LongMemory Releases

This release introduces a robust Memory Compression Engine to reduce token usage and latency, alongside a VS Code extension that integrates with popular AI tools. It also enhances security with API authentication and rate limiting while optimizing performance through caching and event deduplication.

Oct 30, 2025

Version 1.1.0 expands the backend capabilities by adding support for pluggable vector databases and PostgreSQL, offering greater flexibility in data storage options.

Oct 26, 2025

The initial stable release (v1.0.0) establishes the core functionality by introducing the Model Context Protocol (MCP) for AI integration and adding metadata filtering to queries.

Oct 26, 2025

Ultravox v0.6 introduces new gemma3 and qwen3 model variants, alongside significant improvements in Hindi language understanding and audio robustness. The release also adds support for VoiceBench evaluation and allows for response generation without a user message.

Aug 18, 2025

Minimal release notes: "Release PR https://github.com/neondatabase/neon/pull/12766. Diff with the previous release https://github.com/neondatab"

Jul 29, 2025

Minimal release notes: "Release PR https://github.com/neondatabase/neon/pull/12738. Diff with the previous release https://github.com/neondatab"

Jul 28, 2025

Minimal release notes: "Release PR https://github.com/neondatabase/neon/pull/12737. Diff with the previous release https://github.com/neondatab"

Jul 25, 2025

Minimal release notes: "Release PR https://github.com/neondatabase/neon/pull/12679. Diff with the previous release https://github.com/neondatab"

Jul 22, 2025

Minimal release notes: "Release PR https://github.com/neondatabase/neon/pull/12653. Diff with the previous release https://github.com/neondatab"

Jul 18, 2025

v0.5 significantly improves transcription accuracy by 60% and translation quality by 24%, while expanding language support from 15 to 42 languages. The release also introduces new evaluation metrics like Big Bench Audio and pushes new weights to Hugging Face.

Feb 11, 2025

v0.4.1 upgrades the Whisper encoder to Whisper-large-v3-turbo and adds six new languages (Chinese, Dutch, Hindi, Swedish, Turkish, Ukrainian) to the existing 15 supported languages.

Nov 12, 2024

v0.4 upgrades the Whisper encoder from Whisper-small to Whisper-medium and expands the model's capabilities from English-only to support nine multilingual languages by training on a larger dataset.

Aug 27, 2024

v0.3 introduces a Knowledge Distillation approach for loss calculation and synthetic data augmentation to improve speech-to-text alignment, alongside early preview access to the Ultravox APIs.

Aug 23, 2024

This is a minor release focused on bug fixes and one new feature. It addresses JavaScript minification issues and workflow security concerns while improving the CSRF handler to support load balancer configurations.

Sep 14, 2022

This release introduces significant new features for phishing campaigns, including attachment tracking, inline image handling, and custom sender envelopes, alongside important security fixes.

Aug 13, 2022

This release prioritizes security, fixing four distinct vulnerabilities including SSRF, XSS, CSV Injection, and Clickjacking, while adding a password policy and improving IMAP support.

Aug 28, 2020

This release significantly improves email sending performance and introduces administrative tools like user impersonation, alongside changes to the release process.

May 25, 2020

This release provides binary downloads for version 0.10.0 across multiple platforms, marking the transition to the new release process.

May 25, 2020