AIAny
AI Client2022
Icon for item

TextGen

A local, offline web UI and API for running and interacting with LLMs (text + vision). Supports multiple backends, tool-calling, fine-tuning and portable builds—designed for private, offline use and flexible model/backend switching.

Introduction

Running large language models locally has moved from niche tinkering to a practical requirement for privacy, latency, and reproducibility. TextGen (text-generation-webui) is a community-driven local LLM interface that treats the machine as the single source of truth: you can load GGUF/Transformers/ExLlama/TensorRT models, attach images, call tools, and iterate on training — all without leaving your machine.

What Sets It Apart
  • Multibackend agnostic: swap between llama.cpp, Transformers, ExLlamaV3, TensorRT-LLM and others without restarting. So what: lets you test different loaders/quantizations quickly and pick the best performance/compatibility for your hardware.
  • OpenAI/Anthropic-compatible API + tool-calling: implements familiar Chat/Completions/Messages endpoints and simple python-based tools. So what: existing apps or scripts expecting an OpenAI-compatible API can run locally with minimal changes.
  • Full local feature set (vision, file attachments, LoRA training, image generation): supports multimodal inputs, fine-tuning/resuming LoRA runs, and a dedicated image-generation tab. So what: consolidates common local workflows (inference, RAG inputs, lightweight training) into one UI.
  • Portable & offline-first: offers zero-install portable builds and a one‑click installer for full features. So what: lowers the barrier to try local models on different OSes while keeping telemetry and external calls disabled by default.
Who It's For & Trade-offs

Great fit if you want a flexible local LLM platform for experimentation, private deployments, or small-scale fine-tuning—developers, researchers, and hobbyists who can manage GPU/driver complexity. Not ideal if you need a managed, hosted service or a turnkey solution for non-technical end users: large models demand GPU memory, disk space (~multiple GBs), and some maintenance (drivers, quantization choices). Also exercise caution with trust_remote_code and any public network exposure; enabling public API or tunnels increases your attack surface.

Where It Fits

Compared with hosted LLM APIs, TextGen trades convenience for control and privacy. Compared with single-backend CLIs, it bundles a full-featured UI, API compatibility, and extensions (voice, TTS, galleries), making it a go-to local interface for people who want both GUI and programmatic access. The project is widely used in the community (repo stars and many extensions) and continues to evolve through community contributions.

More Items

GitHub
AI Agent2026

Provides a lightweight Python harness that turns LLMs into working agents with tool-use, skills, persistent memory, permission controls and multi-agent coordination. Ships with a CLI/React TUI, 43+ built-in tools, a plugin/skill system and the ohmo personal-agent for chat gateways. Best for developers prototyping agent workflows and multi-agent experiments.

GitHub
AI Model2026

Runs the Bonsai family of quantized LLMs locally (including vision-capable 27B): provides scripts and demo UIs to run 1-bit and ternary Bonsai models on macOS (Metal), Linux/Windows (CUDA/Vulkan/ROCm), or CPU, with long context, tool-calling and an optional Open WebUI agent demo.

GitHub
AI Client2025

Turns Chromium into a local-first AI browser with an embedded assistant that can summarise pages, extract structured data, automate web tasks, and run scheduled agents. Built as an open-source Chromium fork with 53+ built-in browser tools, 40+ app integrations, and support for BYO AI keys or fully local models (Ollama / LM Studio).