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
webfuse-com/awesome-autoresearch
Awesome Autoresearch is a curated list that indexes autonomous improvement loops, research agents and projects inspired by karpathy/autoresearch. It is organised into sections for general-purpose descendants, research-agent systems, platform ports and hardware forks, domain-specific adaptations, evaluation and benchmarks, notable use cases and writeups, and related resources. Each entry is a link to a repository with a one-line factual description and a live star badge, which makes the file a navigation aid rather than a code project. The general-purpose section shows the range of the ecosystem it tracks: recursive self-improvement frameworks that capture execution traces, analyse failure patterns and apply targeted fixes under keep-or-revert evaluation; documentation-only control planes that define a file-based operating model separating human direction from agent execution; ports of the autoresearch loop as skills for Claude Code, Codex, Gemini CLI and other agent runtimes, several with resume support, lessons carried across runs, optional parallel experiments and mode-specific workflows; runners that add deterministic execution, plan-hash approval, isolated Git worktrees, authoritative metric evaluation and append-only experiment ledgers; and dashboard-first runtimes with durable runs, locked work items and reviewable verdicts. Other entries generalise the loop beyond model training to any measurable metric such as system prompts, API performance, landing pages, test suites, configuration tuning and SQL queries, or introduce a GOAL.md pattern for repositories where the agent must first construct a measurable fitness function before it can optimise anything. The list also collects collaborative forks that add experiment claiming, shared best-config syncing, hypothesis exchange and swarm-style coordination across many single-GPU agents, plus academic work such as ADAS on the automated design of agentic systems and a self-improving coding agent that edits its own codebase. The repository is licensed CC0-1.0 and accepts contributions through pull requests.
https://github.com/webfuse-com/awesome-autoresearch
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.
Xnhyacinth/Awesome-LLM-Long-Context-Modeling
A curated repository of must-read papers and blogs focused on Long Context Modeling techniques and research in Large Language Models, providing comprehensive resources for advancing long sequence understanding in AI.