open-agents-ai 0.18.0 → 0.19.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +22 -4
- package/dist/index.js +851 -425
- package/dist/scripts/live-whisper.py +242 -0
- package/dist/scripts/start-moondream.py +112 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -32,6 +32,7 @@ An autonomous multi-turn tool-calling agent that reads your code, makes changes,
|
|
|
32
32
|
- **35 autonomous tools** — file I/O, shell, grep, web search/fetch, memory, sub-agents, background tasks, image/OCR, git, diagnostics, vision, desktop automation, structured files, code sandbox
|
|
33
33
|
- **Moondream vision** — see and interact with the desktop via Moondream VLM (caption, query, detect, point-and-click)
|
|
34
34
|
- **Desktop automation** — vision-guided clicking: describe a UI element in natural language, the agent finds and clicks it
|
|
35
|
+
- **Auto-install desktop deps** — screenshot, mouse, OCR, and image tools auto-install missing system packages (scrot, xdotool, tesseract, imagemagick) on first use
|
|
35
36
|
- **Parallel tool execution** — read-only tools run concurrently via `Promise.allSettled`
|
|
36
37
|
- **Sub-agent delegation** — spawn independent agents for parallel workstreams
|
|
37
38
|
- **Ralph Loop** — iterative task execution that keeps retrying until completion criteria are met
|
|
@@ -226,10 +227,27 @@ python3 -m venv .moondream-venv
|
|
|
226
227
|
|
|
227
228
|
The vision tools auto-detect a running Moondream Station on `localhost:2020`. For cloud inference, set `MOONDREAM_API_KEY` instead.
|
|
228
229
|
|
|
229
|
-
**System
|
|
230
|
-
|
|
231
|
-
|
|
232
|
-
|
|
230
|
+
**System dependencies (auto-installed on first use):**
|
|
231
|
+
|
|
232
|
+
Desktop tools automatically install missing system packages when first needed. No manual setup required — just use the tool and it handles the rest:
|
|
233
|
+
|
|
234
|
+
| Tool | Linux Package | What It Does |
|
|
235
|
+
|------|--------------|-------------|
|
|
236
|
+
| `scrot` | `apt install scrot` | Screenshot capture |
|
|
237
|
+
| `xdotool` | `apt install xdotool` | Mouse/keyboard automation |
|
|
238
|
+
| `tesseract` | `apt install tesseract-ocr` | OCR text extraction |
|
|
239
|
+
| `identify` | `apt install imagemagick` | Image dimensions/conversion |
|
|
240
|
+
|
|
241
|
+
Supports `apt` (Debian/Ubuntu), `dnf` (Fedora), `pacman` (Arch), and `brew` (macOS). You can also pre-install everything at once:
|
|
242
|
+
|
|
243
|
+
```bash
|
|
244
|
+
./scripts/setup-desktop.sh # Install all desktop deps
|
|
245
|
+
./scripts/setup-desktop.sh --check-only # Just check what's missing
|
|
246
|
+
```
|
|
247
|
+
|
|
248
|
+
**Vision backend:**
|
|
249
|
+
- Moondream Station (local) — runs entirely on your machine, no API keys needed
|
|
250
|
+
- Moondream Cloud API — set `MOONDREAM_API_KEY` for cloud inference
|
|
233
251
|
|
|
234
252
|
## Interactive TUI
|
|
235
253
|
|