AI Infra agents

Affiliate creator discovery engine & commission negotiator (Influx style)

Predictive customer churn & 12M CLV regression synthesizer (Pecan / Julius)

GenPark AI Agent Skill - Practical capability for commerce and influencer workflows.

Generative cinematography 3D camera trajectory controller (Runway Gen-3 style)

Unified multi-channel commerce orchestrator and 3PL warehouse fulfillment (Cart.com style)

Fast unstructured PDF & multi-column table extractor to Markdown/JSON

Universal LLM proxy load balancer with failover & rate limits (LiteLLM style)

Visual workflow canvas orchestrator for modular LLM pipelines (Dify style)

GenPark AI Agent Skill - Propensity score matching and Inverse Probability Weighting (IPW) estimator calculating Average Treatment Effect (ATE) under conditional ignorability.

Autonomous Agent Double Ratchet Key Derivation & Forward-Secret End-to-End Secure Channel Engine

Echo State Network (ESN) reservoir computing framework mapping temporal sequences into high-dimensional non-linear dynamical recurrent states.

Autonomous Agent Double Ratchet Key Derivation & Forward-Secret End-to-End Secure Channel Engine

Echo State Network (ESN) reservoir computing framework mapping temporal sequences into high-dimensional non-linear dynamical recurrent states.

GenPark AI Agent Skill - Graph-theoretic backdoor criterion validator and minimal confounder adjustment set identifier ensuring unconfounded causal effect estimation.

GenPark AI Agent Skill - Structural Causal Model (SCM) DAG engine evaluating observational distributions and simulating Pearl's do-calculus interventions.

Autonomous Agent Tabular Q-Learning Temporal Difference Reinforcement Learning Engine with Epsilon-Greedy Exploration

GenPark AI Agent Skill - Structural Causal Model (SCM) DAG engine evaluating observational distributions and simulating Pearl's do-calculus interventions.

GenPark AI Agent Skill - Propensity score matching and Inverse Probability Weighting (IPW) estimator calculating Average Treatment Effect (ATE) under conditional ignorability.

Autonomous Agent Tabular Q-Learning Temporal Difference Reinforcement Learning Engine with Epsilon-Greedy Exploration

GenPark AI Agent Skill - Graph-theoretic backdoor criterion validator and minimal confounder adjustment set identifier ensuring unconfounded causal effect estimation.

Loopy Belief Propagation (LBP) engine on general factor graphs with sum-product message passing and damping to solve approximate inference on cyclic topologies.

Universal LLM gateway with intelligent routing. One OpenAI-compatible endpoint → automatic model selection from your pool (cheap local + expensive hosted) based on the task type and complexity.

Global creator network campaign matcher & ROI predictor (SparkFly style)

Semantic clipboard history vector buffer & secret redaction (Clipboard Manager)

Stateful autonomous AI employee lifecycle supervisor & task worker (AI Employee)

Joint-embedding predictive architecture (JEPA) world representation (V-JEPA style)

Marketing Mix Modeling (MMM) adstock & saturation estimator (Robyn style)

OS GUI desktop automation vision agent from screenshots (Computer Use style)

Realtime search reranking & factual citation grounder (Perplexity / SearchGPT)

Hierarchical HNSW vector index approximate nearest neighbor searcher (Qdrant)

Autonomous price negotiation discount broker & margin protection (Klarna AI)

Distributed multi-agent chaos latency injection & fault fuzzer (Chaos Mesh)

Multi-step deliberative reasoning search graph verifier (Perplexity Pro style)

Modular B2B procurement marketplace portal with cXML PunchOut (DJUST style)

15-minute quick commerce warehouse order batching optimizer (Astro style)

Payload filtered HNSW vector similarity engine with quantization (Qdrant style)

Symbolic step-by-step mathematical proof solver & LaTeX engine (AI Math Solver)

100% toxin-free natural cookware recommendation catalog and health profiler (The Indus Valley style)

Lightweight multi-agent routine handoff orchestrator & tool swapper (Swarm style)

Real-time WebSocket connection mesh rebalancer and broker with sub-ms failover (Centrifugo style)

Agent session replay behavioral audit recorder & anomaly detector (AgentOps)

Agentic machine micropayment escrow settlement gateway (Stripe Agent Toolkit)

Zero-dependency heuristic adversarial prompt injection & override neutralizer (Lakera / NeMo)

Curso aberto de engenharia e customização de LLMs em português, do zero à produção, com laboratórios reproduzíveis.

Hierarchical episodic & semantic user profile memory graph synthesizer (Mem0)

Autonomous DOM state tree mutation observer & selector healer (Browser Use)

AI agent safety layer for crypto transactions - blocks honeypots, blacklists, and rug pulls before they happen

Production-ready OpenAI Agents SDK (TypeScript) template — agents, handoffs, tools, guardrails, sessions, tracing, CLI.

RAG evaluation and observability lab.

