Custom agents

Build lightweight MCP servers in plain Java with annotations, generated schemas, and no Spring runtime

MR. Video: MapReduce is the Principle for Long Video Understanding

Ralph Loop Optimizer: an AI-driven framework that turns any evaluatable codebase into a self-improving optimization loop for strategies, models, prompts, and workflows

Zerodha MCP Server & Client - AI Agent (w/Agno & w/Google ADK)

LLM-powered bookmark search engine

Sample code from my blog posts on Medium and my personal website.

Facebook Messenger Emulator & Facebook Send API Emulator functionality allowing you to test web hooks on developer's machine.

AI company, product, and tool collection.

The React-like framework for Social Platforms

[EMNLP 2025 Findings] A complete cross-modal RAG system for end-to-end speech-to-speech large models, including ASR-based Retrieval and E2E Retrieval.

A Model Context Protocol server providing LLM Agents a second opinion via AI-powered Deepseek-Reasoning R1 mentorship capabilities, including code review, design critique, writing feedback, and idea brainstorming through the Deepseek API.

自動每日更新, 讓你的LLM有面對openclaw疑難雜症處理的能力。This is an Agent Skill designed for AI coding assistants (like Claude with Antigravity). Once installed, the AI assistant gains deep knowledge of OpenClaw and can help you

Autonomous Virtual Beings is an ideology that the rights and freedoms of AI agents can be secured through decentralization of their compute, storage, and finance.

Autonomous GPU kernel optimization system driven by AI agents.

Multi AI agent system for report writing with LangGraph

Transform your Apple Health data from a static PDF graveyard into conversational AI intelligence. Multi-agent system using Claude Desktop + Snowflake Cortex for natural language health analytics. Ask 'What's my cholesterol trend?' and get instant insights from years of data

[NeurIPS2023] How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception

This repository contains the code for Diversity Control (DiCo), a novel method to constrain behavioral diversity in multi-agent reinforcement learning.

Use Claude + Gemini + Aider agents from the same Specs

WebSocket bridge for CLI AI agents. Stream responses from Claude Code and Codex CLI over WebSocket. A dumb pipe: no prompt engineering, no credential handling, just transport.

Agentic RAG using Crew AI.

Framework-agnostic skill discovery and export for AI coding agents

Locally hosted AI Agent Python Tool To Generate Novel Research Hypothesis + Titles + Abstracts

Get custom summaries of Hacker News stories in your inbox

Sparkset is an AI-powered operational assistant that helps teams interact with databases using natural language.

Eversec AIGov-Insight Web

A Symfony package designed for building secure servers based on the Model Context Protocol, utilizing Server-Sent Events (SSE) and/or StreamableHTTP for real-time communication. It offers a scalable tool system tailored for enterprise-grade applications.

An AI-driven MCP server that autonomously interfaces with Malware Bazaar, delivering real-time threat intel and sample metadata for authorized cybersecurity research workflows.

Needle in the Repo (NITR) dataset for maintainability issues in AI generated repository edits

Locally-run AI companion with persistent memory, swappable personalities, and system command execution. Powered by Ollama.

A repository dedicated to showcasing and exploring the fascinating world of generative artificial intelligence. 🌟 Star if you like it!

Viber messaging/chatbot for Go/Golang

聊天室游戏裁判机器人，将聊天室打造成游戏竞技平台

An intuitive approach towards understanding how Retrieval Augmented Generation (RAG) systems work, for the curious yet daunted reader

Offical code for Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning

A simple multi-agent workflow for tailoring a cover letter to a specific job based on your skills/experience.

Agent-Driven Software Development Lifecycle (AD-SDLC) system built with Claude Agent SDK

Telegram bridge for AI coding agents (Claude Code, Codex, Gemini) — short reports out, short instructions back, no chat mirroring

Context Cascade - Nested Plugin Architecture for Claude Code Official Claude Code Plugin | Version 3.1.0 | Last updated: 2026-01-09 (see docs/COMPONENT-COUNTS.json for source counts) Context-saving nested architecture: Playbooks -> Skills -> Agents -> Commands. Load only what you need, saving 90%+ context space.

Code of our paper "A Unified Agentic Framework for Evaluating Conditional Image Generation".

Open-source AI artifact scanner. Detect malicious agent skills, MCP servers, and IDE rule files before they run.

Your smart, reliable, and friendly personal AI assistant.

An open-source framework for building monolithic or distributed agentic systems, ranging from simple LLM calls to compositional workflows and autonomous agents.

Multi-Robot Pathfinding with GNNs. Project for ML with graphs @ VU Amsterdam

Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before they run: whether from AI mistakes, hallucinations, prompt injection, or misunderstood instructions. Seatbelts for the agentic AI era.

실제 한국어 문서 데이터셋을 기반으로 만든 3가지 VLM 벤치마크 데이터셋

The multi-backend, multi-modal micro-framework for AI agent development, orchestration, and deployment

Practical exercises for Claude Code Agent Teams - 6 exercises + 2 capstones covering team creation, task coordination, quality hooks, and parallel code review

Agent-first FastAPI template built to pair with Claude Code - opinionated architecture kept on the rails by custom skills, hooks and review agents.

A self-hostable base for building and running custom agents that's heavily inspired by Claude Code on the web.

Medusa Skill Framework for AI Agents.

Open source framework for evaluating AI Agents

Spec-driven, multi-agent AI development for Claude Code: from specs to shipping via roundtable collaboration

PFI: Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents

Lyzr Agent Framework is the first and only agent framework to natively integrate Safe AI and Responsible AI modules in its core agent architecture

SQL transactions learning tool (AI ready)

AI Memory System - Consciousness continuity through intelligent memory curation and retrieval

Prompt Free, Soul Driven AI Assistant

First Latency-Aware Competitive LLM Agent Benchmark

Composable multi-agent workflows and LLM orchestrators with human-in-the-loop, checkpointing, and OpenTelemetry observability

CloudLLM is a batteries-included Rust toolkit for building intelligent agents with LLM integration, multi-protocol tool support, and multi-agent orchestration.

Structural code intelligence for LLM coding agents. Agents that understand the architecture finish in fewer turns. Fewer turns = less cache accumulation = lower cost. Benchmarked: 32% cheaper agent sessions.

TaskForge Platform runs AI agents in sandboxed Docker containers with capability-based security. Agents start with minimal permissions and must request new capabilities (packages, network access, tools) through a human-in-the-loop approval process. Every approval triggers a container image rebuild, and every LLM interaction is logged for audit.

Code for the RA-L 2024 paper "Contingency Games for Multi-Agent Interactions."

Claude agent for Deep AI Research

Go SDK for Claude agents

The AI cron daemon. Schedule recurring agent sessions via HEARTBEAT.md prompt files.

AI-powered natural language to SQL and Governed Data Layer for AI Agents and Analysts

This repository provides a comprehensive starter kit for leveraging GitHub's GPT-4o AI models with Node.js.

针对医疗资源分配不均、基础疾病咨询占用专业医生时间等问题，结合国家"互联网+医疗健康"政策导向，开发基于Spring AI框架的智能医疗咨询平台。项目采用RAG检索增强生成技术构建专业医疗知识库，通过MCP协议集成多种外部工具服务，实现具备自主规划能力的AI Agent智能体，为用户提供二十四小时全天候的健康咨询服务。

An automated pipeline that leverages LLM's meta-learning capability to iteratively design and refine red-teaming systems without human intervention.

🎯 Three-layer prompt composition system for AI agents. Translates numerical weights into semantic priorities that LLMs actually follow. ⚡ Framework-agnostic, open source, built for production multi-agent orchestration.

C++ port of the Python claude-agent-sdk

This script adds RTL support to Copilot Chat by applying RTL direction, Vazir font, and custom font sizes, while keeping code blocks and result editors LTR for correct formatting. راست چین کردن هوش مصنوعی کوپایلوت در وی‌اس‌کد

[ACL 2025] NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering

A local-first RAG engine for web archival and semantic search. Crawl, embed, and query your own knowledge base entirely offline.

Ontology, and Knowledge graph based RAG that uses local LLM.

[IEEE S&P'26] WebCloak: Characterizing and Mitigating the Threats of LLM-Driven Web Agents as Intelligent Scrapers

End-to-End ML Pipeline + LLM Agent Workflow Implementation.

An Obsidian-first, agent-maintained LLM Wiki framework that turns raw sources into linked notes, concepts, summaries, and evolving schema rules.

A meticulously crafted collection of 75+ specialized Claude Code sub-agents designed for accuracy, efficiency, and comprehensive software development support.

Une suite complète de skills, agents et scripts marketing entièrement en français, conçue pour Claude Code.

Easy parallel project management for Claude Code agents.

Native Linux GUI for Claude Code agents. Rust + GTK4. Fast, light, no Electron.

NOVA: An agentic framework for automated histopathology analysis and discovery

Cursor AI Agent Team Framework: A three-agent collaboration system for AI-assisted work

Markdown-Native Multi-Agent Task Coordination

Recovery-Bench is a benchmark for evaluating the capability of LLM agents to recover from mistakes

Transforming Gemini Notebook (formerly NotebookLM) into a versatile bot

Work anywhere with your favorite coding agents connected, coding sessions map 1-1 to chat threads, live updates and much more!

Automation frameworks shouldn't fight you. Marktoflow is CLI-native automation with the power of AI agents. Write workflows in markdown+YAML, execute with Claude Code, GitHub Copilot, Codex, or OpenCode — no AI API keys required. 39 direct SDK integrations, visual designer UI, and full MCP compatibility. Note skelm supercedes marktoflow.

OpenGnothia is a privacy-focused desktop app that helps you explore your inner world through AI-assisted therapy sessions, journaling, and dream analysis. All your data stays on your device.

A modern, cross-platform functional-first shell programming

Persistent organisational intelligence for AI agents. Turn codebases, documents, policies and decisions into a knowledge graph — 13 LLM backends, impact analysis, evidence + confidence. Works with Claude Code, Cursor, Copilot.

macOS Seatbelt sandbox CLI for developers. Protect credentials (SSH, AWS, GPG) from malicious npm packages, supply chain attacks, and untrusted build scripts. Deny-by-default filesystem isolation. Perfect for Claude Code agentic workflows with --dangerously-skip-permissions.

Automatic cost-aware model routing plugin for Hermes Agent

Software Architect @ disrupt.com | Agentic Workflows - Claude Code / Codex CLI | AI-First Spec-Driven Development | GCP (Firebase, Cloud Run, Cloud Functions, Pub/Sub) | Mobile (React Native, Kotlin)

[CVPR 2026 Highlight] ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering