agentgui 1.0.578 → 1.0.579

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 (2) hide show
  1. package/README.md +86 -16
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -1,18 +1,24 @@
1
1
  # AgentGUI
2
2
 
3
+ [![npm version](https://img.shields.io/npm/v/agentgui?color=brightgreen)](https://www.npmjs.com/package/agentgui)
4
+ [![npm downloads](https://img.shields.io/npm/dw/agentgui?color=brightgreen)](https://www.npmjs.com/package/agentgui)
5
+ [![license](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
6
+ [![GitHub Pages](https://img.shields.io/badge/docs-live-blue)](https://anentrypoint.github.io/agentgui/)
7
+
3
8
  Multi-agent GUI client for AI coding agents (Claude Code, Gemini CLI, OpenCode, Goose, etc.) with real-time streaming, WebSocket sync, and SQLite persistence.
4
9
 
5
10
  ![Main Interface](docs/screenshot-main.png)
6
11
 
7
12
  ## Features
8
13
 
9
- - **Real-time Agent Execution** - Watch agents work with streaming output and tool calls
10
- - **Multi-Agent Support** - Switch between Claude Code, Gemini CLI, OpenCode, Kilo, and more
11
- - **Session Management** - Full conversation history with SQLite persistence
12
- - **WebSocket Sync** - Live updates across multiple clients
13
- - **Voice Integration** - Speech-to-text and text-to-speech support
14
- - **Tool Management** - Install and update agent plugins from the UI
15
- - **File Browser** - Explore and manage conversation files
14
+ - 🤖 **Multi-Agent Support** - Switch between Claude Code, Gemini CLI, OpenCode, Kilo, and more from one interface
15
+ - **Real-Time Streaming** - Watch agents work with live streaming output and tool calls via WebSocket
16
+ - 💾 **Session Persistence** - Full conversation history stored in SQLite with WAL mode
17
+ - 🔄 **WebSocket Sync** - Live updates across multiple clients with automatic reconnection
18
+ - 🎤 **Voice Integration** - Speech-to-text and text-to-speech powered by Hugging Face Transformers (no API keys)
19
+ - 🛠️ **Tool Management** - Install and update agent plugins directly from the UI
20
+ - 📁 **File Browser** - Drag-and-drop uploads, direct file editing, and context-aware operations
21
+ - 🔌 **Developer Friendly** - Hot reload, REST API, WebSocket endpoints, and extensible plugin system
16
22
 
17
23
  ### Screenshots
18
24
 
@@ -30,7 +36,17 @@ Multi-agent GUI client for AI coding agents (Claude Code, Gemini CLI, OpenCode,
30
36
 
31
37
  ## Quick Start
32
38
 
39
+ ### Using npx (Recommended)
40
+
41
+ ```bash
42
+ npx agentgui
43
+ ```
44
+
45
+ ### Manual Installation
46
+
33
47
  ```bash
48
+ git clone https://github.com/AnEntrypoint/agentgui.git
49
+ cd agentgui
34
50
  npm install
35
51
  npm run dev
36
52
  ```
@@ -39,9 +55,11 @@ Server starts on `http://localhost:3000/gm/`
39
55
 
40
56
  ## System Requirements
41
57
 
42
- - Node.js 18+
58
+ - Node.js 18+ (LTS recommended)
43
59
  - SQLite 3
44
60
  - Modern browser (Chrome, Firefox, Safari, Edge)
61
+ - At least one AI coding agent installed (Claude Code, Gemini CLI, etc.)
62
+ - Optional: Python 3.9+ for text-to-speech on Windows
45
63
 
46
64
  ## Architecture
47
65
 
@@ -62,37 +80,89 @@ static/js/websocket-manager.js WebSocket connection handling
62
80
  ### Key Details
63
81
 
64
82
  - Agent discovery scans PATH for known CLI binaries at startup
65
- - Database lives at `~/.gmgui/data.db`
66
- - WebSocket endpoint at `/gm/sync`
67
- - ACP tools (OpenCode, Kilo) auto-launch as HTTP servers on startup
83
+ - Database lives at `~/.gmgui/data.db` (WAL mode for concurrent access)
84
+ - WebSocket endpoint at `/gm/sync` for real-time updates
85
+ - ACP tools (OpenCode, Kilo) auto-launch as HTTP servers on startup with health checks
68
86
 
