@sourcegraph/amp 0.0.1764266081-g6d5b8e → 0.0.1764282342-g3292fd

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.
Files changed (3) hide show
  1. package/README.md +3 -2
  2. package/dist/main.js +785 -786
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -2,14 +2,15 @@
2
2
 
3
3
  Amp is a frontier coding agent for your terminal and editor, built by Sourcegraph.
4
4
 
5
- - **Multi-Model:** Sonnet, GPT-5, fast models—Amp uses them all, for what each model is best at.
5
+ - **Multi-Model:** Claude Opus 4.5, GPT-5.1, fast models—Amp uses them all, for what each model is best at.
6
6
  - **Opinionated:** You're always using the good parts of Amp. If we don't use and love a feature, we kill it.
7
7
  - **On the Frontier:** Amp goes where the models take it. No backcompat, no legacy features.
8
8
  - **Threads:** You can save and share your interactions with Amp. You wouldn't code without version control, would you?
9
9
 
10
10
  Amp's agent has 2 modes:
11
11
 
12
- - `smart`: unconstrained state-of-the-art model use (Gemini 3 Pro, GPT-5, and more)
12
+ - `smart`: unconstrained state-of-the-art model use (Claude Opus 4.5, GPT-5.1, and more)
13
+ - `rush`: fast and efficient models for narrowly defined tasks (Claude Haiku 4.5)
13
14
  - `free`: [free of charge](https://ampcode.com/free), using fast basic models
14
15
 
15
16
  <br/>