企业级安全研判多智能体平台，基于多 Agent 协同与 Supervisor-Worker 分层推理架构，融合全链路 RAG 能力体系（文档解析、Hybrid Retrieval、多意图识别、Query Rewrite）与分层记忆机制，实现多源安全事件接入、风险研判、处置决策与智能运维的闭环协同。平台内置可观测与质量评估体系，支持请求级 Trace、Token 消耗分析、成本核算及 KPI 量化评估，实现多 Agent 协同的全流程监控与运行治理。

Custom Trained LLM application with Llama, and grounding via RAG. This project uses Streamlit to create a simple UX LLM based chatbot with Llama3 & RAG grounding on Stehen Hawking's books

ClawCut-MLX Proxy - A high-performance bridge between OpenClaw and LLM.

Complete alignment and safety architecture for autonomous AI agents. Membrane security, continuous trust verification, epistemic hygiene, emergence protocols, and defence tools. 30 years of cybernetic research — deployable today.

Transforms MCP tools into collaborative, reasoning agents using modern agent frameworks.

A simple AgenticAI RAG agent showcasing autonomous reasoning and decision-making by integrating thought, logic, and action in real-time tasks.

MemorizedMCP delivers a high‑performance, local‑first MCP Server in Rust that equips AI agents with an advanced hybrid memory system. It combines a knowledge graph, vector embeddings, and full‑text search with a novel documentary memory capability, enabling accurate recall of exact documents alongside rich semantic relationships.

This project helps you check your JetBrains AI Assistant quota usage information. 本项目帮助您查看 JetBrains AI Assistant 的配额使用情况。

Fullstack Chatbot using open source LLM (Huggingface)

Runtime Reliability Infrastructure for LLM Pipelines — enforce deterministic rules, measure the Balance Index, and audit every decision.

A Streamlit document Q&A assistant for PDF, DOCX and TXT files, with OCR for scanned pages and TF-IDF retrieval over a FAISS index.

TurboQuant vector quantization for browser and edge runtimes

OpenHAB-MCP: Total command of your OpenHAB (v5+) system via the Model Context Protocol. Full exposure of Items, Things, Rules, Persistence, and Semantic Tags.

Harlo — Your AI coach. Built on USD composition semantics for persistent cognitive state management. Patent Pending.

🚀 High-performance MCP (Model Context Protocol) server built with Fastify, TypeScript, and functional programming. Production-ready with authentication, metrics, and auto-discovery capabilities for AI agents and LLM applications.

AI-powered chatbot built with Python, NLP, and Flask — automate customer support queries with intent recognition and dynamic responses.

Creating Bedrock Agents with Streamlit Framework

Transform vague prompts into clear, actionable instructions - promptly and thoughtfully

Python bindings for Cross-Language MCP Orchestrator, think of LangChain + Vercel AI kit but for MCP

🧰 Tool Search Engine for Efficient Tool Use in AI Agents

🦞 Curated OpenClaw config templates for Chinese LLM providers, multi-channel setups, automation & more | OpenClaw 配置模板大全

Backend server for AGI OS - Awesome Gamer Insight Orchestrating System

Lightweight MCP client that uses a local Ollama LLM to query multiple MCP servers defined in config.json

A library for creating structured collaborative worlds for AI agents and humans. OpenClaw compatible.

Semantic side-effect tracking for AI agents.

LLM inference in solana programs.

A curated collection of OpenClaw resources, guides, skills, and best practices. Open source AI agent platform for WhatsApp, Telegram, Discord automation.

Cycles budget and action guard for OpenClaw agents

A framework for agentic AI software engineering workspaces

Self-improvement loops for OpenClaw agents via multi-model LLM council

Prompt generator for LLM agents with interceptors

🤖 Lightweight, message-first agent runtime

Empowering Decentralized Applications with Intelligent Agents

基于 ChatGLM 等大语言模型与 Langchain 等应用框架实现，开源、可离线部署的 RAG 与 Agent 应用项目

LLM chatbot example using OpenVINO with RAG (Retrieval Augmented Generation).

Learning and sharing about libraries and frameworks on LLMs 😎

mini prompts for LLMs

JS bindings for Cross-Language MCP Orchestrator, think of LangChain + Vercel AI kit but for MCP

Implementing Retrieval-Augmented Generation (RAG) with constructed Knowledge Graph

This chatbot lets users upload and query multiple documents, using RAG to provide precise answers by combining retrieval and generation techniques.

A Scripting Language for Building LLM Apps

Question Answering Generative AI application with Large Language Models (LLMs) and Amazon OpenSearch Service

Gradio demo of LLM chatbot using RAGs

An implementation of Retrieval Augmented Generation (RAG) to enhance Large Language Models for Document Q&A and Information Retrieval.

An Bot wich can use most of Large Language Models

AI-Agent powered academic paper discovery engine

finLLM using llama-2-7b-chat-ggml, langchain, chainlit, and faiss vector db on encyclopedia of finance, sfsu

Personalized AI assistant for university students who answers from the students' slides, textbooks, and notes.

Demo server for NLUX's website, that uses LangChain and OpenAI

Declarative prompting and optimization for LangChain-style pipelines. Enterprise ready.