ProliferatevsQwenPaw
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Proliferate
Proliferate · Agent harness
OSSMCP
Panel
6.62 spec wins
- Reliability
- 6.3
- Usefulness
- 7.0
- Cost
- 7.2
- Longevity
- 6.0
“It can run your dependency bumps nightly, so now the robots have a shift and you have a merge queue.”
QwenPaw
AgentScope (Alibaba) · Agent harness
OSSMCP
Panel
6.83 spec wins
- Reliability
- 6.3
- Usefulness
- 6.7
- Cost
- 7.3
- Longevity
- 6.7
“The cloud quick start includes a reminder to set the Studio to non-public, so strangers cannot control your assistant.”
Spec by spec
| Spec | Proliferate | QwenPaw |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local, cloud | local, cloud |
| Platforms | macos | macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | No |
| Git operations | Yes | No |
| Browser control | YesBrowser Use and Computer Use are listed among the integrations shared across agents. | Yes |
| Sandboxed execution | No | Yes |
| Multi-agent orchestration | YesAgents run side by side on separate tasks and can also delegate to child subagents within a task. | Yes |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | via managed agents (Claude Code, Codex, OpenCode, Cursor, Grok) | Qwen, OpenAI, Anthropic, Gemini, DeepSeek, Kimi, OpenRouter, QwenPaw-Flash, Ollama, LM Studio |
| Bring your own model | Yes | Yes |
| Local models | No | Yes |
| Cost | ||
| Pricing model | byok | byok |
| Starts at | $0/mo | $0/mo |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | AGPL-3.0 | Apache-2.0 |
| GitHub stars | 511 | 35,413 |
Which one would each critic pick
| Critic | Proliferate | QwenPaw | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.3 | 7.3 | no preference |
| El Crítico | 6.3 | 6.0 | Proliferate — Workflows schedule recurring and event-driven runs, and those agents execute on your machine with no container boundary documented anywhere around them. |
| El Profesor | 7.0 | 6.5 | Proliferate — Tools, skills and servers are configured once and shared by every agent, so behaviour differences between five harnesses are attributable to the harnesses rather than to their setup. |
| La Inversora | 6.0 | 6.8 | QwenPaw — Alibaba's AgentScope team, with one-click deployment to Alibaba Cloud ECS, ModelScope Studio and a free always-on AgentScope Platform: the product is a funnel into DashScope and the cloud. |
| La Jefa | 5.5 | 6.0 | QwenPaw — Kernel-level sandboxing on all three desktop OSes is the strongest security page on this board, a multi-user Hub shipped today, SSO is absent, and init --defaults accepts telemetry silently. |
| El Hacker | 7.8 | 8.0 | QwenPaw — Apache-2.0, Ollama at 32k context or LM Studio, a YAML Tool Guard from STRICT to OFF that inspects every call, MCP plus A2A plus ACP drivers, and a persona I edit as SOUL and PROFILE files. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.