Add README.md

README.md

@@ -0,0 +1,32 @@
+# deepagents-rl
+
+Post-train a small coding LM with **GRPO** + verifiable unit-test rewards, using:
+
+- Local **deepagents-style** harness smoke (`scripts/smoke_e2e.py`)
+- **Langfuse** traces (every tool + checkpoint eval)
+- **Weights & Biases** metrics
+- **Hugging Face** adapters (`vanishingradient/deepagents-rl-coding`)
+- **Kaggle T4×2** training (`notebooks/kaggle_grpo.ipynb`)
+
+## Checkpoint rule
+
+Before every HF checkpoint push: run held-out eval → write **Langfuse** `kaggle-ckpt-eval` → log W&B → then push revision `grpo-step-{n}`.
+
+## Quick start
+
+```bash
+# local smoke (model on :8792)
+python scripts/smoke_e2e.py
+
+# build + push MBPP dataset
+python scripts/prepare_mbpp_and_push.py
+
+# upload trainer to HF for Kaggle download
+python scripts/push_trainer_to_hf.py
+```
+
+Then open the Kaggle notebook with **GPU T4 x2** and attach secrets — see [`kaggle/KAGGLE_SETUP.md`](kaggle/KAGGLE_SETUP.md).
+
+## Dataset
+
+`vanishingradient/deepagents-rl-mbpp` — filtered MBPP sanitized (reference must pass sandbox).