Upload README.md

README.md

@@ -1,5 +1,5 @@
 ---
-title: Chan Compass · US Stocks
+title: Chan Compass · US
 emoji: 🧭
 colorFrom: blue
 colorTo: purple
@@ -8,9 +8,17 @@ app_port: 7860
 pinned: false
 license: mit
 short_description: Local Chan-theory US stock signals, fine-tuned 1.7B
+tags:
+  - build-small-hackathon
+  - backyard-ai
+  - off-brand
+  - tiny-titan
+  - best-agent
+  - best-demo
+  - bonus-quest-champion
 ---
 
-# 🧭 Chan Compass — US Stocks
+# 🧭 Chan Compass — US Edition
 
 Multi-timeframe **缠论 (Chan theory)** signal engine for US stocks — monthly → weekly →
 daily → 60m → 30m → 15m → 5m → 1m **nested-interval (区间套) confirmation** — plus a
@@ -101,28 +109,34 @@ recomputes just that view.)
 convert to GGUF, push to the Hub, and point `MODEL_ZOO` at it. The published
 result is already wired in as the **Interpreter sub-agent**.
 
-## Hackathon badge checklist
-
-🔌 **Off the Grid** — all inference local, zero cloud APIs · 🦙 **Llama Champion** —
-Qwen3 GGUF through the llama.cpp runtime (installed at first run into `/data/pylibs`
-to dodge the build-container OOM) · 🐜 **Tiny Titan** — the everyday language work
-(Signals summary, rotation narrative, news briefs) all runs on **1.7B** models, and
-the Interpreter sub-agent is a **fine-tuned 1.7B** · 🤖 **Best Agent** — the multi-agent
-Auto Research desk (parallel evidence tools + Analyst/Reporter writing in parallel,
-every step logged) · 📡 **Sharing is Caring** — each research run writes a full JSON
-agent trace (PLAN -> each tool call + result -> each sub-agent request/response),
-**published as a Hub dataset**:
-[`ranranrunforit/chan-compass-agent-traces`](https://huggingface.co/datasets/ranranrunforit/chan-compass-agent-traces)
-(one click from the Automation tab) · 🎨 **Off-Brand** — a hand-built **React +
-Spectrum 2** frontend served by `gradio.Server` (the app's own HTML/CSS/JS, not the
-default Gradio component render) · 🎯 **Well-Tuned** — a published fine-tuned model
-(`ranranrunforit/chan-compass-qwen3-1.7b-gguf`) the app actually uses · 📓 **Field
-Notes** — a write-up of the build:
-[blog post](https://huggingface.co/blog/build-small-hackathon/chan-compass).
+## Hackathon track & badges
+
+**Track — 🏡 Backyard AI.** A real tool for real people: my family's nightly
+Chan-theory routine, automated and made readable.
+
+Bonus badges this build targets:
+
+🎨 **Off Brand** — a hand-built **React + Spectrum 2** frontend served by
+`gradio.Server` (the app's own HTML/CSS/JS, not the default Gradio component
+render). · 🐜 **Tiny Titan** — the everyday language work (Signals interpret,
+rotation narrative, news briefs) all runs on **1.7B** models, and the Interpreter
+sub-agent is a **fine-tuned 1.7B** (≤ 4B). · 🤖 **Best Agent** — the multi-agent
+Auto Research desk: PLAN → parallel evidence tools → Analyst + Reporter writing
+different sections at once, every step logged. · 🎬 **Best Demo** — app + demo
+video + social posts (links below). · 🏆 **Bonus Quest Champion** — stacking the
+above plus the extras below.
+
+Extra credentials (beyond the current badge list): all inference is **local via
+llama.cpp**, zero cloud APIs; a **published fine-tuned model**
+(`ranranrunforit/chan-compass-qwen3-1.7b-gguf`) the app actually uses; and each
+research run writes a full JSON agent trace, **published as a Hub dataset**
+([`ranranrunforit/chan-compass-agent-traces`](https://huggingface.co/datasets/ranranrunforit/chan-compass-agent-traces),
+one click from the Automation tab); plus a build write-up
+([blog post](https://huggingface.co/blog/build-small-hackathon/chan-compass)).
 
 > Show, Don't Tell: 🎬 [demo video](https://www.youtube.com/watch?v=Ynwdzsf_KBA) ·
-> 📣 social posts: [post 1](https://x.com/ranranrunforit/status/2066096644135764377),
-> [post 2](https://x.com/ranranrunforit/status/2066217978773782669).
+> 📣 social posts [1](https://x.com/ranranrunforit/status/2066096644135764377),
+> [2](https://x.com/ranranrunforit/status/2066217978773782669).
 
 ## Architecture (🎨 Off-Brand)
 
@@ -167,4 +181,4 @@ analyzer cache · `data_us.py` — yfinance loader · `signal_runner.py` · `rot
 `llm_local.py` · `emailer.py` · `finetune_data.py` · `trace_publish.py` · `server.py` (the gr.Server entry) · `ui_kits/chan-compass/` (the React frontend) ·
 `finetune/` — the fine-tuning notebook + guide.
 
-*Built with Love for My Family.*
+*Educational tool — not investment advice.*