AIChat

Stale

GitHub Rust Apache-2.0

Description

All-in-one LLM CLI tool with Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, supporting OpenAI, Claude, Gemini, Ollama, Groq, and more.

Key Features

Supports 20+ LLM providers: OpenAI, Claude, Gemini, Ollama, Groq, Deepseek, and more
Shell assistant — describe tasks in natural language, get precise shell commands
Interactive Chat-REPL with tab autocompletion, multi-line input, and history search
RAG integration for document-aware conversations
Function calling, AI tools, MCP support, and AI agents (CLI version of OpenAI GPTs)
Built-in HTTP server with Chat Completions API, LLM Playground, and LLM Arena

Use Cases

💡 Convert natural language tasks into shell commands across any OS

💡 Build conversational AI workflows with session context and roles

💡 Index and query local documents using RAG for contextual answers

💡 Compare LLM outputs side-by-side using the built-in Arena

💡 Expose a unified LLM proxy API for downstream applications

Strengths & Limitations

✅ Strengths

• High community interest (10.4k stars)
• Permissive open-source license (Apache-2.0)
• Established track record (3 years in production)
• Responsive to issues, low backlog

Quick Start

brew install aichat (or cargo install aichat) → set OPENAI_API_KEY env var → aichat (starts REPL) → or: aichat 'list all files in current directory'

Visit GitHub

Related Projects

Deep Research Web UI

2.2k · TypeScript

Active A

An AI-powered research assistant web UI that performs iterative, deep research on any topic by combining search engines with LLM reasoning.

typescriptagentllm +3

· Client-side mode with API keys staying locally in the browser for maximum security
· Real-time streaming AI responses with search visualization using tree structure
· Multi-language web search support via Tavily, Firecrawl, and Google PSE providers

View on GitHub

Speech-to-Speech

12.6k · Python

Active A+

Build local voice agents with open-source models. An end-to-end speech-to-speech pipeline from HuggingFace for fully local voice AI agent deployment.

voicepythonllm +2

· Fully open modular speech-to-speech pipeline: VAD → STT → LLM → TTS
· Multiple STT backends: Whisper, Parakeet TDT (sub-100ms), Lightning Whisper MLX
· Flexible LLM integration: HuggingFace Transformers, mlx-lm, OpenAI API

View full details → View on GitHub

Text Generation WebUI

47.5k · Python

Normal A

Text Generation WebUI is oobabooga's all-in-one local LLM desktop tool supporting text, vision, tool calling and agent workflows.

local-llmchat-uidesktop +2

· Web-based UI — fully featured interface out of the box
· Multi-model — GGUF, GPTQ, AWQ, EXL2 formats
· Tool calling — OpenAI-style function calling and execution

View full details → View on GitHub

Langchain-Chatchat

38.5k · Python

Stale B

A local knowledge base RAG and Agent application platform built on Langchain with support for ChatGLM, Qwen, Llama and other LLMs, offering conversation, knowledge base management, and agent capabilities.

ragllmpython +3

· Local knowledge base QA — Document loading, text splitting, vectorization and semantic retrieval via Langchain with BM25+KNN hybrid search
· Multi-framework model inference — Supports Xinference, Ollama, FastChat, LocalAI for GLM-4, Qwen2, Llama3 and more
· Agent tool calling — Optimized for ChatGLM3/Qwen with auto tool selection, single tool parameter parsing, and multimodal image chat

View full details → View on GitHub

AIChat

Description

Key Features

Use Cases

Strengths & Limitations

✅ Strengths

Tags

Categories

Quick Start

Related Projects

Deep Research Web UI

Speech-to-Speech

Text Generation WebUI

Langchain-Chatchat