You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+87-39Lines changed: 87 additions & 39 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,8 @@
1
1
# RouteBox
2
2
3
-
macOS menu bar app — LLM API proxy with intelligent routing, real-time monitoring, and cost tracking.
3
+
macOS menu bar app — LLM API proxy with intelligent routing, real-time monitoring, cost tracking, built-in chat, and web search.
4
+
5
+
**v2.3.0** · [Download DMG](https://github.com/createpjf/RouteBox/releases/latest) · MIT License
4
6
5
7
## What it does
6
8
@@ -9,9 +11,12 @@ RouteBox runs a local OpenAI-compatible proxy (`http://localhost:3001/v1`). You
9
11
1.**Routes** requests to the best provider based on your rules (cheapest, fastest, or smartest)
10
12
2.**Tracks** tokens, cost, latency, and savings in real-time
11
13
3.**Manages** multiple provider API keys securely in macOS Keychain
14
+
4.**Chat** directly with any model via the built-in Chat window or Spotlight
15
+
5.**Search** the web in real-time with Brave Search integration
12
16
13
17
```
14
18
Your App → RouteBox (localhost:3001) → OpenAI / Anthropic / Google / DeepSeek / MiniMax / Kimi / FLock.io
19
+
↑ Brave Search results injected as context
15
20
```
16
21
17
22
## Supported Providers
@@ -26,7 +31,66 @@ Your App → RouteBox (localhost:3001) → OpenAI / Anthropic / Google / Dee
26
31
|[Kimi](https://kimi.ai)| Kimi K2.5, Kimi K2, Moonshot |[platform.moonshot.ai](https://platform.moonshot.ai/)|
27
32
|[FLock.io](https://flock.io)| Qwen3-235B, Qwen3-30B, DeepSeek-V3.2, Kimi K2.5 |[platform.flock.io](https://platform.flock.io)|
28
33
29
-
> **Tip:**[FLock API Platform](https://platform.flock.io) provides access to open-source models (Qwen3, DeepSeek, Kimi)— a good option for cost-effective routing.
34
+
**Local models**: Ollama and LM Studio are auto-discovered on your network — no API key needed.
35
+
36
+
> **Tip:**[FLock API Platform](https://platform.flock.io) provides access to open-source models (Qwen3, DeepSeek, Kimi) — a good option for cost-effective routing.
37
+
38
+
## Features
39
+
40
+
### Three Windows
41
+
42
+
| Window | Shortcut | Description |
43
+
|--------|----------|-------------|
44
+
|**Panel**|`⌘⇧R`| Menu bar dashboard — routing, analytics, logs, settings |
45
+
|**Spotlight**|`⌘⇧Space`| Quick floating window — ask a question, get an instant answer |
46
+
|**Chat**| Via panel | Full chat interface with conversation history and sidebar |
47
+
48
+
### Dashboard Tabs
49
+
50
+
| Tab | What it shows |
51
+
|-----|---------------|
52
+
|**Dashboard**| Requests, tokens, cost, savings, traffic sparkline, provider status |
53
+
|**Routing**| Strategy selector, model preferences (pin/exclude), content-aware rules |
54
+
|**Logs**| Full request history with model, provider, latency, cost per request |
55
+
|**Analytics**| Charts for cost trends, provider latency, model usage breakdown |
0 commit comments