osagent 0.2.80 → 0.2.82
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 +12 -0
- package/cli.js +16430 -23885
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -318,8 +318,20 @@ osagent /init
|
|
|
318
318
|
|
|
319
319
|
### Cloud Models (Ollama Cloud)
|
|
320
320
|
- `qwen3-coder:480b-cloud` - Most powerful (256K context)
|
|
321
|
+
- `kimi-k2.5:cloud` - High-performance coding model (131K context)
|
|
321
322
|
- `qwen3-coder:30b` - Efficient (30B params, 3.3B active)
|
|
322
323
|
|
|
324
|
+
### GROQ (Fast Inference)
|
|
325
|
+
- `moonshotai/kimi-k2-instruct-0905` - Best coding model (256K context, ~200 tok/s)
|
|
326
|
+
- `moonshotai/kimi-k2-instruct` - Kimi K2 (256K context)
|
|
327
|
+
- `llama-3.3-70b-versatile` - Versatile general coding
|
|
328
|
+
- `llama-3.1-8b-instant` - Ultra-fast for simple tasks
|
|
329
|
+
|
|
330
|
+
### Anthropic
|
|
331
|
+
- `claude-opus-4-5-20251101` - Most powerful
|
|
332
|
+
- `claude-sonnet-4-5-20250929` - Best balance (recommended)
|
|
333
|
+
- `claude-haiku-4-5-20251001` - Fastest
|
|
334
|
+
|
|
323
335
|
### Local Models (Ollama)
|
|
324
336
|
- `qwen2.5-coder:32b` - Best local coding model (~20GB VRAM)
|
|
325
337
|
- `qwen2.5-coder:14b` - Great balance (~10GB VRAM)
|