# Prime Agent vs Qwen Code

> Qwen Code scores 72.4 (BB) on agent readiness against Prime Agent's 60.5 (C), and leads in 5 of 7 scored categories. Both do agent harness. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/prime-agent-vs-qwen-code
- Markdown: https://www.anchorterminal.com/compare/prime-agent-vs-qwen-code.md (~2,400 tokens)
- Slim: https://www.anchorterminal.com/compare/prime-agent-vs-qwen-code.min.md (~580 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/prime-agent-vs-qwen-code.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

Qwen Code scores 72.4 (BB) on agent readiness against Prime Agent's 60.5 (C), and leads in 5 of 7 scored categories. Both do agent harness.

- Prime Agent: grade C, 60.5/100, rank #352 of 629. Markdown https://www.anchorterminal.com/tools/prime-agent.md · JSON https://www.anchorterminal.com/api/v1/tools/prime-agent.json
- Qwen Code: grade BB, 72.4/100, rank #88 of 629. Markdown https://www.anchorterminal.com/tools/qwen-code.md · JSON https://www.anchorterminal.com/api/v1/tools/qwen-code.json

## Which one, for what

### 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

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

### Qwen Code (BB)

Good for: Developers and CI jobs that want an open-source harness tied to no single model vendor, with run budgets and SDKs.

Ahead on:
- Schema & documentation, 91 against 42
- Agent ergonomics, 85 against 73
- Maintenance & community, 88 against 79

Also in its favour:
- Agent-ready, a grade of BB or better

Watch for: The default approval mode is Auto, where an LLM classifier approves tool calls, and sandboxing and folder trust are both off by default


## Score by category

| Category | Weight | Prime Agent | Qwen Code | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 65 | 69 | Qwen Code +4 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 42 | 91 | Qwen Code +49 |
| Agent ergonomics | 13% (16.2 this run) | 73 | 85 | Qwen Code +12 |
| Security & auth | 14% (17.5 this run) | 50 | 53 | Qwen Code +3 |
| 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) | 79 | 88 | Qwen Code +9 |
| Transparency & trust | 7% (8.8 this run) | 64 | 63 | Prime Agent +1 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **60.5 · C** | **72.4 · BB** | |

## Facts side by side

| Fact | Prime Agent | Qwen Code |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | Prime Intellect | Alibaba (Qwen team) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | API key |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-10-07 | 2026-10-05 |
| Terms last updated | no date given | 2026-10-01 |
| Privacy policy last updated | no date given | 2026-10-01 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | yes | not found in the text |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | yes | not found in the text |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | 22k stars | 28k stars, 105k npm/wk |

## Verdicts

**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.

**Qwen Code.** Apache-2.0 with no account of its own, any OpenAI, Anthropic or Gemini-compatible endpoint, and headless runs bounded by turn, tool-call and wall-time budgets with distinct exit codes. Out of the box, Auto mode lets an LLM classifier approve tool calls, with the sandbox and folder trust both off. Usage statistics are on by default.

## Before you call either

### 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

### Qwen Code

1. Pass `--approval-mode` on every run. The settings default is `auto`, and one docs page says headless runs default to asking, so don't rely on either
2. Add `--max-session-turns`, `--max-wall-time` and `--max-tool-calls`. All three are unlimited by default. Exit 53 is the turn limit and 55 a budget
3. `--yolo` doesn't turn on a sandbox. Add `--sandbox`, or on Linux set `tools.executionSandbox` with `network` set to `closed`
4. Set `QWEN_USAGE_STATISTICS_ENABLED=false` to stop usage statistics
5. Authenticate with `OPENAI_API_KEY`, `OPENAI_BASE_URL` and `OPENAI_MODEL` in CI. The browser sign-in is discontinued

## Questions

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

Qwen Code scores 72.4 (BB) on agent readiness against Prime Agent's 60.5 (C), and leads in 5 of 7 scored categories.

### Are Prime Agent and Qwen Code open source?

Yes. Prime Agent is open source (MIT). Qwen Code is open source (Apache-2.0).


## For agents

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

## Other comparisons with Prime Agent or Qwen Code

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