Pinned Loading

1. harbor-framework/frontier-bench harbor-framework/frontier-bench Public

   Measuring and evolving with the frontier of agent work

   Python 409 348

2. abundant-ai/swe-marathon abundant-ai/swe-marathon Public

   SWE-Marathon: an ultra long-horizon SWE benchmark

   Rust 116 26

3. stair-lab/kg-gen stair-lab/kg-gen Public

   [NeurIPS '25] Knowledge Graph Generation from Any Text

   Python 1.2k 195

4. BasedHardware/omi BasedHardware/omi Public

   AI that sees your screen, listens to your conversations and tells you what to do

   Dart 13.1k 2.1k

5. rl-scaling-laws rl-scaling-laws Public

   qwen3-base family of models RL on gsm8k using verl, is there an RL power law on downstream tasks?

   Python 27 1

6. harbor-framework/harbor harbor-framework/harbor Public

   Framework for evaluating and improving agents

   Python 3.6k 1.4k