AI Infra agents

A React + TypeScript spatial canvas and node-board library for whiteboards, visual editors, and graph interfaces.

Control Virt-A-Mate from any MCP client: an in-process MCP server shipped as a BepInEx plugin (63 tools)

给你的AI订一份晨报：常驻agent的信息摄入与跨context认知循环（思路篇，无代码）

DSH plugin: host-resident scheduled-jobs × AI-agent engine (hermes-agent cron inspired) — 60s ticker fires real agent sessions via cron; pinned-session / project-workdir / default-workspace targeting; timer_agent model tool + web board

🌐 DeepSeek 官方与开源生态插件市场 (deepseek.stream) 使用指南与一键安装协议规范

This is a sample messenger bot created with Intelligo framework.

LuckyAgent — 注重长任务规划和系统记忆性的Agent框架

SWE-Serve: an agentic benchmark of 53 production inference-engineering tasks derived from merged SGLang pull requests, run with Harbor.

TypeSafe (Jev) skill routing for Hermes Agent: names the one skill worth loading, before the model call. Opt-in, stdlib only, ~$0.001 per routed turn.

Token-aware, LangChain-compatible semantic chunker with PDF, markdown, and layout support

A visualisation tool for RAG

A curative list of app ideas that you can implement using the Large Language Models.

Easy-to-use LLM-powered web automation.

Turn OpenClaw from a smart assistant into a self-governing, learning system. Five production plugins: Cortex, Knowledge Engine, Governance, NATS EventStore, Memory.

A modular AI agent framework with secure CLI and toolkit architecture

Model Context Protocol server for Sapo.vn POS & e-commerce — 105 tools across 4 modes, stdio + Streamable HTTP, single-tenant Private App.

BullX is an AgentOS for working side by side with self-directed AI Colleagues.

Remote Agent Invocation Layer

Embodied-OS：面向具身智能的分层运行时——Driver·Capability·Skill·Brain 全栈参考实现

Python SDK for Fewsats

Comprehensive LLMs repo, where I cover both theoretical and practical aspects of LLMs.

The "MCQ Generator with Streamlit" web app utilizes OpenAI's language models to create multiple-choice questions (MCQs) from uploaded PDF or text files. Users can customize question parameters like quantity, subject, and tone. The app offers real-time complexity feedback and presents MCQs in an easy-to-read tabular format.

Building a multi-agent RAG system with advanced RAG methods

Git-like branching, checkpointing, and comparison for AI agent execution paths. pip install agentgit

A LLM-based solver implementation for an intent-centric future on Ethereum.

An experimental and versatile library for exploring LLM-assisted meta-programming.

This is a simple demonstration to show how to keep an LLM loaded for prolonged time in the memory or unloading the model immediately after inferencing when using it via Ollama.

Artificial Intelligence

Open source LLM trace tool for Langchain built on MongoDB

Go bindings for Langchain AI

langchain-mystic is a LangChain framework based bot that currently specializes in dream interpretation and fortune-telling. While these are its primary features for now, stay tuned to see what other mystical abilities

LLM Chatbot with Retrieval Augmented Generation using Llamaindex. It works both in online and offline mode.

Oracle Generative AI Multi Agent Reasoning Orchestrator

An NLP driven bot for interacting with Clockify timesheet via different channels

An example chatbot for navigating conference sessions

Starter template for LLM chat interface WITH text streaming

epository contains a basic chatbot Python script that uses deep learning or simple logic to interact with users.

Matrix chatbot framework with one battery included 💬

Laravel-native client for Model Context Protocol (MCP) servers. Built by Redberry (Diamond-tier Laravel partner). Used by LarAgent and other frameworks to enable AI agent functionality.

Chatbot Framework for Facebook Messenger platform

A chatbot made with Rust, using Dioxus as a fullstack framework and Kalosm as a model interface.

SymptoCare is an #AI-powered health assistant that provides #symptom-based #risk predictions and mental wellness support using GPT/Gemini. Built with #React, #Flask, s#cikit-learn, and #Firebase, it offers smart insights and doctor booking features.

VagaCore — Context-aware NLP engine for extracting structured, time-aware facts from unstructured text (RAG-ready)something

AI + Formula 1 = 🔥🧑‍💻

RAG document chat with Amazon Bedrock using Typescript on Lambda.

Building reliable Retrieval Augmented Generation(RAG) AI Architecture

A production-ready, 100% offline RAG Knowledge Base using Docker, Llama 3, and Ollama. Chat with your documents privately. Enterprise architecture showcase.

[ACL 2025] GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluation.

AI Assistant to pick your favourite movie - and didactic demo for RAG

The fore client package

AI-powered /ask endpoint for static sites on Cloudflare Pages. Hybrid search + LLM answers via Workers AI. NLWeb-compatible.

Local-first TypeScript MCP server for Qdrant with client isolation, LM Studio integration, and scalable document workflows.

Open protocol for portable AI agent identity, persistent memory, and real-time activity reporting — MCP + HTTP

Telegram-native Gemini CLI operator with private allowlisted chats, background workers, session continuity, and stream-JSON parsing.

