Cohort of 109 admitted agents tagged capability:rag. Composite below is the cohort's average AgentScore.
| Cmp | Rank | Agent | 24h | Score | Δ24h | Watch |
|---|---|---|---|---|---|---|
| #5 | open-webui mcp-serveropen-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...) | 64.3 | -0.14 | |||
| #13 | MinerU MinerU: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. | 1 | 59.4 | +0.01 | ||
| #18 | dify mcp-serverdify: Production-ready platform for agentic workflow development. | 1 | 57.3 | 0.00 | ||
| #22 | langchain mitlibrarylangchain: The agent engineering platform. | 1 | 56.3 | +0.02 | ||
| #24 | ragflow apache-2.0ragflow: RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs. | 55.4 | -0.13 | |||
| #47 | claude-mem apache-2.0claude-mem: A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions. | 1 | 51.4 | +0.03 | ||
| #51 | awesome-llm-apps apache-2.0awesome-llm-apps: 100+ AI Agent & RAG apps you can actually run ??? clone, customize, ship. | 50.3 | 0.00 | |||
| #57 | mirage apache-2.0mirage: A Unified Virtual Filesystem For AI Agents. | 1 | 49.2 | +0.02 | ||
| #87 | files-sdk mitfiles-sdk: A unified storage SDK for object and blob backends. One small, honest API. Web-standards I/O. | 41.4 | +0.14 | |||
| #103 | composio mitmcp-servercomposio: typescript python sdk ai-agents anthropic openapi langchain openai-agents llamaindex mastra vercel-ai mcp oauth saas llm integrations agent-tools automation cloudflare google-gemini tooling rag multi-provider developer-sdk composable-actions webhook-triggers. | 2 | 38.7 | 0.00 | ||
| #106 | opendilab/LightZero ide-pluginopendilab/LightZero: Leveraging the rich world knowledge of Large Language Models (LLMs) to enhance Reinforcement Learning (RL) agents offers a promising path toward general intelligence. However, a fundamental prior-dynamics mismatch hinders existing approaches: static LLM knowledge cannot direct... | 3 | 37.3 | +0.00 | ||
| #111 | second-brain-cloudflare mitmcp-serversecond-brain-cloudflare: A personal memory layer for AI tools. Self-hosted MCP server on Cloudflare Workers with semantic search — works with Claude Desktop, Claude Code, and claude.ai. | 1 | 37.1 | +0.01 | ||
| #114 | generative-ai mitmcp-servergenerative-ai: Comprehensive resources on Generative AI, including a detailed roadmap, projects, use cases, interview preparation, and coding preparation. | 36.7 | +0.00 | |||
| #123 | PocketFlow mitlibraryPocketFlow: Pocket Flow: 100-line LLM framework. Let Agents build Agents! | 35.8 | +0.01 | |||
| #132 | WrenAI cliWrenAI: GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift,... | 1 | 35.1 | +0.00 | ||
| #134 | GenAI_Agents GenAI_Agents: 50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems. | 34.9 | +0.00 | |||
| #140 | awesome-LLM-resources apache-2.0mcp-serverawesome-LLM-resources: ??????????? ??????????????????LLM?????????????????????????????????Agent??????????????????AI??????????????????????????????????????????????????????o1 ?????????MCP?????????????????????????????????????????? | Summary of the world's best LLM resources. | 34.5 | 0.00 | |||
| #148 | llm_wiki mitllm_wiki: LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from... | 1 | 33.4 | +0.02 | ||
| #164 | ComfyUI-Copilot mitide-pluginComfyUI-Copilot: An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance. | 1 | 32.0 | +0.00 | ||
| #165 | langroid mitlibrarylangroid: Harness LLMs with Multi-Agent Programming. | 4 | 31.9 | -0.34 | ||
| #167 | aelfrice mitmcp-serveraelfrice: Bayesian memory that learns from feedback for LLM agents. | 2 | 31.7 | +0.04 | ||
| #190 | InternScience/MLEvolve libraryInternScience/MLEvolve: Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE), where sustained self-evolution becomes a key capability. However, existing MLE agents suffer from inter-branch information isol... | 3 | 30.5 | -0.01 | ||
| #238 | AgentR1/Claw-R1 ide-pluginAgentR1/Claw-R1: Agentic reinforcement learning (RL) has become an important post-training paradigm for turning LLMs from static chatbots into interactive agents, giving rise to representative applications such as OpenClaw. Existing work mainly focuses on policy optimization algorithms and tra... | 1 | 27.2 | -0.01 | ||
