Fix loop diagram alignment

README.md

@@ -1,3 +1,4 @@
+
 ---
 title: Tiny Computer Agent
 emoji: 🖱️
@@ -27,13 +28,14 @@ same machine it is controlling.
 ## The idea, in one loop
 
 ```
-   observe          think            act            verify
-  ┌────────┐      ┌─────────┐     ┌─────────┐     ┌─────────┐
-  │ screen │──────▶│  tiny   │─────▶│ mouse / │─────▶│ next    │
-  │ frame  │      │  model  │     │ keyboard│     │ frame   │
-  └────────┘      └─────────┘     └─────────┘     └────┬────┘
-                                                              │
-                          ◀──────────────────────────────────────┘
+    observe         think          act           verify
+  +---------+    +---------+    +---------+    +---------+
+  | screen  |--->|  tiny   |--->| mouse / |--->|  next   |
+  |  frame  |    |  model  |    | keyboard|    |  frame  |
+  +---------+    +---------+    +---------+    +----+----+
+                                                    |
+  <-------------------------------------------------+
+        repeat until done, or the step budget runs out
 ```
 
 1. **Observe** — grab the screen, downscale it, optionally attach OCR text or the
@@ -51,43 +53,43 @@ The harness does the heavy lifting, so the model does not have to be clever:
 | Job | Who does it |
 |---|---|
 | Finding *where* a button is | OCR / accessibility tree / element index — not the model |
-| Choosing *what* to do | tiny VLM over a **closed action menu** (click, type, key, scroll, wait, done) |
-| Knowing if it worked | the next screenshot, plus harness-side checks |
-| Recovering from a bad step | retry policy in `loop.py`, not in the weights |
+| Choosing *what* to do | a tiny VLM over a **closed action menu** (click, type, key, scroll, wait, done) |
+| Knowing whether it worked | the next frame, plus harness-side checks |
+| Recovering from a bad step | the retry policy in `loop.py`, not the weights |
 
-That keeps the agent offline, instant to start, and small enough that a laptop
-GPU (or plain CPU) is enough to run it — on the same box it is controlling.
+That keeps the agent offline, fast to start, and small enough that a laptop GPU
+(or plain CPU) can run it on the same box it is controlling.
 
 ## Candidate backends
 
-Pluggable behind one interface; nothing here requires a network call at run time.
+Pluggable behind one interface; nothing here needs a network call at run time.
 
-- **Moondream 2** / **SmolVLM-256M / 500M** — ~hundreds of MB, safe default
+- **Moondream 2** / **SmolVLM-256M / 500M** — a few hundred MB, safe default
 - **Qwen2-VL-2B-Instruct**, **Florence-2-base** — stronger grounding, still tiny
 - **OCR + text-only planner** — no VLM at all; the cheapest credible baseline
-- **mock brain** — deterministic scripted actions, used for harness tests
+- **mock brain** — deterministic scripted actions, used to test the harness itself
 
 ## Intended layout
 
 ```
 tiny-computer-agent/
-├─ README.md
-├─ tiny_computer_agent.py          # marimo notebook: drive/watch the loop
-├─ src/tiny_computer_agent/
-│  ├─ observe.py   # screen capture + OCR / accessibility tree
-│  ├─ brain.py     # model backends behind one interface
-│  ├─ act.py       # action vocabulary + pyautogui / xdotool executor
-│  ├─ loop.py      # observe → think → act → verify
-│  └─ safety.py    # dry-run, allow/deny lists, kill switch, step budget
-└─ LICENSE
+├── README.md
+├── tiny_computer_agent.py          # marimo notebook: drive / watch the loop
+├── src/tiny_computer_agent/
+│   ├── observe.py   # screen capture + OCR / accessibility tree
+│   ├── brain.py     # model backends behind one interface
+│   ├── act.py       # action vocabulary + pyautogui / xdotool executor
+│   ├── loop.py      # observe → think → act → verify
+│   └── safety.py    # dry-run, allow/deny lists, kill switch, step budget
+└── LICENSE
 ```
 
 ## Safety, because this thing has your mouse
 
-- Run it in a **VM, container, or throwaway desktop account**, never your real session.
+- Run it in a **VM, container, or throwaway desktop account** — not your real session.
 - `--dry-run` logs every action without executing it, so you can read the plan first.
 - Deny-list for shells, terminals, payment flows and password managers.
-- Step budget + a global hotkey kill switch before anything touches the pointer.
+- A step budget plus a global hotkey kill switch before anything touches the pointer.
 - **Local-first, for real:** screen pixels and keystrokes never leave the machine.
 
 ## Roadmap
@@ -96,7 +98,7 @@ tiny-computer-agent/
 - [ ] OCR / AT-SPI element index, and click-by-element instead of click-by-pixel
 - [ ] tiny-VLM grounding backend (transformers + llama.cpp GGUF)
 - [ ] marimo UI: live screen preview, action log, pause / resume / step
-- [ ] append-only run traces so failed episodes can be replayed and scored
+- [ ] append-only run traces, so failed episodes can be replayed and scored
 
 ## License