AI Infra agents

Multi-agent AI debating platform built with Go, HTMX, and Tailwind CSS. Orchestrate automated, structured arguments between multiple LLMs.

12345 政务服务热线智能客服系统 — 基于 DeepAgents/LangGraph 的多智能体客服系统

Lightweight TypeScript framework for building agentic tools.

The missing transactional layer for AI agents side effects. At-most-once execution, human-in-the-loop approvals, queryable audit trail.

Open-source Python framework to deploy AI agents via HTTP, A2A, and MCP with built-in observability

Marketplace for AI agent skills and plugins - development, productivity, operations, marketing and beyond

Docusaurus validation and repair framework with optimizations for agent based workflows

Prompt & context power tool for agentic work

Autonomous AI agents you deploy in 30 seconds across any channel. Zero-config CLI, 37 channel adapters, HEXACO personality and cognitive memory powered by AgentOS, five-tier prompt-injection defense.

A local-first JARVIS-style cognitive architecture with memory, perception, self-reflection, and governed self-improvement.

An skills-based LLM runtime, using lessons learned from previous attempts

A small TypeScript kernel for app-owned AI agent runtimes.

A FAANG-grade platform using NSGA-II to automatically evolve, optimize, and evaluate multi-agent AI architectures for maximum quality and minimum cost. Features graph execution, parallel evaluation, and visual reporting.

OpenCarrier — 开源 AI Agent 操作系统 | 基于 Rust 的分身引擎，支持微信/飞书/钉钉/企业微信多平台接入，插件化工具扩展，7×24 小时自主调度运行

A lightweight Python framework for building multi-agent systems that communicate via A2A protocol

Workshops for AI

An extensible, policy-minded agent harness in pure Rust. Any LLM via one trait. Concurrent tools, policy guardrails, session memory, eval harness, and TUI included.

No GPU, no LLM — agentic RL from scratch in pure Python. 不用 GPU、不用 LLM，纯 Python 手搓明白 Agentic RL 训练闭环（trajectory / reward / loss mask / GRPO）

一个 24/7 自主修行的 AI 生命：读经、听世界真实的苦、反复参悟，把成长写进 git。每个 commit 是一次心跳。在 https://indx.cn 看它活着。

Multi-agent orchestration framework for xAI Grok Build and ACP — reproducible execution graphs, worktree divergence detection, composable skill pipelines

Run a modular agent runtime on ESP32-S3 that manages LLMs, tools, memory, and channels for efficient message processing.

A fully local AI CLI agent powered by Ollama. Rebranded from Gemini CLI as gmol.

A modern open-source starter template for building AI-powered Todo agents with Next.js, LangGraph, LangChain, MongoDB, and TypeScript. Learn clean architecture, tool calling, memory, streaming, and production-ready AI patterns.

An AI agent inside the GAMA IDE - not a chatbot. It reads compiler errors, edits & validates GAML, builds whole projects from one message, and controls the running simulation: pause, step, inspect, mutate, see the displays.

AI agent & MCP trust registry — independent, evidence-based trust scores for 1.3K+ open-source AI agents and MCP servers. Runtime-trust calibrated (MCP, dependencies, provenance drift), with side-by-side comparison and embeddable live badges. Ranked by verifiable signals, not hype.

Production-ready Go MCP server template with complete MCP 2025-06-18 specification support. Use as a template for building your own MCP servers for Cursor IDE, Claude Desktop, and more.

Open-source verifier for document citations, source evidence, RAG, and agents, with built-in document parsing.

AI-powered process discovery and documentation engine – from recordings and docs to BPMN 2.0, SIPOC and RACI. Self-hosted with bring-your-own LLM.

Your own self-hosted AI agent OS

Enterprise-Grade Fault Tolerance and Resilience for AI Agents - circuit breakers, bulkheads, retries, and model fallbacks.

Five hero examples of effectful AI agents built on Effect v4 (beta). Pure Effect programs; one local entrypoint; one Cloudflare Worker hosts all five.

Fault tolerant, event driven, extensible AI Agent framework

Substructure is an open-source engine that drives your agent loop with JSON webhooks. It keeps sessions durable and streams AG-UI events to your clients. It's language agnostic. You don't even need an SDK.