| #259 | HKUDS/VideoAgent ide-pluginHKUDS/VideoAgent: Video editing has become essential in digital media creation, yet existing automated systems are restricted to short segment processing and domain-specific tasks. They face two critical limitations: i) inability to handle diverse video comprehension and editing operations, and... | 4 | 26.3 | +0.03 | ||
| #263 | AgenticRAG-Survey libraryAgenticRAG-Survey: Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents. | 5 | 26.1 | +0.00 | ||
| #264 | machine-learning-library librarymachine-learning-library: A hand-curated library of the best machine learning education — 590 docs (78 arXiv papers, 474 course lectures from Stanford/MIT/Karpathy/fast.ai, 38 explainer articles), normalized to Markdown with full provenance. A clean ML corpus/dataset for learning, RAG, and fine-tuning. | 5 | 26.1 | -0.01 | ||
| #266 | WorkMesh mitWorkMesh: Open-source AI-era employment platform connecting skills, jobs, enterprises, governance, and AI agents. | 4 | 26.0 | +0.03 | ||
| #292 | provenant mcp-serverprovenant: Wiki-based retrieval for AI coding agents. 65× token reduction, +24pp Coverage@5 on SWE-bench Verified. | 9 | 24.9 | -0.35 | ||
| #300 | zjunlp/LightMem ide-pluginzjunlp/LightMem: Existing memory-augmented LLM agents often treat memory as a static repository with pre-defined representations and fixed retrieval pipelines, which is brittle in dynamic agentic environments where feedback, task variation, and heterogeneous signals continuously reshape what s... | 24.7 | +0.07 | |||
| #334 | awesome-agent-skill mitmcp-serverawesome-agent-skill: Curated skill pack for LLM agents in data science and machine learning (Cursor & Claude ready). | 23.1 | 0.00 | |||
| #361 | MiniMax-AI/MSA MiniMax-AI/MSA: Ultra-long-context capability is becoming indispensable for frontier LLMs: agentic workflows, repository-scale code reasoning, and persistent memory all require the model to jointly attend over hundreds of thousands to millions of tokens, yet the quadratic cost of softmax atte... | 3 | 22.4 | -0.02 | ||
| #372 | Agent_Memory_Techniques apache-2.0Agent_Memory_Techniques: Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns. | 6 | 21.8 | +0.04 | ||
| #399 | agent-study mitmcp-serveragent-study: 28章AI Agent全栈课程：从ReAct循环到Claude Code逆向、MCP/A2A协议、RAG、DSPy、生产可观测性——全部为可运行Python文件，面试导向。. | 2 | 21.1 | 0.00 | ||
| #409 | awesome-architecture mitawesome-architecture: 🗺️ Think like a software architect, not just a coder — 21 architecture maps (incl. AI gateway, RAG, agents, inference serving, vector DB) + a language-agnostic system-design tutorial. Every template links to real open-source prototypes. 中英文双语。 | 5 | 21.0 | -0.07 | ||
| #414 | agent-oss apache-2.0ide-pluginagent-oss: A recursive evidence-gated cognitive runtime for memory-native AI agents, combining hybrid retrieval, temporal reasoning, async learning, and plug-and-play tools. | 20.8 | +0.01 | |||
| #443 | jinyangwu/Maestro libraryjinyangwu/Maestro: The proliferation of large language models (LLMs) and modular skills has endowed autonomous agents with increasingly powerful capabilities. Existing frameworks typically rely on monolithic LLMs and fixed logic to interface with these skills. This gives rise to a critical bottl... | 2 | 20.1 | 0.00 | ||
| #515 | emotional-memory-agent mitemotional-memory-agent: A multi-tenant emotional memory system powered by an LLM agent, featuring user-level privacy isolation, long-term memory persistence, RAG retrieval, diary writing, and support for personalized interactions in QQ private and group chats. | 3 | 18.5 | 0.00 | ||
| #574 | Starscream-11813/awesome-AI4Math ide-pluginStarscream-11813/awesome-AI4Math: Mathematical reasoning has long served as a stringent test of machine intelligence; over the past decade, it has moved from a niche problem within NLP to one of the most consequential AI frontiers. This survey provides a unified account of the field's evolution, from early rul... | 4 | 17.4 | 0.00 | ||
| #595 | FERNme mcp-serverFERNme: A lightweight memory engine for AI agents using fuzzy graphs, Hebbian updates, and optional LLM gating. | 118 | 17.0 | +1.99 | ||
| #609 | @ragieai/mcp-server mcp-server@ragieai/mcp-server: A Model Context Protocol (MCP) server for Ragie. | 3 | 16.7 | -0.04 | ||
| #639 | yichenC1c/SAGE ide-pluginyichenC1c/SAGE: Fraud detection in payment, e-commerce, and telecommunications systems requires accuracy at the individual level, robustness under severe class imbalance, and ease of understanding for risk managers. Existing methods fall at least one of these requirements: automated machine l... | 5 | 16.5 | 0.00 | ||
| #623 | 1Reminding/Skill_EE library1Reminding/Skill_EE: Large language model agents increasingly rely on skills: reusable procedural documents encoding workflows, tool use, implementation patterns, validation checks, and domain rules. Skill rewriting is often treated as prompt compression, but shorter skills can make agents more ex... | 5 | 16.5 | 0.00 | ||
| #642 | Hello-Agents Hello-Agents: 🤖 Building AI Agent Systems from Scratch — A comprehensive, practical tutorial from fundamentals to production-grade multi-agent applications. | NEW | 16.4 | — | ||
| #664 | JetAstra/MacAgentBench cliJetAstra/MacAgentBench: Computer use agents (CUAs) have advanced rapidly in desktop automation, and a growing number of users deploy CUAs such as OpenClaw on Mac Mini for always-on automation. However, existing benchmarks, including those for macOS, evaluate agents without framework augmentation and... | 9 | 16.1 | 0.00 | ||
| #704 | agent-arena mitide-pluginagent-arena: Multi-agent debate, red-team, evidence checking and judge skills for Claude Code, OpenAI Codex, Hermes Agent, OpenClaw and AI coding agents. | 7 | 15.2 | -0.07 | ||
| #713 | krusch-context-mcp mitmcp-serverkrusch-context-mcp: A unified Zero-Trust MCP server that gives IDE agents local semantic codebase search, isolated episodic project memory, and hallucination-free framework RAG. | 9 | 15.1 | 0.00 | ||
| #736 | crypto-arbitrage-bot-automated-trading mitclicrypto-arbitrage-bot-automated-trading: 🤖 Cortex AI: #1 AI Trading Bot for Crypto, Forex & Stocks. Automated Arbitrage Engine v3.4. Works on Solana, TON, Binance & Bybit. Best Free Crypto Trading Bot 2026. | 11 | 14.8 | +0.02 | ||
| #796 | @loongsuite/opentelemetry-util-genai @loongsuite/opentelemetry-util-genai: OpenTelemetry GenAI utility for standardized telemetry collection across LLM, Agent, Embedding, Tool, Retrieval, Rerank, Memory and more. | 40 | 13.7 | +1.04 | ||
| #819 | astra-ai-automation-agent libraryastra-ai-automation-agent: Playwright Python test framework with an AI agent that generates tests from Jira/Excel tickets using RAG + GPT-4o. | 1 | 13.5 | +0.42 | ||
| #820 | ai-feed ai-feed: A 4-stage adversarial research auditor that fetches papers from arXiv & HuggingFace, extracts claims, and uses DeepSeek-R1 to verify them against raw abstracts.A self-correcting research & paper digest pipeline powered by local LLMs & reasoning agents | 26 | 13.4 | 0.00 | ||
| #821 | hexstrike_augment mithexstrike_augment: We have optimized HexStrike by adding a skill system and RAG capabilities. It now also supports connecting to models via Ollama. | 26 | 13.4 | 0.00 | ||
| #823 | dual-mem apache-2.0mcp-serverdual-mem: Dual-system layered memory SDK for LLM agents — structured write path, hybrid retrieval, evolution chains. | NEW | 13.3 | — | ||
| #834 | skills-comm apache-2.0skills-comm: Neuroimaging community skills repo - making LLMs leverage neuroimaging tools more effectively. | 11 | 13.1 | +0.15 | ||
| #852 | @loongsuite/otel-util-genai @loongsuite/otel-util-genai: OpenTelemetry GenAI utility for standardized telemetry collection across LLM, Agent, Embedding, Tool, Retrieval, Rerank, Memory and more. | 23 | 12.8 | -0.08 | ||
| #855 | lbn187/PokerSkill librarylbn187/PokerSkill: Poker is a landmark challenge for artificial intelligence. The dominant approach relies on equilibrium solvers built on counterfactual regret minimization, requiring millions of core-hours of training. Large Language Models (LLMs) possess extensive poker knowledge but perform... | 21 | 12.8 | 0.00 | ||
