Awesome AI AgentsLLM Research Repositories

TeleAI-UAGI/Awesome-Agent-Memory

⭐ 633 repository created 2025-10-30

Awesome Agent Memory is a curated index of the research and engineering work behind long-term context and persistent recall for AI agents, maintained by the Ubiquitous AGI team at TeleAI together with Bloo-Mind AI. It is organised as a set of entry points rather than a flat bibliography: readers who want to add a memory layer to an agent go to a products section, readers choosing an evaluation method go to benchmarks, newcomers start from tutorials and surveys, and researchers follow separate sections for nonparametric memory architectures, parametric memory, memory that lets agents improve from experience, and defences against memory poisoning and abuse. The curation rules are stated openly. Resources with reproducible public code are marked in bold and ranked higher. Open-source products are ordered by GitHub star count, described in the list as an objective and continuously checked popularity signal rather than a quality judgement, and products below one hundred stars sit in a collapsed emerging section until they cross that threshold. Descriptions are required to be factual rather than promotional, and entries affiliated with the maintainers are marked with a dagger while following the same ranking and formatting rules as everything else. Projects that become inactive or archived, or whose claims are disputed, move to an archival subsection with a neutral status label, links to the supporting evidence and the date the status was last verified. A news section tracks announcements about agent memory from vendors and researchers, including managed memory services, self-improving memory systems and public leaderboard results. The repository is Apache 2.0 licensed, accepts pull requests through a contributing guide, and serves engineers selecting a memory component as well as researchers tracking the memory literature.

https://github.com/TeleAI-UAGI/Awesome-Agent-Memory

agent-memoryai-agentllm-memorymemory-managementmultimodal-llm-memoryragawesome-listbenchmarkssurvey

Also in LLM Research Repositories

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.

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.