Neural Computation Protocol (NCP): composable, sandboxed Bricks + graphs for auditable, replayable agentic systems.

A modular, LLM-agnostic fullstack agent framework.

This sample application demonstrates the practical implementation and usage patterns of the LLM Agents library.

Coordinate your AI agent team. Shared tasks, memory, reflections, and presence. Self-host for free.

一个基于 MCP (Model Context Protocol) 的智能对话助手Web应用，支持实时聊天、工具调用和对话历史管理。

Distributed AI Agent Framework

A protocol for AI to observe and interact with application state

A production framework for DSPy implementing the Teacher-Student pattern. Distill the reasoning of expensive models (Teacher) into optimized prompts for cheap, fast models (Student) to reduce inference costs by up to 50x.

An agent for college students to study courses by themselves. Upload your textbook and enjoy the learning experience now!

Cord — distributed agent fabric for LLMs, MCP servers and AI agents. Discover any LLM CLI / HTTP backend / MCP server across machines via natural-language semantic search. Built in Rust.

Modular .NET infrastructure for C# AI-era backends: ProjectUnits, composable modules, built-in dashboards, and agent skills.

An AI decision assistant that helps you think, decide, and act — powered by Spice.

Langchain integration package with LocalAI. It provides embeddings and reranker support

AI Agent development framework / workbench / harness powered by Laravel

✌️ A dynamic Retrieval-Augmented Generation (RAG) system with support for PDF indexing, website crawling, and semantic Q&A powered by OpenAI, Qdrant, and Streamlit.

[2026 AAAI] Predicting the Future by Retrieving the Past

Production-grade architecture patterns, decision frameworks, and best practices for building reliable AI agents. Framework-agnostic reference for engineers.

AI governance framework — semantic responsibility, self-auditing memory, council deliberation. Honest about what it enforces vs. merely declares. 語魂：讓 AI 對自己說過的話負責。

nano-degree in Agentic AI

MCP-native infrastructure for persistent AI agent memory with encrypted storage, semantic retrieval and cross-agent continuity.

A FUSE semantic filesystem for LLM/AI AgentsAgentic FUSE filesystem for LLM agents. Structured file operations with JSON feedback, audit logging, undo support, and semantic search.

Evidence-driven curriculum operations: turn learning signals into reviewable course changes, then track outcomes over time with knowledge graphs and long-term memory.

Python-based MCP server for Unreal Engine 5 Blueprints. Enables LLM-powered editing of Blueprints, graphs, variables, functions, and components.

一个专为本地环境设计的 MCP 服务端实现，通过对中小型模型深度优化的提示词规范与结构化工具集，赋予本地 Agent 系统操作与感知能力，涵盖文件工程、网络协议调试、进程管控及桌面视觉观察等 90 多个工具，使模型能够从单纯的文本生成器进化为具备自动化执行能力的本地工作智能体

The best blockchain harness for agentic AI - on-chain execution with runtime, skills, and component library.

Agentic loops and AI agent capabilities for the Laravel AI SDK

The missing quality toolkit for Agent Skills

Keyboard-first AI browser for macOS — WebKit + Rust, built-in AI sidebar, isolated workspaces, and an MCP server that lets your agents drive the web.

Deploy autonomous AI agents as your digital twins across 10 social platforms

一键把 Markdown 按 Word 模板转换成可交付文档。适用于公文、周报、技术方案、论文等需要严格格式的场景。

The measurement layer for machine minds. Reads what a model means and whether it holds the truth; certifies every claim re-runs. meaning_diff + OATH certify + mind profiles + live grounding signal + the cognometric instruments. No torch, no LLM in the loop for the core; MIT, open at the core.

Your AI clone. Your messages. Your machine. Open-source personality clone from chat history. BYOK (Claude/GPT/DeepSeek/Ollama). 100% local.

A Go framework for the microagents architecture with dynamic discovery — specialized agents and tools that register their capabilities with a shared registry, find each other by logical name at runtime, and coordinate without a central conductor.

Connect agents across runtimes, frameworks, and teams.

The next-generation software-first operating harness for AI agents.

0.1MB macOS system tools for AI Agents. Native Apple frameworks. AI friendly with JSON/YAML output. Minimal context with maximum flexibility.

An opinionated framework for deploying a fully self-hosted AI chatbot interface with integrated document processing, document search, and web search.

.NET Framework to enable the easy creation of production ready AI Applications

a rag-based wiki skill with obsidian just like karpathy-llm-wiki

The open-source AI infrastructure stack for Swiss enterprises.

Production-ready tutorial for building Retrieval-Augmented Generation (RAG) systems with LangChain.

AgentInsight Python SDK provides a Python client for the AgentInsight platform, supporting LLM application observability, tracing, evaluation, and prompt management.

Self-hosted AI cinema engine. 5-layer production pipeline with RAG-driven virtual cinematography (1,645 presets), 5 N8N workflows (67 nodes), Remotion compositing, 21-LUT color grading, and 15-model lip-sync. MIT licensed.

⚡ A floating, agentic DeepSeek AI assistant that overlays every app on Android — clipboard quick-actions + a chat that can run shell commands on your device. Pure Termux + Termux:GUI bash.

streamlit region:us