-written Python and shell commands with the user's rights and asks nothing first
2. Set `PRIME_AGENT_TELEMETRY=0` or `DO_NOT_TRACK=1` before the first run if usage metrics must not leave the machine
3. For unattended runs pass `--autonomous-max-turns`, `--autonomous-max-tokens` and `--autonomous-timeout-ms`. Reaching a limit does not mean the task succeeded
4. Headless use is `-p` with `--mode json` per the argument parser. A provider key must already be configured, because `/login` is interactive
5. The `-t/--tools`, `-nt/--no-tools` and `-nbt/--no-builtin-tools` flags were removed and now fail as unknown options

## Questions

### Which is better for AI agents, Paperclip or Prime Agent?

Prime Agent scores 60.5 (C) on agent readiness against Paperclip's 59 (C), and leads in 2 of 7 scored categories. Paperclip leads on schema & documentation and security & auth.

### Are Paperclip and Prime Agent open source?

Yes. Paperclip is open source (MIT). Prime Agent is open source (MIT).


## For agents

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

## Other comparisons with Paperclip or Prime Agent

- [Aider vs Prime Agent](https://www.anchorterminal.com/compare/aider-vs-prime-agent.md)
- [Amp vs Prime Agent](https://www.anchorterminal.com/compare/amp-vs-prime-agent.md)
- [Claude Code vs Prime Agent](https://www.anchorterminal.com/compare/claude-code-vs-prime-agent.md)
- [Cline vs Prime Agent](https://www.anchorterminal.com/compare/cline-vs-prime-agent.md)
- [Cursor CLI vs Prime Agent](https://www.anchorterminal.com/compare/cursor-cli-vs-prime-agent.md)
- [Devin vs Prime Agent](https://www.anchorterminal.com/compare/devin-vs-prime-agent.md)
- [Pi vs Prime Agent](https://www.anchorterminal.com/compare/earendil-pi-vs-prime-agent.md)
- [Gemini CLI vs Prime Agent](https://www.anchorterminal.com/compare/gemini-cli-vs-prime-agent.md)
- [GitHub Copilot CLI vs Prime Agent](https://www.anchorterminal.com/compare/github-copilot-cli-vs-prime-agent.md)
- [goose vs Prime Agent](https://www.anchorterminal.com/compare/goose-vs-prime-agent.md)
- [Kiro CLI vs Prime Agent](https://www.anchorterminal.com/compare/kiro-cli-vs-prime-agent.md)
- [OpenAI Codex vs Prime Agent](https://www.anchorterminal.com/compare/openai-codex-vs-prime-agent.md)
- [OpenCode vs Prime Agent](https://www.anchorterminal.com/compare/opencode-vs-prime-agent.md)
- [OpenHands vs Prime Agent](https://www.anchorterminal.com/compare/openhands-vs-prime-agent.md)
- [Prime Agent vs Qwen Code](https://www.anchorterminal.com/compare/prime-agent-vs-qwen-code.md)
- [Amp vs Paperclip](https://www.anchorterminal.com/compare/amp-vs-paperclip.md)
- [Claude Code vs Paperclip](https://www.anchorterminal.com/compare/claude-code-vs-paperclip.md)
- [Cline vs Paperclip](https://www.anchorterminal.com/compare/cline-vs-paperclip.md)
- [Devin vs Paperclip](https://www.anchorterminal.com/compare/devin-vs-paperclip.md)
- [Gemini CLI vs Paperclip](https://www.anchorterminal.com/compare/gemini-cli-vs-paperclip.md)
- [GitHub Copilot CLI vs Paperclip](https://www.anchorterminal.com/compare/github-copilot-cli-vs-paperclip.md)
- [goose vs Paperclip](https://www.anchorterminal.com/compare/goose-vs-paperclip.md)
- [Kiro CLI vs Paperclip](https://www.anchorterminal.com/compare/kiro-cli-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 Qwen Code](https://www.anchorterminal.com/compare/paperclip-vs-qwen-code.md)