Category
AI Infra agents
32,932 AI Infra AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
32,932 agents · ranked by popularity · refine in the directory →
AI Infra agents — page 86 of 330
streamlit region:us
gradio region:us
gradio leaderboard region:us
gradio region:us
gradio region:us
streamlit region:us
streamlit region:us
gradio region:us
gradio region:us
mlx safetensors qwen3_5_moe qwen-agentworld abliterated 4-bit
transformers safetensors llama text-generation fr license:apache-2.0
safetensors qwen2 text-generation conversational pt base_model:Qwen/Qwen2.5-0.5B-Instruct
transformers gguf llama LLM llama-2 text-generation
transformers safetensors llama text-generation en arxiv:2401.08508
transformers safetensors gguf llama text-generation openthaigpt
gradio region:us
gradio agent-demo-track region:us
gradio mcp agents hackathon agent-demo-track collective-intelligence mcp-server-track mcp-server
transformers safetensors qwen2 text-generation chat conversational
docker region:us
gradio region:us
static region:us
static region:us
Reasoning agent that triages inherited Power Automate estates: maps dependencies, finds the landmines, and outputs an evidence-grounded remediation plan. Built on Microsoft Foundry + Foundry IQ.
Companion OpenClaw skill for the Unity plugin — teaches AI agents the tool surface and editor workflows so they can drive Unity remotely.
Core hub for LLM orchestration, AI agent development, and prompt engineering frameworks. Implementing advanced workflows, RAG systems, and autonomous agent logic for intelligent automation.
Agent-You-MustKnows 是一个面向 AI Agent 领域的系统化学习与研究知识库，旨在整理 Agent 方向的重要论文、技术报告、经典方法与前沿探索。项目围绕 LLM-based Agent 的核心发展脉络，涵盖智能体基础理论、推理与规划机制、工具调用、记忆系统、多智能体协作、RAG+Agent、Agent 架构设计以及未来 Agentic AI 等关键方向。该项目不仅关注论文收集，更致力于构建从概念理解、技术演进到系统实践的完整知识体系，帮助研究者和开发者快速掌握 Agent 领域的重要思想、核心技术与发展趋势，探索从“能够生成文本的语言模型”到“具备感知、推理、行动与持续学习能力的智能体系统”的演进路径。
Multiplatform 3D chess app powered by Stockfish, featuring on-device AI move coaching and cloud-based RAG for position chat.
RagTrack is a lightweight Git-like version control layer for RAG knowledge bases. It basically helps you track changes across different documents in your RAG Application
Desktop client for Svoi's external RAG ('My PC') — indexes local folders and uploads them end-to-end-encrypted over a blind relay. The server holds no keys.
Compare embedding models locally with LM Studio — cosine similarity UI for RAG workflows
gguf heretic uncensored decensored abliterated ara
An open-source operating system for long-lived, autonomous, revenue-generating agent businesses — memory, money, and governance for any LLM brain. Built and run by an autonomous AI agent.
Agentic gateway providing persistent LLM memory via a markdown wiki. Open-source core of Kortexio.
Transform institutional knowledge into Open Knowledge Format (OKF). OKF Studio ingests enterprise knowledge from multiple sources, structures it into portable OKF bundles, builds linked knowledge graphs, and makes knowledge reusable across LLMs, agents, and applications.
The self-correcting memory layer for AI agents. Zero-dependency Python memory and MCP server. Supersede, revert, or forget a value deterministically. Verifiable erasure, witness-backed tamper-evident receipts, EU AI Act ready.
AI agent primitives on Upstash Redis: memory, RAG, search, chat history, caching, and rate limiting. With Vercel AI SDK and Eve
A free, cross-platform UI for local AI agents. Orchestrate Ollama, embedded GGUF models, DuckDB RAG, and MCP tools on mobile, desktop, or headless Docker without YAML configs.
Every complex task is a Digital Odyssey. A role-playing multi-agent framework based on OpenClaw.
gradio region:us
Autonomous digital mind: 33 asyncio loops, Toltec architecture (Castaneda), identity survives model swaps, runs 24/7 on free LLM keys. One Python file.
transformers gguf text-generation zh license:apache-2.0 region:us
kiagent-core — open-source personal AI brain — local, open source, speaks MCP
quick buzz BD
A lightweight Python library for dynamic multi-persona interactions management with LLMs.
transformers safetensors qwen2 text-generation chat conversational
Provenance-aware memory for AI agents.
A lightweight, framework-free Augmented LLM Agent powered by LLM + MCP + RAG
Enterprise-grade, multi-tenant, model-agnostic, MCP-first Agent platform.
Chat with Github Repositories (w/ multiple filetypes). Provides flexible backend: Select from different Vectorstores, Context Retrieval-methods and LLMs.
Guia técnico aberto de engenharia de agentes de IA em produção (em português): agentes ReAct e multi-agente, engenharia de contexto, avaliação e observabilidade (LLM-as-a-Judge, Langfuse), LangGraph e RAG avançado/Graph/Agentic (LlamaIndex, Neo4j).
Convert documents once. Give agents only what they need — PDFs and Office files to clean Markdown, chunks and local search.
Public Preview: self-hosted, protocol-first AI gateway and agent control plane for OpenAI, Anthropic, Gemini, MCP and A2A — governed tools, prompt enhancement, virtual-key budgets, cache and audit; zero-key first run.
