@hyperlite-ai/win32-x64 0.1.1
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 +45 -0
- package/hl.exe +0 -0
- package/package.json +15 -0
package/README.md
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
# HyperLite
|
|
2
|
+
|
|
3
|
+
A terminal-native local LLM chat client. Fast, offline, and agentic — runs entirely on your machine using [Ollama](https://ollama.com).
|
|
4
|
+
|
|
5
|
+
## Install
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
npm install -g hyperlite-ai
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
## Run
|
|
12
|
+
|
|
13
|
+
```bash
|
|
14
|
+
hyperlite
|
|
15
|
+
```
|
|
16
|
+
|
|
17
|
+
## Requirements
|
|
18
|
+
|
|
19
|
+
- [Ollama](https://ollama.com) installed and running
|
|
20
|
+
- A downloaded model (e.g. `ollama pull qwen2.5-coder:14b`)
|
|
21
|
+
- Node.js 16+
|
|
22
|
+
|
|
23
|
+
## Features
|
|
24
|
+
|
|
25
|
+
- Chat with any local Ollama model
|
|
26
|
+
- Agentic coding tools — read, write, edit, search files directly from chat
|
|
27
|
+
- Multi-session history with persistent storage
|
|
28
|
+
- Tabbed command palette (Ctrl+P)
|
|
29
|
+
- Visual folder browser (Ctrl+O) — open any repo as working directory
|
|
30
|
+
- Download models from inside the app
|
|
31
|
+
- Syntax-highlighted responses with markdown rendering
|
|
32
|
+
- Hardware detection — recommends models for your GPU/RAM
|
|
33
|
+
|
|
34
|
+
## Supported Platforms
|
|
35
|
+
|
|
36
|
+
| Platform | Architecture |
|
|
37
|
+
|----------|-------------|
|
|
38
|
+
| Windows | x64 |
|
|
39
|
+
| Linux | x64 |
|
|
40
|
+
| macOS | Apple Silicon (arm64) |
|
|
41
|
+
| macOS | Intel (x64) |
|
|
42
|
+
|
|
43
|
+
## Source
|
|
44
|
+
|
|
45
|
+
[github.com/Sean504/HyperLite](https://github.com/Sean504/HyperLite)
|
package/hl.exe
ADDED
|
Binary file
|