QwenPaw vs core
Self-hosted personal AI assistants compared
QwenPaw and core are self-hosted personal AI assistants built around persistent context and task support. QwenPaw emphasizes customizable agents, local model options, and broad interfaces, while core organizes work into planned tasks and connects it to apps and coding agents.

QwenPaw: Run a Self-Hosted AI Assistant Across Chat Apps
QwenPaw is a personal AI assistant you can run locally or in the cloud, connect to chat apps, and extend with skills, plugins, and MCP tools. It suits people who want persistent memory and configurable agents across a web console, terminal, and messaging channels.

core: Self-Host a Personal AI Assistant for Everyday Work
CORE is a self-hosted AI assistant that combines persistent memory, task planning, app integrations, and coding agents. It suits people who want one assistant to work across their tools, with human approval and control over their data.
| QwenPaw | core | |
|---|---|---|
| Language | TypeScript | TypeScript |
| License | Apache-2.0 | NOASSERTION |
| Stars | 35.5k | 2k |
| Forks | 3.2k | 196 |
| Last analyzed | Oct 9, 2026 | Oct 3, 2026 |
Key differences
- QwenPaw offers skills, plugins, MCP tools, multiple agents, and file workflows; core centers on task plans, a temporal knowledge graph, and app integrations.
- QwenPaw supports local models and cloud providers, while core describes browser and terminal execution through a gateway with local or remote options.
- QwenPaw provides a web console, terminal UI, beta desktop app, and messaging integrations; core offers a web interface, voice, WhatsApp, Slack, and Telegram.
- QwenPaw is licensed Apache-2.0; core's metadata says NOASSERTION while its README displays an AGPL 3.0 badge, so verify the license before adoption.
- QwenPaw has 35.4k stars and 3.2k forks, compared with core's 2k stars and 196 forks; core also lists 211 open issues.
- QwenPaw's listed language is TypeScript, as is core's.
Choose QwenPaw if you…
- want a customizable assistant with local model options and multiple agent interfaces.
- need editable persistent memory, file workspace tools, or scheduled tasks.
- want security controls such as sandboxing, file guards, and approval policies.
Choose core if you…
- want task plans and a knowledge graph to carry context across connected services.
- need integrations with 50+ apps and webhook-triggered work.
- want to delegate coding tasks to Claude Code or Codex through a gateway-based workflow.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.