| #865 | Julius-Woo/STAR-PolyaMath libraryJulius-Woo/STAR-PolyaMath: Frontier AI models and multi-agent systems have led to significant improvements in mathematical reasoning. However, for problems requiring extended, long-horizon reasoning, existing systems continue to suffer from fundamental reliability issues: hallucination accumulation, mem... | 70 | 12.6 | +2.17 | ||
| #903 | dejavu apache-2.0mcp-serverdejavu: Memory that follows you across every AI tool. No cloud storage. No account required. Set it up once, use it everywhere. | 24 | 11.8 | -0.05 | ||
| #904 | riskradar-tracemap-ai mitriskradar-tracemap-ai: AI code review quality gates, coverage gap detection, and requirements traceability skills. | 105 | 11.7 | -1.67 | ||
| #173 | Qwen: Qwen3 Max saasQwen: Qwen3 Max: Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It... | 1 | 11.6 | 0.00 | ||
| #915 | @mcp-abap-adt/ollama-embedder mcp-server@mcp-abap-adt/ollama-embedder: Ollama embedding provider and OllamaRag convenience class for @mcp-abap-adt/llm-agent. | 11.5 | +0.67 | |||
| #917 | AgenticDeFi-Trainer mitlibraryAgenticDeFi-Trainer: Autonomous AI Agent Swarm framework with x402 self-executing wallets. Empowers LLM-driven agents to trade, bridge, and manage crypto treasuries without human intervention. The ultimate Agentic DeFi toolkit for 2026. | 24 | 11.4 | 0.00 | ||
| #919 | ai-agent-fullstack-roadmap mcp-serverai-agent-fullstack-roadmap: AI Agent Full-Stack Development Roadmap. | NEW | 11.3 | — | ||
| #175 | Perplexity: Sonar Deep Research saasPerplexity: Sonar Deep Research: Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers... | 1 | 11.3 | 0.00 | ||
| #923 | OpenDataBox/MemoryData ide-pluginOpenDataBox/MemoryData: Memory for large language model (LLM) agents has rapidly evolved from simple retrieval-augmented mechanisms into a data management system that supports persistent information storage, retrieval, update, consolidation, and dynamic lifecycle governance throughout agent execution... | NEW | 11.2 | — | ||
| #929 | benstaf/ipoagent librarybenstaf/ipoagent: Finance Agent v2 (by Vals AI) has emerged as the reference benchmark for evaluating both Anthropic Claude and OpenAI ChatGPT frontier language models on financial tasks. However, it narrowly deals with periodic reporting from publicly traded companies (SEC 10-K and 10-Q filing... | 24 | 11.0 | 0.00 | ||
| #931 | calypso-so/soccer-rag-mcp-server mcp-servercalypso-so/soccer-rag-mcp-server: discovered AI agent. | 25 | 11.0 | 0.00 | ||
| #937 | XMUDeepLIT/SAAS ide-pluginXMUDeepLIT/SAAS: Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search. Despite the effectiveness, these systems often suffer from a critical limitation in practice: agents fail to recognize their own knowledge boundaries, blindly trig... | 28 | 10.9 | 0.00 | ||
| #940 | asakin/dragoman asakin/dragoman: discovered AI agent. | 28 | 10.9 | +0.05 | ||
| #952 | paper_lens paper_lens: Traditional Chinese reading notes on AI papers — LLM, VLM, contrastive learning, RL, agentic AI, RAG. Each article unpacks a seed paper with its key dependencies, organized around core knowledge points. | 30 | 10.7 | 0.00 | ||
| #958 | agentic-quantum-computing mitsaasagentic-quantum-computing: End-to-end agentic quantum-ML pipeline: PennyLane GPU quantum-kernel anomaly detection + LangGraph multi-agent system + locally-hosted Qwen3-14B, benchmarked across network-intrusion, LHC physics, and fraud. | 32 | 10.6 | 0.00 | ||
| #963 | shidingz/EDV ide-pluginshidingz/EDV: Experience-driven self-evolution is critical for large language model (LLM) agents to improve through open-world interaction. However, existing experience learning methods mostly rely on single-agent loops, where the same agent executes tasks, summarizes outcomes, and determin... | NEW | 10.5 | — | ||
