big-AGI Releases
135 releases of enricoros/big-AGI
- flame-v1.34.0v1.34.0
Adds gesture support for scaling, introduces a linear layout component, and bundles multiple effects into a single CombinedEffect.
Feb 12, 2026
- flame-v1.35.0v1.35.0
Introduces a free-list strategy for SpriteBatch, adds new animation methods, and fixes routing and layout notification issues.
Feb 12, 2026
- v1.35.1
Fixes a tap handling issue where touches starting inside a component and ending outside were not being canceled correctly.
Feb 12, 2026
- v1.3.1
Major update bringing a Web UI, EPUB 3 packaging, GPU-accelerated Supertonic TTS engine, and advanced audiobook features.
Feb 6, 2026
- v2.0.3
This release brings major model updates including Kimi 2.5, Gemini 3 Flash, GPT 5.2, and introduces Google Drive integration for attaching documents plus Inworld speech synthesis with streaming playback.
Feb 2, 2026
- v4.3.5
Addresses two regressions affecting animation capabilities, specifically regarding inline element animation and CSS background color parsing.
Jan 25, 2026
- v4.3.4
Enhances Web Animations API (WAAPI) integration by automatically persisting synced animations and fixes a comment syntax error in the onScroll handler.
Jan 23, 2026
- axum-core-v0.5.6axum-core v0.5.6
Updates error message handling to include diagnostic attributes for improved developer guidance.
Dec 27, 2025
- axum-extra-v0.12.3axum-extra v0.12.3
Updated the typed-routing feature to enable routing and fixed an integer underflow in file stream responses.
Dec 20, 2025
- v2.1.7
Added pause functionality and auto-reload connections, alongside fixes for SPN bootstrapping, mouse navigation crashes, and UI lifecycle issues.
Dec 17, 2025
- v1.2.5
Added support for the UV package manager to simplify setup, introduced a queue setting to override item settings, and resolved various Linux compatibility and dependency issues.
Dec 10, 2025
- v2.0.2
A complete redesign of text-to-speech with multi-vendor support including Web Speech API, LocalAI, ElevenLabs, and OpenAI TTS, along with Claude Opus 4.5 support and starred models for quick access.
Dec 1, 2025
- v1.2.4
Expanded subtitle generation capabilities to non-English languages and integrated spaCy for improved sentence segmentation and better readability.
Nov 28, 2025
- v2.0.1Open v2.0.1
This release adds the latest models including Gemini 3 Pro with code execution, Nano Banana Pro for image generation, and expands image generation support to Azure and LocalAI with improved error resilience.
Nov 24, 2025
- v1.2.3
Enabled audio generation for subtitle files and added cover image embedding for M4B files to enhance media playback.
Nov 18, 2025
- v3.0.9v3.0.9 | fix tag caching Issue from latest security fix breaking PP-AI
Resolved a tag caching issue that caused failures in PP-AI following a recent security fix update.
Nov 4, 2025
- v3.0.8Release v3.0.8 | Security Fix | Updates | Merges
Fixed tag serialization errors, implemented sorting history by tags, and added pre-existing document types to the AI context.
Nov 3, 2025
- 3.4.0
Fixed an issue in the CI pipeline that was incorrectly closing valid issues and updated the project readme documentation.
Oct 28, 2025
- v2.0.0
Major 2.0 release with Beam 2 multi-modal intelligence, professional features including reasoning models and web search, local-first redesign, and introduction of three-tier model (Open, Free, Pro) with cloud sync.
Oct 28, 2025
- v1.2.1
Upgraded the user interface from PyQt5 to PyQt6 and enhanced the queue manager with new file opening options and visual indicators.
Oct 27, 2025