big-AGI

LLM Frameworks

AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Includes AI personas, AGI functions, world-class Beam multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud.

Track releases GitHub Website

TypeScript Latest v2.0.5 · 21d ago Security brief →

Features

Multi‑model AI workspace supporting Beam & Merge for de‑hallucination and native search
Best‑in‑class AI chat UX with clean, highly customizable interface
Local‑first architecture delivering zero‑latency performance

Recent releases

View all 6 releases →

No immediate action

v2.0.5 New feature 21d

Gemini Deep Research resumability

Open

v2.0.4 New feature 2mo

Notable features

Anthropic Opus 4.6, Sonnet 4.6 support
AWS Bedrock integration
API-validated model parameters

View release on GitHub

v2.0.3 New feature 4mo

Notable features

Google Drive integration
xAI Responses native support
Kimi K2.5 with reasoning

View release on GitHub

v2.0.2 New feature 6mo

Notable features

Speex multi-vendor TTS (Web Speech API, LocalAI, ElevenLabs, OpenAI)
Claude Opus 4.5 support
Starred models for quick access

Full changelog

Big-AGI 2.0.2 - Speex

What's New

Speex: Multi-Vendor Speech Synthesis

A complete redesign of text-to-speech with support for multiple providers:

Web Speech API - Zero-config browser-native voices (works offline)
LocalAI - Self-hosted TTS with Kokoro, Bark, Piper backends
ElevenLabs - High-quality voice synthesis and cloning
OpenAI TTS - gpt-4o-mini-tts with voice instructions, plus tts-1 and tts-1-hd

Engines auto-detect from your configured LLM services—no duplicate API key entry. Priority-based fallback ensures speech always works.