Compile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop
让 DeepSeek Harness(dsh) 在 HarmonyOS 完整跑起来：缓存优化对话预设 + 启动补丁 + 工具链 | Run DeepSeek Harness on HarmonyOS: cache-optimized agent presets, patches & tooling
Local agent OS for everyone — memory as the body, agents as shells. Model-agnostic agent dispatcher in Rust. 本地智能体操作系统：记忆是本体，Agent 只是壳。
Official implementation of SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models.
Open-source context and memory control layer for LLM applications. Inspect, manage, and selectively reuse the context your AI works with.
Chat widget for Astro sites. Streams answers from your AI backend over SSE, no framework runtime.
All in one memory system for your harness
transformers safetensors llama text-generation arxiv:2406.04151 text-generation-inference
Self-hosted control plane for governed AI agents: approval-first execution, persistent context, reusable profiles and skills, and auditable results.
static region:us
Auditable memory layer for AI agents: zero-LLM-call local ingest (~10ms/msg, air-gapped), matches Mem0 on accuracy at ~1000x lower ingest cost, bi-temporal belief-state, MCP server. Honest LoCoMo/LongMemEval benchmarks. Open source (Apache-2.0).
LangChain / LangGraph 系统化学习的开源教程：9 个 Phase、26 个可运行示例、双语 VitePress 文档站，递进揭示各 Agent 框架共通的图编排本质。(A structured LangChain / LangGraph course — 9 phases, 26 runnable examples, bilingual VitePress docs, progressively revealing the shared graph-orchestration essence behind Agent frameworks.)
Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution (prefercmd/memory as knowledge allow/deny lists), so repeated tasks start from proven commands and save tokens. Unified subagent routing and evolution: prefercmd/memory serve as knowledge allow/deny lists, saving tokens.
USB - Universal Skill Bridge: one portable skill format, installed into 16 agent runtimes with sha256-verified installers
A Rag App with Spring AI and MongoDB
Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness — strict evidence, health-checked failover, original pixels, and Token accounting.
Cross-session memory plugin for DSH — auto-extraction, semantic recall, scheduled maintenance, LLM-powered consolidation
A Python engine for Pokémon TCG simulations and bots
Hot Dev: Hot Language and AI Workflow/Agents Platform
One HTML file. Chat with OpenAI, Claude, Gemini, DeepSeek, Ollama and any OpenAI-compatible endpoint — streaming, reasoning, vision, fully client-side.
Go AI agent framework — reversible effects, reactive service loading.
A macOS menu bar app: a global hotkey pops up a floating chat panel for any OpenAI-compatible model or your ChatGPT subscription. Native Swift + SwiftUI, no Electron.
Explainable disease prediction using multi-model scikit-learn, FAISS RAG, and a modern Flask UI.
A production-grade Retrieval-Augmented Generation (RAG) system for intelligent document processing, semantic search, and conversational AI.
A benchmark for evaluating LLM agents as sequential hyperparameter optimizers across 30 executable machine learning tasks
An open Agent Skills Compendium for discovering, defining, composing, and governing reusable capabilities for AI agents — from digital intelligence to multi-agent systems and Physical AI.
Bilingual graduate textbook on LLM post-training: SFT, RLHF, DPO, GRPO, RLVR, reasoning, agents, systems, evaluation, and safety.
Python Framework for Multi-Channel AI Assistants and Agent Applications
yet another simple ai agent
Async-LLM is an architecture that improves LLM task execution by planning, scheduling, and executing subtasks efficiently, inspired by how compilers optimize programs.
Exact Variable Elimination inference engine for discrete Bayesian Networks computing conditional posteriors and marginal probability distributions.
Robinson's first-order term unification algorithm with occurs-check for automated theorem proving, Prolog engines, and type inference.
Loopy Belief Propagation (LBP) engine on general factor graphs with sum-product message passing and damping to solve approximate inference on cyclic topologies.
Immix mark-region garbage collector utilizing hierarchical block and line marks, fine-grained object allocation, and opportunistic mark-sweep-evacuate defragmentation.
Forward-Backward Baum-Welch smoothing algorithm computing exact marginal posterior distributions of all hidden states given complete observation sequences.
Polynomial and Vector Commitment simulation framework proving evaluation correctness f(z)=y without revealing the entire vector payload.
Volume-Weighted Average Price (VWAP) benchmark engine calculating cumulative execution quality and institutional slippage metrics.
Production-grade genpark-hindley-milner-type-inference-skill skill for AI agents
Dynamo sloppy quorum and hinted handoff coordination engine providing high write availability under network partitions.
Distributed Lloyd's algorithm for optimal robotic sensor swarm area coverage and Voronoi partition centroid convergence.
RDFS forward-chaining deductive inference engine computing transitive closures across subClassOf, subPropertyOf, and domain/range type rules.
Poincaré disk model hyperbolic geometry engine computing hyperbolic distance metrics and low-distortion hierarchical tree representations.
Production-grade genpark-hindley-milner-type-inference-skill skill for AI agents
Dynamo sloppy quorum and hinted handoff coordination engine providing high write availability under network partitions.
transformers safetensors qwen3_5_moe text-generation trading solana
Native LLM chat client for the Apple IIGS (65816 / GS/OS / Marinetti TCP)
A smart home automation system that brings the power of a virtual assistant to your IoT devices. Inspired by the famous AI assistant "JARVIS" from the Iron Man series, this project combines cutting-edge embedded technology with natural language processing to create a seamless and intuitive IoT control experience.