Tsinghua and collaborators release PilotDeck 2.0 with editable memory and model routing

What happened

Tsinghua University's THUNLP lab, ModelBest, OpenBMB, and collaborators released PilotDeck 2.0, an open-source agent operating system with isolated project workspaces, inspectable and editable memory, background execution, and native MCP support. Across seven complex tasks, the team reported that routing between Sonnet 4.6 and MiniMax-M2.7 scored 70.6 at $3.15, compared with 69.1 at $18.36 for standalone Claude Sonnet 4.6. PilotDeck uses AGPL-3.0 and supports macOS, Linux, Windows, and Docker deployment.

The story so far

Tsinghua University’s THUNLP lab, ModelBest, OpenBMB, and collaborators released PilotDeck 2.0, an open-source agent operating system that supports isolated project workspaces, inspectable and editable memory, background execution, and native MCP integration. The system is available under the AGPL-3.0 license and supports macOS, Linux, Windows, and Docker deployment. The team also reported results from routing tasks between Sonnet 4.6 and MiniMax-M2.7. Across seven complex tasks, that configuration scored 70.6 at a cost of $3.15, compared with a score of 69.1 at $18.36 for standalone Claude Sonnet 4.6. Those results apply to the team’s seven-task evaluation.

Keep reading

Trending now

1. 1DeepSeek Releases V4.1-Flash-1017, Now Available on Ollama Cloud With US Hosting
2. 2Meta Removes Business Terms Language That Raised Website Scraping and AI Training Concerns
3. 3Google DeepMind Says Four Gemini 4 Argon Agents Beat Minecraft Without Human Help
4. 4Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary