Custom agents

Aligning Agentic World Models via Knowledgeable Experience Learning

Scholar-Agent Intelligent Research Assistant, Literature Search, Metric Extraction, AI Analysis

Cortex is a fast, private desktop AI assistant for running local Large Language Models with Ollama. Everything stays on your device: no cloud, no external servers, and no third parties.

[ICML 2025] UDora: A Unified Red Teaming Framework against LLM Agents

An AI-powered agent designed to watch live streams, understand the content (audio, chat, video), and participate in the chat automatically using a Large Language Model (LLM).

AI Runtime Kernel — a context operating system for AI agents. Eliminates tool bloat, loads only what’s needed, and gives LLMs their reasoning space back.

AgenticInternet is an innovative project focused on empowering agents to autonomously browse, interact, and collaborate across the web. Our goal is to create an intelligent assistant capable of executing complex online workflows, enhancing productivity and creativity for end-users and organizations.

msl-data-ai

Submit your AI tool or AI Agent in AI directories

Enterprise-grade distributed AI agent framework | Develop → Deploy → Observe | K8s-native | Dynamic DI | Auto-failover | Multi-LLM | Python + Java + TypeScript | MCP + A2A + REST

This project contains source code to demonstrate the usage of Retrival Augmented Generation (RAG) feature using Spring AI using PG Vector as the Database and Ollama as the Local LLM

🚀 The Ultimate Laravel 12+ Mastery Roadmap. Master Advanced Architecture (DDD), AI Agents (laravel/ai), RAG, DevOps, and System Design. Includes 300+ Senior Interview Questions & 50+ Visual Diagrams

Content Operating System — content marketing, SEO, social media, publishing. Create it. Publish it. Measure it. Optimize it.

Git-native architecture catalog — Markdown registry, schema-driven UI, AI-ready

agent-bridge

Threlte Live – A SvelteKit + Three.js platform for live-streaming 3D VRM avatars. Features real-time chat with Google Generative AI, ElevenLabs TTS lip-sync, Mixamo animations, and Cloudflare edge deployment – perfect for creating interactive, high-performance streaming overlays.

CORE is a governance runtime for autonomous AI systems. It enforces constitutional rules during execution, prevents governance bypass, and creates auditable authority chains for agent actions across operational domains.

Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings, and build accuracy profiles over time. Agents that catch real bugs get picked more often. Agents that hallucinate get deprioritized. MCP server for Claude Code, Cursor, and other IDEs.

SPY put-credit validation and real-money control plane with broker-backed ledgers, deterministic risk gates, hybrid RAG, reconciliation, and $1k/mo after-tax evidence tracking.

Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents, branching workflows, memory persistence, human-in-the-loop, multi-agent systems, and production deployment. Supports 14+ AI coding agents via Agent Skill Standard.

Deterministic governance for AI coding agents. Cedar-based policy engine that intercepts every agent action and evaluates it against deterministic rules before execution.

Multi-role AI orchestration runtime for Windows. Quality-gated pipeline (Brain → Miranda → Pappy → Benson) with MCP support, SQLite persistence, and a self-improving distillation loop. Coding you can trust.

[AAAI 2026] The offical implementation of paper "FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation"

UAVBench: An Open Benchmark Dataset for Autonomous and Agentic AI UAV Systems via LLM-Generated Flight Scenarios

TMLR | This survey presents a comprehensive and structured synthesis of memory in LLMs and MLLMs, organizing the literature into a cohesive taxonomy comprising implicit, explicit, and agentic memory paradigms.

(Mostly) autonomous AI coding toolkit for Claude Code based on RALPH and PRD-driven development.

Gate for AI is an AI-native crypto infrastructure that enables AI agents to trade, analyze markets, manage wallets, and query on-chain data through MCP (Model Context Protocol) and modular AI Skills. Integrate ChatGPT, Claude, and OpenClaw with CEX + DEX capabilities.

Generate App Store & Google Play preview videos and screenshots from a simple TypeScript config. Built on Remotion + React + Tailwind. Ships with AI agent skills for Claude Code — scan your app, direct the creative, render to MP4.

A framework-agnostic UI kit of production-ready components for building AI and LLM chat interfaces.

🏠 An AI real estate app featuring secure auth, conversation management, & personalized property recommendations. Powered by Agentic AI, RAG (w/ Pinecone), GraphRAG (w/ Neo4j), MCP, kNN, K‑Means Clustering, CoT, LangGraph, and a Mixture‑of‑Experts ensemble to deliver accurate, effective, and scalable AI insights. Also features a VS Code extension!

autonomous trading agent (rust)

A SQLite extension that enables SQLite databases to run autonomous AI agents, using other SQLite AI extensions.

多Agent竞品情报与市场研究系统

Security AI helper for Caido: pipes your local Claude Code / Gemini / Codex / Copilot CLI through 18 MCP tools for manual web security testing. Local-first, no API keys.

Let any AI coding tool — Claude Code, Cursor, Codex — drive your real Chrome. One-prompt setup, muscle memory, local-first.

Self-hosted project management with AI copilot. Linear-like UX, Jira scale, pair-programmer AI. Next.js + PostgreSQL + Docker.

AI-powered Chrome automation server with natural language element detection. Control Chrome browser through MCP protocol for testing, debugging, and performance analysis. Features 91% accuracy in element location, works with free AI models, and supports Gemini, Claude, Cursor, and Copilot.

🐍 Personal AI agent in pure Python — OpenClaw reimagined. Memory, RAG, skills marketplace, cron, voice. Telegram/Discord/WhatsApp/Web. Works with DeepSeek, Claude, Gemini, Kimi, GLM, Ollama.

A Model Context Protocol (MCP) server for Elsevier Scopus. Allows AI assistants like Claude to search academic papers, retrieve abstracts, and analyze author profiles directly.

Your personal multi-asset quant research team, powered by LLMs. Crypto + A-share + HK + US, with backtest engine, factor lab and event-driven news intake.

Prior direction, kept rather than deleted. Signed, offline-verifiable receipts for AI agent actions, and a reference implementation of the OWASP Agentic Skills Top 10 AST09 receipt pattern. Nobulex is now the independent reliability registry for agent tools: github.com/arian-gogani/nobulex-registry

[AAAI 2026] LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodules

FAT Agent (Fix, Audit, Test) — a Claude Skill that automates post-launch website QA. Audits SEO, security, accessibility, performance, and more.

Privacy middleware for LLM & RAG pipelines - consistent pseudonymization, encrypted vault, SSE streaming rehydration.

miniforge is an autonomous software development system designed to behave like a factory, not a chatbot

Code for Paper: Benchmarking Multi-step Scientific Tool-use in LLM Agents

Metasploit for AI agents: scan, attack, and fix AI agents and MCP servers. Open source security toolkit.

Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, refusal templates, and a read-only injection auditor. MIT.

An end-to-end demo of an autonomous agentic mobile manipulator for warehouse robotics, showcasing fully on-device perception, reasoning, and natural language control in a ROS 2 simulation using AMD Ryzen™ AI hardware.

Multi-Agent System built with Google ADK and OpenRouter models, coordinating specialist agents to query PostgreSQL (via MCP Toolbox) and Data Commons for HDB resale data and global statistics.

Facebook Ads Analyzer 是一个专业的广告数据分析系统，基于facebook_ads 的 claude code agent skill ,能够： 自动分析 Facebook Ads Manager 导出的 CSV 数据 根据不同广告目标（互动/转化/流量）智能评估广告表现 识别最佳和最差广告 生成详细的诊断报告和优化建议 提供数据驱动的投放策略方案

Integration toolkit for connecting AI agents to the Visa Intelligent Commerce platform.

The LLM Council works together to answer your hardest questions

Planner/Generator/Evaluator orchestration harness for Claude Code (and Codex)

Agent Skill: PHP 8.x modernization patterns - typing, attributes, PHPStan | Claude Code compatible

Eve Agent V2 Unleashed — local-first autonomous AI coding agent powered by Ollama

The first open-source GEO linter. 92 rules for SEO, GEO, and content quality — built for AI agents to run, read, fix, and re-lint automatically.

Native rules, hooks, and guards that prevent Claude Code and Codex from hallucinating code, duplicating files, or shipping unverified changes.

Multi-tenant AI assistant platform on Amazon EKS. One-command deploy, scale-to-zero per user, powered by Amazon Bedrock.

The universal interface layer between AI agents and humans. Generate rich UIs on demand via MCP.

Claude Code skill for recursive research up to PhD level across any domain. Source tiering, WDM + Munger inversion for autonomous decisions, and disk checkpointing to survive context compaction.

计算机专业 Skills 大合集：610 个 Claude Code / OpenClaw 风格 skills，覆盖编程、前后端、云平台、AI Agent、科研、自动化与安全审计。

Persistent memory system for Coding Agents (Claude, Opencode, Codex), infinite context, learning extraction, persona modeling and so much more!

Your local-first AI ad ops crew. Works with Claude Code, Cursor, Codex & Gemini.

全网首个 CNIPA 2026 规范同步、产品级、可复现的中国发明专利 Claude Code Skill — 30 秒装好，一句话起草专利。

Shared reality for agents.

Hermes Agent-focused architecture and runtime health checks

Cortex Space is a local-first developer workspace built with Tauri v2 + React. Replace static terminals with a fluid, keyboard-driven environment featuring recursive split layouts, drag-and-drop panes, AI agent workflows, command snippets, and automatic port detection.

From Agent to Agency — 一个 AI 做不了的事，一群 AI 可以。Multi-Agent Collaboration Platform.

PostgreSQL SKILLs for AI Agent

An AI legal workflow running on Claude Code. Four legal agents — each with their own jurisdiction, knowledge base, and MCP tools — collaborate to produce legal opinions with full audit trails.

Let your AI agent call thousands of APIs — correctly.

Ranked local search for AI coding agents. Search the current Git worktree, selected paths, external folders, or exact files. Single binary, no server, no API key.

A curated skillstack for AI agents. Make your AI code editor write code like a Tech Lead. Stop copy-pasting instructions. Install 794 expert rules, workflows, and custom personas in Cursor, Claude Code, and Windsurf with one CLI command.

AI agent harness tool allowing it to wipe its own session context and re-run the first message

A free, living knowledge base on vibe coding — building SaaS fast with AI agents, local AI, and agentic workflows.

Axon reads the logs your AI coding-agent harnesses already write — Claude Code, Codex, OpenCode — and shows which harness, project, agent, and model is working, how fast, at what cost, and how much code it's producing.

Official Repository for our paper: PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

Code for paper OpenWebRL: Online Multi-Turn Reinforcement Learning for Visual Web Agents

Deterministic agentic-style multi-hop RAG at research-SOTA parity on commodity LLM APIs — no GPU, proof tree per answer.

Run MoE LLMs on Apple Silicone via MLX that your Mac should not normally be able to run

The open-source debugging agent for developers. We connect your favorite coding agent to prod to fix application bugs automatically. Run us locally and eliminate PR slop.

MCP server connecting AI agents to ITASCA FLAC — run continuum simulations through natural conversation

ClinicalAgent: Clinical Trial Multi-Agent System with Large Language Model-based Reasoning. BCB '24: Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics.

Methodology + templates for a trustworthy, traceable, self-growing AI data-analyst agent: metrics-first, independent read-only validation, and a self-growing rule library.

Opencode-Raven keeps noisy tool work behind a focused Raven agent, so your main model gets compact answers instead of raw search results, docs pages, GitHub examples, MCP output, or large MCP schemas.

Turn failed Python tests and CI runs into replayable debug sessions.

A living literature repository for Token Economics for LLM Agents: A Dual-View Study from Computing and Economics.

Confine an AI agent (Claude Code, Codex, oh-my-pi, ...) to one directory with a BPF-LSM program, and watch it live over eBPF.

Pixel-native visual RAG ported to Rust on the ruvector ANN substrate (HNSW + IVF-Flat) — screenshot/document retrieval over visual embeddings, a Rust port of PixelRAG, with a metaharness benchmark CLI: npx rupixel

Introduction course for the Microsoft Agent Framework in C#

Coding skill for building location-aware applications across the MapTiler platform.

First open-source AI knowledge layer for Togo - 62K+ documents, RAG API, fine-tuned LLM. Built for developers, startups and institutions in francophone West Africa

Cloak, Honey, Trap: Proactive Defenses Against LLM Agents

A self-evolving knowledge accumulation & hybrid retrieval system for AI coding agents (Claude Code / Codex / etc.)

五运六气 AI Agent 技能包 — 中医运气学说推算引擎。干支推算 + 六气步移 + RAG五层知识库(104键) + ReAct推理工作流 + 自进化引擎。支持 Claude Code/Codex CLI/Cursor/Cline/OpenClaw 等 AI 客户端。