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
RyanAlberts/best-of-Agent-Harnesses
This project catalogues the runtime layer that turns a language model into an acting agent, which it calls the agent harness: the component deciding which tools exist, what requires approval, what the model sees each turn and what survives a crash. The introduction grounds that definition in published sources, citing Simon Willison on agents running tools in a loop, Karpathy framing the model as the kernel of an operating system with the harness as the rest of it, and the SWE-agent paper on the agent-computer interface. It argues from benchmark evidence that harness choice can matter more than model choice, quoting reported SWE-bench Pro swings from 23 to 52 percent pass at one on a single model when only the harness changed, and noting that harness rankings barely transfer between models. Around 160 projects are ranked by relevance to harness concerns, environment, orchestration, lifecycle and guardrails, and by stars and activity, with scores refreshed weekly. Generated assets accompany the tables: a landscape chart plotting adoption surface area against stars, an autonomy-by-recovery grid placing every loop-owning project, markers for headless-ready and durable projects, and a browsable site with one page per harness and filters by capability, autonomy and recovery. Decision material sits alongside the raw ranking, including a guide of six questions for picking a harness, a two-week test-drive protocol, and head-to-head comparisons for terminal coding agents, multi-agent orchestration frameworks and agent memory layers. The list is also machine-readable: an llms.txt file, a JSON export and an MCP server exposing recommendation tools let an agent query the catalogue directly and pick a harness matched to its model and task. It suits engineers evaluating agent runtimes and anyone tracking the field.
https://github.com/RyanAlberts/best-of-Agent-Harnesses
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.