69
87
  ## REST API
70
88
 
71
89
  All routes prefixed with `/gm`:
72
90
 
91
+ **Conversations:**
73
92
  - `GET /api/conversations` - List conversations
74
93
  - `POST /api/conversations` - Create conversation
75
94
  - `GET /api/conversations/:id` - Get conversation with streaming status
76
95
  - `POST /api/conversations/:id/messages` - Send message
96
+ - `DELETE /api/conversations/:id` - Delete conversation
97
+
98
+ **Agents & Tools:**
77
99
  - `GET /api/agents` - List discovered agents
78
100
  - `GET /api/tools` - List detected tools with installation status
79
101
  - `POST /api/tools/:id/install` - Install tool
80
- - `POST /api/stt` - Speech-to-text
81
- - `POST /api/tts` - Text-to-speech
102
+ - `POST /api/tools/:id/update` - Update tool
103
+
104
+ **Speech:**
105
+ - `POST /api/stt` - Speech-to-text (raw audio input)
106
+ - `POST /api/tts` - Text-to-speech (returns audio)
107
+ - `GET /api/speech-status` - Check model download progress
108
+
109
+ **WebSocket:** `/gm/sync` - Subscribe to conversation/session updates with events like `streaming_start`, `streaming_progress`, `streaming_complete`
82
110
 
83
111
  ## Environment Variables
84
112
 
85
113
  - `PORT` - Server port (default: 3000)
86
114
  - `BASE_URL` - URL prefix (default: /gm)
87
115
  - `STARTUP_CWD` - Working directory passed to agents
116
+ - `HOT_RELOAD` - Enable watch mode (default: true)
117
+
118
+ ## Troubleshooting
119
+
120
+ ### Server Won't Start
121
+ - Check if port 3000 is in use: `lsof -i :3000` (macOS/Linux) or `netstat -ano | findstr :3000` (Windows)
122
+ - Try a different port: `PORT=4000 npm run dev`
123
+
124
+ ### Agent Not Detected
125
+ - Verify agent is installed: `which claude` / `where claude`
126
+ - Check PATH includes agent binary location
127
+ - Restart server after installing new agents
128
+
129
+ ### WebSocket Connection Failed
130
+ - Verify BASE_URL matches your deployment
131
+ - Check browser console for errors
132
+ - Ensure no firewall blocking WebSocket connections
133
+
134
+ ### Speech Models Not Downloading
135
+ - Check internet connection and firewall
136
+ - Verify `~/.gmgui/models/` is writable
137
+ - Monitor progress via `/api/speech-status` endpoint
88
138
 
89
139
  ## Development
90
140
 
91
141
  ```bash
92
- npm run dev # Start with watch mode
93
- npm start # Production mode
142
+ npm run dev # Start with watch mode and hot reload
143
+ npm start # Production mode (no watch)
144
+ npm test # Run tests (if available)
94
145
  ```
95
146
 
147
+ Hot reload is enabled by default. File changes trigger automatic restart without losing state.
148
+
149
+ ## Contributing
150
+
151
+ Contributions welcome! Please:
152
+
153
+ 1. Fork the repository
154
+ 2. Create a feature branch (`git checkout -b feature/amazing-feature`)
155
+ 3. Commit your changes (`git commit -m 'Add amazing feature'`)
156
+ 4. Push to the branch (`git push origin feature/amazing-feature`)
157
+ 5. Open a Pull Request
158
+
159
+ ## Links
160
+
161
+ - **GitHub:** https://github.com/AnEntrypoint/agentgui
162
+ - **npm:** https://www.npmjs.com/package/agentgui
163
+ - **Documentation:** https://anentrypoint.github.io/agentgui/
164
+ - **Issues:** https://github.com/AnEntrypoint/agentgui/issues
165
+
96
166
  ## License
97
167
 
98
- MIT
168
+ MIT © [AnEntrypoint](https://github.com/AnEntrypoint)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "agentgui",
3
- "version": "1.0.578",
3
+ "version": "1.0.579",
4
4
  "description": "Multi-agent ACP client with real-time communication",
5
5
  "type": "module",
6
6
  "main": "server.js",