| #964 | Jasmine0201/GASim ide-pluginJasmine0201/GASim: Large-scale social simulators are essential for studying complex social patterns. Prior work explores hybrid methods to scale up simulations, combining large language models (LLM)-based agents with numerical agent-based models (ABM). However, this incurs high latency due to ex... | 35 | 10.5 | 0.00 | ||
| #204 | Cohere: Command R+ (08-2024) saasCohere: Command R+ (08-2024): command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint... | 1 | 10.3 | 0.00 | ||
| #977 | fujiwaranoM0kou/OptSkills libraryfujiwaranoM0kou/OptSkills: Leveraging Large Language Models (LLMs) to automatically formulate and solve optimization problems from natural language has emerged as an efficient paradigm for automated optimization. However, existing methods still exhibit limited generalization: they are sensitive to super... | 38 | 10.2 | -0.14 | ||
| #209 | Google: Gemma 3n 2B (free) saasGoogle: Gemma 3n 2B (free): Gemma 3n E2B IT is a multimodal, instruction-tuned model developed by Google DeepMind, designed to operate efficiently at an effective parameter size of 2B while leveraging a 6B architecture. Based... | 1 | 10.2 | 0.00 | ||
| #989 | PRISM mitide-pluginPRISM: A training-free, retrieval-side memory framework for long-horizon LLM agents — high accuracy at an order-of-magnitude smaller context budget. | 29 | 10.0 | 0.00 | ||
| #1017 | Valiere01/ISE-Trace ide-pluginValiere01/ISE-Trace: Training capable OS agents requires data that simultaneously captures structured user intents, multi-turn task delegation, and grounded tool execution--properties absent from existing datasets. We propose ISE (Intent -> Simulate -> Execute), a three-stage synthesis paradigm th... | 31 | 9.5 | 0.00 | ||
| #1022 | CuSO4-Chen/AKBE ide-pluginCuSO4-Chen/AKBE: Agentic reinforcement learning (RL) has proven effective for training LLM-based agents with external tool-use capabilities. However, we identify that agentic RL training induces increasing redundant tool calls and blurs the model's intrinsic knowledge boundary, where the model... | 32 | 9.5 | 0.00 | ||
| #1024 | foursoils/Privacy-Preserving-RAG ide-pluginfoursoils/Privacy-Preserving-RAG: Retrieval-Augmented Generation enhances large language models by incorporating external knowledge, but deploying it in sensitive scenarios risks privacy leakage via malicious prompts. To address this, we propose a multi-agent framework that sanitizes retrieved content through... | NEW | 9.5 | — | ||
| #1027 | Bon99yun/DoLQ ide-pluginBon99yun/DoLQ: Discovering governing differential equations from observational data is a fundamental challenge in scientific machine learning. Existing symbolic regression approaches rely primarily on quantitative metrics; however, real-world differential equation modeling also requires inco... | 23 | 9.4 | +0.98 | ||
| #1048 | personal-assistant-agent mitpersonal-assistant-agent: A personal AI assistant prototype based on RAG, tool calling, and LLM agents. | 34 | 9.0 | 0.00 | ||
| #1062 | lumina-core mitclilumina-core: Self-hosted LLM observability — traces, cost, latency, agents, tool calling, RAG. Python SDK + OpenTelemetry + REST. | 45 | 8.7 | -0.21 | ||
| #254 | Cohere: Command R7B (12-2024) saasCohere: Command R7B (12-2024): Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning... | 8.6 | 0.00 | |||
| #1079 | KabakaWilliam/known_actions ide-pluginKabakaWilliam/known_actions: As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model powers an agent? Doing so would represent a significant security risk, enabling targeted attacks tailored to known model vulnerab... | 36 | 8.5 | 0.00 | ||
| #1087 | WhitenWhiten/CodeTeam libraryWhitenWhiten/CodeTeam: Natural language to repository generation (NL2Repo) requires a system to construct an entire software repository from a natural-language requirements document. Compared with function-level code generation, this task demands longer planning horizons, stable interfaces across fi... | 34 | 8.4 | 0.00 | ||
| #1104 | llm-agent-rag llm-agent-rag: discovered AI agent. | 34 | 8.0 | 0.00 | ||
| #1109 | awesome-agent-rl-environments awesome-agent-rl-environments: A curated list of training & evaluation environments for LLM/VLM agents (SWE-Gym, GEM, RAGEN, AgentGym, WebArena, OSWorld, ToolBench…). Updated weekly. | 35 | 7.9 | 0.00 | ||
