Versions:

0.0.158
0.0.157
0.0.156
0.0.155
0.0.154
0.0.152
0.0.151
0.0.150
0.0.148
0.0.146
0.0.145
0.0.144
0.0.142
0.0.141
0.0.138
0.0.137
0.0.136
0.0.135
0.0.134
0.0.133
0.0.132
0.0.131
0.0.130
0.0.129
0.0.128
0.0.127
0.0.126
0.0.125
0.0.124
0.0.123
0.0.122
0.0.121
0.0.120
0.0.119
0.0.118
0.0.117
0.0.116
0.0.115
0.0.114
0.0.113
0.0.111
0.0.110
0.0.109
0.0.107
0.0.106
0.0.105
0.0.104
0.0.103
0.0.101
0.0.100
0.0.99
0.0.98
0.0.97
0.0.95
0.0.94
0.0.93
0.0.92
0.0.91
0.0.90
0.0.89
0.0.88
0.0.87
0.0.85

AQBot, published by aqbot and currently at version 0.0.158 with 63 released versions, is a lightweight, high-performance, cross-platform desktop client that combines AI conversation capabilities with a local AI gateway. Falling into the AI assistant and developer tools category, it supports multiple providers including OpenAI, Anthropic Claude, and Google Gemini, along with any OpenAI-compatible API, and offers model management with remote model list retrieval and custom parameters such as temperature, max tokens, and top-p. Users can configure multiple API keys per provider with automatic rotation, view streaming token-by-token output with collapsible thinking blocks, switch between multiple versions of replies, and branch conversations from any message node for comparison. An Agent mode allows the AI to autonomously perform multi-step tasks such as reading and writing files, running commands, and analyzing code, governed by three permission levels, a working-directory sandbox, a tool approval panel, and per-session token and cost tracking. Content rendering includes full Markdown with code highlighting, LaTeX, tables, and task lists, an embedded Monaco code editor with diff preview, Mermaid and D2 diagram rendering, and an Artifact panel for code, HTML, and notes. Search and knowledge features cover web search via Tavily, Zhipu WebSearch, and Bocha with cited sources, local RAG knowledge bases with automatic document parsing and semantic retrieval, a multi-namespace memory system, and flexible context attachment. The client implements the Model Context Protocol over stdio and HTTP with built-in MCP tools, while its local API gateway exposes OpenAI-, Claude-, and Gemini-compatible endpoints with API key management, usage statistics, SSL/TLS support, request logging, and configuration templates for common CLI tools. Sensitive data such as API keys is stored locally with AES-256 encryption.

Tags:

人工智能 48

大语言模型 49

聊天机器人 26