Upload README.md

README.md

@@ -1,10 +1,25 @@
 ---
 title: README
-emoji: ⚡
-colorFrom: gray
-colorTo: red
+emoji: 🔁
+colorFrom: blue
+colorTo: indigo
 sdk: static
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# EnvLoop Research
+
+EnvLoop builds environments and evaluation for agents. EnvLoop Research publishes the models, benchmarks and code
+behind that work, with pre-registered evaluation and the data needed to check the numbers.
+Homepage: [www.envloop.ai](https://www.envloop.ai) · Contact: [research@envloop.ai](mailto:research@envloop.ai)
+
+## Releases
+
+**PersonaRSI** — a calibrated fast-decision model for personal agents with long-term memory, and the benchmark it was
+evaluated on.
+
+- Paper (PDF): [persona-rsi.pdf](https://github.com/EnvLoop/PersonaRSI/blob/main/docs/tech-report/persona-rsi.pdf)
+- Model: [EnvLoop/PersonaRSI-27B-LoRA](https://huggingface.co/EnvLoop/PersonaRSI-27B-LoRA) (gated, non-commercial research)
+- Benchmark: [EnvLoop/PersonaRSI-Bench](https://huggingface.co/datasets/EnvLoop/PersonaRSI-Bench) (gated, non-commercial research)
+- Leaderboard: [EnvLoop/PersonaRSI-Leaderboard](https://huggingface.co/spaces/EnvLoop/PersonaRSI-Leaderboard)
+- Code and pre-registration: [github.com/EnvLoop/PersonaRSI](https://github.com/EnvLoop/PersonaRSI)