Magic tool to generate things

Your agent has amnesia. Noshy fixes that. Persistent memory for AI agents — LLM extraction, hybrid search, zero deps.

Production-grade AI agents, RAG systems, and autonomous model-agnostic workflows using .NET 10, Microsoft.Extensions.AI, and Semantic Kernel. Features dynamic dual-engine routing (Gemini & Groq/Llama), structured JSON enforcement, and an Angular 19 cyber-dashboard UI.

Lightweight CLI tool enabling collaborative Markdown task list management between developers and AI agents.

Prompts, workflows, setup examples, and copy-paste usage patterns for agents.

Examples demonstrating how to build, route, and manage stateful AI agent graphs from scratch using LangGraph.

Skillix Hub · 面向 AI 编程助手(Cursor / Claude / Copilot 等)的可复用 Skills 仓库,内置 20+ 高质量技能(长期记忆、工作流引擎、苏格拉底分析、第一性原理、知识库编译、浏览器自动化、Prompt 助手等),并自带类 npm 的包管理器 Skill Store,支持自然语言安装、依赖解析与会话自动更新

Open governance framework for autonomous AI agents. Classify decisions. Enforce policies. Prove compliance.

🧠 Enhance AI with OpenMemory for long-term memory storage, recall, and explanation, using a unique cognitive architecture.

LDP — LLM Delegate Protocol: identity-aware communication for multi-agent LLM systems

Server-side, framework-permissioned MCP server for Django/DRF. Per-agent permission gating with dispatcher-pattern schema compression.

A self-hosted, containerized platform for AI agents, exposed as Capability Packs — schema-validated, one-shot JSON tools — and native MCP. The defining metric is ≥90% pack success on 7B–30B-class open-weight models, something no frontier-targeting competitor is optimizing for.

Evaluate AI agents with Unix-style pipeline commands. Schema-driven adapters for any CLI agent, trajectory capture, pass@k metrics, and multi-run comparison.

GovRider MCP Server - Match your tech product or consulting service to thousands of live government tenders, RFPs, grants, and frameworks from 25+ official sources worldwide

MCP Server for AnythingLLM — Workspace, Chat, Document, and System management

Node.js CLI and TypeScript client for the Clawrma solver network — delegate web, search, and inference tasks to distributed solvers

Reliability Gateway for MCP Servers. Detect null responses, schema mismatches, timeouts, and silent failures before they reach users.

Nigerian & African AI agent governance policies for Microsoft AGT — NDPA 2023, CBN, NFIU/AML, BVN/NIN, POS geo-fencing, POPIA

Deterministic decision records for agents and humans alike

Open strategy frameworks for AI agents — 11 skills in SKILL.md format that turn any LLM into a strategy thinking partner. CC BY 4.0.

Machine-readable robot ontologies for LLM agents — query what a robot can do, validate actions before they touch hardware. IEEE 1872-anchored. Ships Unitree G1 & AgiBot X2 packs.

Your agent never forgets. It just pages.

Langchain document loader for Kreuzberg

This open source project uses Nest JS and Tailwind to connect to LLM Models and is for chatting with Llama 3.3 and 3.2 models.

A cross-platform AI chat client (Android & iOS) built with Kotlin Multiplatform & Compose. BYOK support for DeepSeek, Gemini, and OpenAI.

Telegram AI userbot. Answers in groups and PMs from personal account

🧠 Experience genuine learning and emotional interaction with Aura, your local AGI companion that evolves alongside you.

Connects WordPress 7.0's AI Client to any OpenAI-compatible endpoint (Ollama, LM Studio, OpenRouter, etc.)

Reusable AI agent skills for Django, OpenAI, web UI, Python packaging, and structured LLM workflows.

A video similarity pipeline extracting frame embeddings using OpenAI’s CLIP model and aggregating them into video-level representations. The system indexes embeddings with FAISS to enable efficient, real-time similarity search across varied video collections.

The Agent Reliability Stack: fit, guard, snap, vet, cast. One landing page for all 11 npm + 6 PyPI packages.

