elder-plinius/CL4R1T4S
CL4R1T4S is a project that provides transparency by collecting and sharing the hidden system prompts and guidelines used by major AI models and agents to promote trust and understanding of AI behavior.
Awesome AI Agents › LLM Research Repositories
MiniMax-AI/MiniMax-M2.1
MiniMax-M2.1 is an open-weight large language model published by MiniMax under a modified MIT license and aimed at agentic workloads rather than plain chat. This repository holds no model code: it is the release and documentation package, with the weights hosted on Hugging Face and ModelScope. The README reports benchmark numbers against the previous M2 release and against closed models on software engineering suites such as SWE-bench Verified, Multi-SWE-bench, SWE-bench Multilingual, SWT-bench and Terminal-bench 2.0, on tool use and browsing suites such as Toolathlon and BrowseComp, and on general reasoning sets including AIME25, MMLU-Pro and GPQA-Diamond. The evaluation notes describe which agent scaffolding produced each score, naming Claude Code, Droid and mini-SWE-agent, which makes the results easier to reproduce and shows that the model was trained to generalise across coding agent harnesses rather than a single one. Several internal benchmarks are described as well, covering code review, long-horizon instruction following for code agents, and verification of interactive program behaviour. The documentation directory carries deployment guides for SGLang, vLLM, Transformers and MLX-LM, recommended sampling parameters, the default system prompt, and a separate tool calling guide describing how the model emits and consumes function calls. The intended audience is developers who build coding agents, tool-using assistants or multi-step workflow agents and want to run the model themselves instead of calling a hosted API, along with researchers comparing open and closed agentic models. A hosted API and a MiniMax Agent product built on the same model are linked from the README.
https://github.com/MiniMax-AI/MiniMax-M2.1
Also in LLM Research Repositories
WooooDyy/LLM-Agent-Paper-List
A comprehensive repository compiling essential academic papers and a detailed survey on the rise, framework, applications, and societal aspects of Large Language Model based AI agents.
mahseema/awesome-ai-tools
A curated repository listing top Artificial Intelligence tools across various categories including generative AI, chatbots, search engines, and writing assistants.
filipecalegario/awesome-generative-ai
A curated and comprehensive list of Generative AI tools, projects, models, artworks, and educational resources, regularly updated to reflect the latest advancements in the field.
DSXiangLi/DecryptPrompt
DecryptPrompt is a comprehensive resource hub that summarizes prompt and LLM research papers, open-source datasets and models, and AIGC applications, providing in-depth tutorials and analyses for AI researchers and practitioners.
zjunlp/LLMAgentPapers
LLMAgentPapers is a curated repository of essential academic papers on Large Language Model agents, covering topics from agent personality to multi-agent systems and applications.
luo-junyu/Awesome-Agent-Papers
A comprehensive and up-to-date research collection of papers on Large Language Model (LLM) agents, covering methodologies, applications, challenges, and key categories such as construction, collaboration, evolution, tools, security, benchmarks, and real-world applications.
webfuse-com/awesome-autoresearch
Curated index of autonomous improvement loops and research-agent systems descended from karpathy/autoresearch, grouped into general-purpose forks, research systems, platform ports, domain adaptations and benchmarks.