Release papersgpt-v0.2.4: 5x Faster PDF Reading.

Release papersgpt-v0.2.4:

1. 5x Faster PDF Reading.
2. Improve the reading effect of long texts, such as dozens or hundreds of pages of PDF.

Release papersgpt-v0.2.3

Release papersgpt-v0.2.3:

1. Improve the quality of chatting pdf and performance with Local LLM on Mac.
2. Update the latest SOTA Local LLMs(Gemma3 1b, 4b, DeepSeek-Distill-Qwen-8B,...) on Mac.
3. Add new light papersgpt agent for Mac.
4. Fix some bugs of papersgpt agent.

v0.2.2

Release papersgpt-v0.2.2:

1. Optimize the startup process of papersgpt agent on Windows.
   Important notes - The related agents of papersgpt may be mistakenly defined as a Trojan or virus by Microsoft Defender or other anti-virus software. If you want to use the Local LLMs on your Windows, please allow the safe papersgpt agents to run on your device in Microsoft Defender or anti-virus software.

2. Support DeepSeek R1 0528 distill Qwen3 running locally on Windows.

3. Optimize the local LLMs running parameters and improve the answer quality of local LLMs.

papersgpt-beta-v0.2.1

Release papersgpt-beta-v0.2.1:
This is a beta version, very big update for the backend, windows agent was introduced, it may not be stable. If want a stable version, please use v0.1.3 first.
Each new version provides an additional 30 free credits for users whose free trial expires.
Each credit can be used to chat about PDF once.
Add Claude Sonnet 4 and Claude Opus 4.
Add Gemini 2.5 Flash Preview 0520 and Gemini 2.5 Pro Preview.
Update the hottest models of OpenRouter.
Fix a bug that the latest models may not be updated.
Fix a bug that when opening the plugin with the configure of local llm, it would not be opened any more.
Fix a bug that the showing of Customized is error

Release papersgpt-v0.2.0, support local LLM on Windows

Support one click running local AI models on Windows:

1. Now support Phi 4 mini reasoning, Phi 4, Gemma 3, Mistral 2503, Qwen 3, DeepSeek Distill Llama and llama 3.2 on Windows.
2. Models of different sizes are built in based on the size of the local machine GPU.
3. Add papersgpt agent for complex tasks on Windows.
4. Compatible with ollama, if use ollama, please set Customized API URL to http://localhost:11434/api/chat in the selection of Customized.

v0.1.3

Release papersgpt-v0.1.3:

1. Add the ability of chatting multiple PDFs in Zotero by PapersGPT. Support generating literature review based on multiple PDFs in Zotero.
2. Support gpt-4.1, o1/o3/o4-mini, gemini-2.5-flash-preview, gemini-2.5-pro-preview and Grok 3(used in OpenRouter).
3. Fix the bug that the selected multiple PDFs may not be read occasionally.
4. Support free Qwen3 in local llm and openrouter.

v0.1.2

Release papersgpt-v0.1.2:

1. Integrate OpenRouter
2. Support saving the result of chatting PDF to zotero note
3. Support the latest Llama 4 in OpenRouter

v0.1.1

Release papersgpt-v0.1.1:
No registration required to use
Support gemini-2.5-pro, the #1 model of ChatBot Arena
Support changing to a higher pricing plan

v0.1.0

Support Gemma 3 local model on Mac

v0.0.20

Release papersgpt-v0.0.20:
Compatible with Zotero v7.1-beta*