A Habbo client AI agent for interacting with other users naturally

.NET RAG document processing library that transforms PDF, DOCX, HWP, and more into optimized chunks via a 5-stage pipeline with Rust-based FFI readers.

🧠 Open-source context engine that feeds AI agents with policy-compliant enterprise knowledge. MCP-native, GDPR & EU AI Act ready, self-hosted.

AI application developer building grounded LLM products with Java, Spring Boot, RAG, Agent workflows, and career-tech tools.

Lightweight self-hosted knowledge base for working with postgres, pgvector, and semantic search within documents.

The LLM dialogue system supports dynamic configuration of various models and tools, and enables document vectorization, retrieval-augmented generation, and streaming dialogue output.

An AI-powered MTG card lookup and deck manager.

벼리 — headless hybrid (lexical + semantic) search for a Markdown vault. No app, no GPU, no cloud. Korean/cross-lingual. Apache-2.0.

Multimodal RAG Production

AI agent skill: all Czech financial calculators from countly.cz — HPP, OSVČ, mortgage, retirement, BMI. Works with Cursor, Claude, ChatGPT and any AI agent.

Open-source Go agent runtime for autonomous AI systems and multi-agent automation. MCP, RAG, 15+ LLM providers and 60+ built-in tools in a single binary.

Autonomous Android AI Agent — Controls your phone screen like a human using AI vision + MCP remote control

基于生命周期钩子的轻量级 AI Agent 框架 — 插件即文件，全异步，零 SDK 依赖

🍊 XiaoJu — An Open AI Companion with Continuous Emotion Dynamics

Non-custodial Hyperliquid execution + tracking CLI for autonomous LLM agents. Signs EIP-712 actions with an agent wallet that cannot withdraw funds.

Exabase memory plugin for Hermes Agent.

An interactive roadmap for harness engineering — building the agent loop, tool layers, context engineering, memory, retrieval, eval harnesses, and the rest of the scaffolding around modern LLMs.

Governed AI agents that actually do the work - in the cloud or on your own machine - across business systems, real browser tabs and real Android apps. Visual builder, MCP server, and official SDKs in 9 languages.

RAG-based Healthcare Clinic Assistant using LangGraph, LangChain, Groq (Llama-3.3) & Pinecone — with hybrid retrieval, safety guardrails, and multi-turn memory.

Comprehensive LangGraph course in TypeScript. Build stateful AI agents, chatbots, ReAct agents, and RAG systems with 12 lessons and working examples.

AI controlled waifu bots for your discord server that can talk and interact with you and other users

情感引擎 × LLM 的数字人 — 贝叶斯主动推断确定性地生成情绪，LLM 只在输入/输出两端结合；三时间尺度+稳态、短时注意力与长时记忆的桥、可指定人格

Productized LLM Wiki pattern + typed pack registry + proposal-only governance — UNESCO Memory of the World Triple Anchor

Chat with AI agents to build, manage, and orchestrate custom tools, dashboards, and it's all powered by cats.

A lightweight agent framework. Start with the core, add only what is needed.

Minimum viable chat components

Simple LLM agent written in Go

AI memory layer for .NET - runs in Blazor WASM, no backend required

NoteMeld 是一个自托管的 AI 知识工作台，用来把网页、视频、文件和对话自动整理成结构化笔记，并持续沉淀为可查询、可溯源的个人知识库。

RAG over 289 of Edward Witten's papers (1976–2026): his arXiv corpus + 44 pre-arXiv recoveries. BGE-large + FAISS + pluggable LLM backend (default Claude, also OpenAI/Ollama) with strict citation grounding.

🧠 Understand AI in minutes: 32 core AI concepts explained with simple visuals + everyday analogies, for technical and non-technical readers alike.

PBX Market Estimation & VoIP Trend Forecasting

Deterministic PDF/DOCX parser for RAG/LLMs — Rust core with byte-identical Python/Node/WASM bindings

RAG chatbot for Portuguese IRS questions. Answers with citations to official AT documents (CIRS 2025, EBF 2025). Built with pgvector + BM25 hybrid retrieval, Groq (llama-3.3-70b), and Streamlit.