Article
Projects
Table 1 Projects
| Project | Description | Link |
|---|---|---|
| FrontierPhysics | FrontierPhysics is an open benchmark measuring whether AI agents can carry out authentic, specialist-level physics research. | benchflow.ai/frontierphysics |
| BenchFlow | BenchFlow is a frontier environment lab. We build the environments AI agents learn in. We ship SkillsBench, ClawsBench, PostTrain, and the runtime. | benchflow.ai |
| SkillsBench | SkillsBench evaluates how well skills work and how effective agents are at using them. | github.com/benchflow-ai/skillsbench |
| first-tree | Open-source agent orchestration for engineers. Put Claude Code, Codex, Cursor and your own agents on one backlog — parallel runs on your keys, review before merge, everything lands as a pull request. | first-tree.aigithub.com/first-tree-ai/first-tree |
| DeepTutor | DeepTutorZotero is a research sources manager based on Zotero, with amazing AI capability powered by DeepTutor. | github.com/KnoWhiz/DeepTutorZotero |
| mews | Represent you to finish all the work, when you are sleeping. | github.com/bingran-you/mews |
| smolclaw | High resolution mock environments for testing and improving claw like agents | github.com/bingran-you/smolclaw |
| SBTI CLI | SBTI CLI - Test SBTI for your agents. | github.com/bingran-you/sbti-cli |
| bem | triangulation, boundary element method (BEM), fast multipole method (FMM) code for python | github.com/HaeffnerLab/bem |
| artiq_photonics_integration | ARTIQ Control Framework (ACF) of Photonics Integration | github.com/HaeffnerLab/artiq_photonics_integration |