Pinned Loading

1. browser-use-vision browser-use-vision Public

   Vision-grounding plugin for browser-use agents with SoM, Florence-2, Vision–DOM alignment, adaptive visual context, and objective evaluation.

   Python 88 1

2. voice2task-posttraining voice2task-posttraining Public

   Evidence-first post-training and evaluation for Chinese ASR commands to schema-valid browser task contracts.

   Python

3. hermes-skilleval hermes-skilleval Public

   Verification-gated skill routing and self-improvement harness for Hermes-style agent skills

   Python

4. manual-rag-agent manual-rag-agent Public

   Citation-grounded RAG with evidence traces, abstention verification, retrieval/reranking baselines, and fail-closed evaluation gates.

   Python

5. voice-browser-agent voice-browser-agent Public

   Bounded Chinese-first Voice-to-Browser Agent with safe browser execution traces.

   Python