gpt-researcher Releases

A comprehensive update to the QwenPaw platform focusing on UI/UX improvements, new console features like simple and wide modes, Vietnamese language support, and desktop application enhancements.

Jun 17, 2026

Introduces `RFDETRKeypointPreview` for keypoint detection with uncertainty estimates, adds a new local export method for offline bundles, and fixes gradient accumulation loss scaling for keypoint training.

Jun 16, 2026

v0.2.0 is a beta candidate release for the SIP series crates, featuring a refactored developer API for the rvoip-sip library to improve simplicity, interoperability, and reliability.

Jun 4, 2026

RF-DETR 1.7.1 is a focused patch release that fixes three critical bugs affecting common workflows, specifically related to BF16 mixed-precision training, loading official checkpoints, and NumPy 2.x compatibility.

May 28, 2026

A major update introducing new model providers and retrievers, alongside significant performance optimizations and bug fixes for stability and cost tracking.

May 28, 2026

A major release introducing HAMi core modes for Ascend and NVIDIA devices, updating the Volcano plugin, and adding extensive debugging, monitoring, and multi-device support features.

May 19, 2026

A minor patch release addressing specific monitoring failures and device utilization watcher issues that occurred in the v2.8.2 version.

May 19, 2026

A maintenance release that optimizes device application interaction, updates the underlying scrcpy version, and improves keyboard and mouse mapping reliability.

May 19, 2026

A comprehensive update introducing automatic LAN device discovery, advanced keyboard mapping features, and significant performance improvements for the embedded mirroring tool.

May 13, 2026

A maintenance release focused on resolving a critical bug in the device-monitor component that was malfunctioning in the previous version.

Apr 28, 2026

Version 2.8.1 addresses a critical issue preventing the proper launch of the application when using multiple GPUs with vLLM versions greater than 0.18. This bug fix ensures compatibility and stability for users deploying the system in high-performance GPU environments.

Apr 17, 2026

A maintenance release addressing critical parsing and retrieval bugs while introducing support for MiniMax and Xquik as new providers.

Apr 16, 2026

Focused on stability and usability, this release improves PDF handling, fixes Azure integration, and adds cost tracking and UI enhancements to the FastAPI frontend.

Mar 13, 2026

This release prioritizes performance optimization and Docker compatibility, addressing NameErrors and browser pool issues while introducing the Avian LLM provider.

Mar 1, 2026

Maintenance release with bug fixes, new tool integrations, and support for additional LLM providers. Eight new contributors made their first contributions to the project.

Feb 21, 2026

Major feature release introducing inline image generation with Google Gemini, LangSmith observability integration, and Claude Code skills for AI-assisted development.

Jan 29, 2026

This release focuses on improving LLM configuration management and stability. It introduces automatic model loading and connection testing features, along with a warning system for SelfHost workflows and fixes for digital avatar parameter passing errors.

Jan 27, 2026

The update adds 'Action Transfer' capabilities and expands local workflow support for digital avatars and image-to-video generation. It also locks the edge-tts version to ensure audio generation stability.

Jan 26, 2026

Security and performance improvements release focusing on CORS fixes, WebSocket enhancements, and report history persistence.

Jan 25, 2026

This release is a major update for HAMi, introducing Hardware-Aware Multi-IaaS (HAMi) DRA support, leader selection among schedulers, and CDI mode for NVIDIA devices. It also syncs with the latest NVIDIA Kubernetes device plugin.

Jan 20, 2026