monolabsdev/openbench-ai

v0.7.1 Feature

This release adds 1 notable feature for engineering teams evaluating rollout.

Published 5d LLM Frameworks

✓ No known CVEs patched

✓ No known CVEs patched in this version

Topics

local-llm multi-model offline-ai ollama privacy-first tauri

Summary

AI summary

Fixes AudioContext leak and adds a 120‑second maximum recording duration.

Type	Severity	Summary	CVE
Feature
Feature	Low	Add 120s max recording duration Add 120s max recording duration Source: llm_adapter@2026-05-29 Confidence: high	—
Feature	Low	Accept i16 samples from frontend instead of f32 Accept i16 samples from frontend instead of f32 Source: llm_adapter@2026-05-29 Confidence: high	—
Feature	Low	Emit dictation-progress events during model download Emit dictation-progress events during model download Source: llm_adapter@2026-05-29 Confidence: high	—
Feature	Low	Deliver empty transcript when no speech detected Deliver empty transcript when no speech detected Source: llm_adapter@2026-05-29 Confidence: high	—
Deprecation	Low	Remove unused SettingsModal styles Remove unused SettingsModal styles Source: llm_adapter@2026-05-29 Confidence: high	—
Bugfix	Medium	Fix AudioContext leak by reusing singleton Fix AudioContext leak by reusing singleton Source: llm_adapter@2026-05-29 Confidence: high	—
Refactor	Low	Switch Rust state to OnceLock for simpler lazy init Switch Rust state to OnceLock for simpler lazy init Source: llm_adapter@2026-05-29 Confidence: high	—

Full changelog

Full Changelog: https://github.com/monolabsdev/openbench-ai/compare/v0.7.0...v0.7.1

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track monolabsdev/openbench-ai

Get notified when new releases ship.

About monolabsdev/openbench-ai