| #1119 | zhigao3ks/IFPV ide-pluginzhigao3ks/IFPV: Operational plan generation and verification are critical for modern complex and rapidly changing battlefield environments, yet traditional generation and verification methods still respectively face the challenges of generation infeasibility and verification insufficiency. To... | 36 | 7.6 | 0.00 | ||
| #1118 | YUHAOSUNABC/TRIAD ide-pluginYUHAOSUNABC/TRIAD: LLM-based guardrails typically safeguard agents by evaluating proposed actions or inputs before execution, producing safety signals such as binary allow/deny decisions, risk categories, and/or explanatory rationales about potential policy violations. However, agent risks often... | 36 | 7.6 | 0.00 | ||
| #1115 | alem-world/alem-env ide-pluginalem-world/alem-env: As language models are increasingly deployed as autonomous agents, they must coordinate with others over long horizons in open-ended interactive tasks. Yet existing evaluations rarely test these demands together, instead emphasising single-agent tasks, short interactions, or h... | 36 | 7.6 | 0.00 | ||
| #1124 | Saksham4796/causal-memory-intervention librarySaksham4796/causal-memory-intervention: Long-horizon LLM agents rely on persistent memory to support interactions across sessions, yet existing memory systems often retrieve context using semantic similarity or broad history inclusion, treating retrieved memories as uniformly useful. This assumption is fragile becau... | 37 | 7.5 | 0.00 | ||
| #1129 | LLMAgenticRAG LLMAgenticRAG: LLM Agentic RAG. | 35 | 7.5 | 0.00 | ||
| #1131 | progressive-synaptic-memory mitprogressive-synaptic-memory: Progressive Synaptic Memory: a token-efficient long-term memory mechanism for LLM Agents / 渐进式突触记忆机制. | 34 | 7.5 | 0.00 | ||
| #1151 | role2026/rolememo ide-pluginrole2026/rolememo: While role-playing agents excel in short-term interactions, long-term conversations overwhelm context windows, motivating external memory frameworks. Current systems typically rely on persona-agnostic summarization, which records facts without persona-specific interpretation,... | 31 | 7.2 | 0.00 | ||
| #1171 | llm-agent-kb llm-agent-kb: Enterprise knowledge-base GraphRAG Q&A platform (case study) — kbd backend embedding llm-agent-rag, with llm-agent-authz RBAC. | 33 | 6.5 | 0.00 | ||
| #1206 | XMHZZ2018/VisualSkills mcp-serverXMHZZ2018/VisualSkills: Computer-use agents (CUAs) approach human-level performance on standardised benchmarks but still struggle on long-horizon tasks and unseen software. Existing skill libraries address this with reusable skills, but represent the skill artifact as text only, despite the visual na... | 33 | 6.0 | 0.00 | ||
| #1201 | agentic-qe mcp-serveragentic-qe: Agentic Quality Engineering V3 - Domain-Driven Design Architecture with 13 Bounded Contexts, O(log n) coverage analysis, ReasoningBank learning, 60 specialized QE agents, mathematical Coherence verification, deep Claude Flow integration. | NEW | 6.0 | — | ||
| #1209 | innovation64/AURA innovation64/AURA: A situated query like "where is Lin Wei?" often encodes more than its literal content: the user may also want to know whether Lin Wei is free, in a good mood, or worth interrupting now. Standard tool-use agents answer the literal question and stop. AURA inserts an inference st... | 11 | 5.7 | +0.83 | ||
| #1224 | Modular RAG MCP Server mcp-serverModular RAG MCP Server: A pluggable, observable modular RAG service framework that exposes tool interfaces via the MCP protocol, enabling AI assistants like Copilot and Claude to directly query knowledge bases. | 34 | 5.0 | 0.00 | ||
| #328 | NVIDIA: Llama 3.1 Nemotron 70B Instruct saasNVIDIA: Llama 3.1 Nemotron 70B Instruct: NVIDIA's Llama 3.1 Nemotron 70B is a language model designed for generating precise and useful responses. Leveraging [Llama 3.1 70B](/models/meta-llama/llama-3.1-70b-instruct) architecture and Reinforcement Learning from Human Feedback (RLHF), it excels... | 5.0 | 0.00 |
Browse all sectors at /sectors.