Custom agents

Intelligent Document Reranking RAG System

Demo building Restaurant Recommendation Chatbot based on Yelp Public Data

Rune - Discipline Engineering - Multi-agent engineering orchestration for Claude Code. Plan, work, review, and audit using Agent Teams.

Multi-agent pursuit in matrix world (pursuitMW)

基于 Claude Code 的故事生成 Agent Runtime，支持梗概确认、剧本/分镜生成与评估回路。 / A Claude Code-based agent runtime for story generation, with synopsis gating, script/storyboard generation, and evaluation loops.

This is the Official Implementation of "CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution" by Tom Zehle

Machine Learning and Guidance of Swarm in Dynamic and Partially Observable Environments

Ipsa cognitio fructus

Local-first AI inference platform for LLMs — private chat, RAG, defense-in-depth security (Daily/Bulbe, encryption at rest, 2FA), on your own hardware. SvelteKit + FastAPI

Autonomous AI trading system using xAI Grok for market analysis and Interactive Brokers for execution

Asyncio-native Actor framework for Python agent systems — supervision, middleware, pluggable mailbox

AI‑powered personal finance app and website with Flutter and React frontend, FastAPI backend, and an MCP server pipeline for realistic financial data and AI insights. Check out my blog: https://alwaysanidhya.medium.com/how-48-hours-of-caffeine-chaos-and-code-got-us-to-the-finals-at-googles-ai-hackathon-d988690eeb7a

🐆 Self-hosted AI workstation stack for @amd

GO-CODE is a terminal-based AI coding agent. It helps you automate coding tasks, execute shell commands, and manage files directly from your terminal. GO-CODE is designed for developers who want to interact with their codebase and operating system efficiently using natural language.

ClawAI is a Lightweight, Action-oriented Personal AI Assistant.

A Model Context Protocol (MCP) server that lets conversational and autonomous agents securely access and manage HiPay’s payment services.

Meet Likhee: your personal writing teacher and companion that helps you write with ease, confidence, and creativity.

Governed Model Gateway & Agentic Recording/Debugging Platform

NLIP’s Security Guidelines and Best Practices is the companion to the NLIP core specification, brought to you by the NLIP Security Working Group.

Generate a newspaper from my Readwise Reader inbox based on my recent reading and writing

🤖A Voice-First Agentic AI for Government Schemes in Hindi. Built with LangGraph (State Machine), Groq (Llama-3), and EdgeTTS for low-latency, CPU-optimized inference without GPUs.

📊 Analyze 小红书 data to uncover market opportunities and user needs, generating automated reports for business idea validation.

Official samples and examples for the Rezzy API

A Python package for tracking and analyzing LLM usage across different models and applications. It is primarily designed as a library for integration into development process of LLM-based agentic workflow tooling, providing robust tracking capabilities.

🐉 Dungeons & Dragons RAG Exploration 🎲

A free (no API key needed) MCP server providing web search capabilities through SearXNG, optimized for LLM agents.

Agent Skills

A personal‑AI workspace that puts privacy first.

Agex & NiceGui

Spec, plan, and build with AI agents — with enforced guarantees.

Personal desktop assistant with real-time chat, agnostic support for multiple LLM providers (local and free-tiers included), a full agentic team and local automation with permissions. You can customize it as you wish.

Simple Node.JS based AI agent

Deterministic regression testing for AI agents

Webknot is an intelligent prompt generator designed specifically for AI-powered development tools like. It guides you through a comprehensive wizard to capture every aspect of your website vision and generates professional, detailed prompts that AI tools can understand perfectly.

A 💅 stylish 💅 local multi-model AI assistant and API.

🤖 A full-stack AI chatbot built with React, Tailwind CSS, JavaScript, HTML, and Python featuring intelligent API integration, real-time messaging, and a sleek, responsive interface.

DoubleXTouch is a lightweight AI-powered desktop PDF assistant for students and small offices. It focuses on fast PDF organization, smart summaries, and essential editing—without the bloat of traditional PDF editors.

Local LLM chat inerface for OpenCloud with on-premise AI, full data sovereignty and enterprise-grade security.

Lightweight journal/memory plugin for Claude Code with zero ML dependencies. Features slash commands, proactive skills, and auto-capture hooks.

🧠 AI Personal Assistant System built with Claude Code - Complete documentation of the MAGI System architecture and Iris development methodology

A MCP server that integrates the eBird API to connect with an AI agent.

RAG legal Q&A assistant in C# using QDrant, Ollama, and KernelMemory for fast, local, context-aware retrieval and chat.

The goal of this projest is to present 3 different approaches for text classification (trained ML model, zer-shot transformer, RAG).

MindOps is the layer where AI meets awareness, where observability data becomes self-interpreting, and where signals evolve into neural decisions. It is the operating system for understanding — not just monitoring — modern infrastructure.

TalentScout is an AI-powered hiring assistant provide intelligent recruiting and candidate evaluation support. The system features configurable AI personas, adjustable conversation memory, and a user-friendly interface designed to streamline the hiring process through natural language interactions.

In this workshop you will learn more about Prompt Engineering, AI principles and how to utilize SAP AI Launchpad to execute Document Grounding and configure the orchestration service to execute on a typical RAG flow.

The missing developer tool for working with vector databases. A comprehensive desktop app for visualizing, querying, and managing vector data.

A knowledge aggregator for computational biology

The repo underpins a codelab, demonstrating how to use Gemini File Search to enable RAG in your Agentic Application. Use the Gemini File Search to ingest and index documents without having to worry about the details of chunking, embedding or vector database.

Enterprise semantic search system for GitHub repositories powered by Go.

Enhance your RAG with Contextual Retrieval

Cross-platform desktop app to select and copy multiple file contents (without boilerplate) — built with Flutter & Cursor. Perfect for LLM prompts.

Turn any Java, Kotlin or Python project into an AI-ready context file in one command.

End-to-end LangChain JS learning repo with real examples: prompts, tools, RAG, agents, and LangGraph workflows.

102 AI Agent Skills for the full product lifecycle. Compatible with Trae / Claude Code. 9 modules from discovery to launch to growth. | 102 个覆盖产品全生命周期的 AI Agent Skills，兼容 Trae / Claude Code，9 大模块从探索发现到上线增长。

An AI technical biographer that transforms your GitHub footprint into a professional Persona Audit PDF. Features agentic repository deconstruction and a savage roast mode.

Benchmark-driven model routing for OpenClaw with data-driven policy tuning. Inspired by karpathy/autoresearch.

Claude Code session capture and analysis. Trace tool calls, detect backtracks, analyze decisions, track edit chains, and measure plan drift. Local-first, zero-dependency observability.

Turn AI into anyone — data-driven persona generation from real social media. 说一个名字，AI 就能变成 TA。自动采集真实数据，生成比手写人设真实100倍的角色。

⚔️ Disciplined orchestration plugin for OpenCode — automatic 4-tier pipeline, ClarityGate, dual review, runtime fallback

AI × Web3 School bootcamp track — pre-study notes (42/42) · daily logs · hackathon MVP · agent-driven workflow with Claude Code / Kiro skills.

🐧 is currently a work in progress... Stay tuned!

AI research-to-manuscript workflow for academic writing: literature search, source verification, research wiki, argument trees, outlines, drafts, reviews, citations, DOCX export, and thesis-destroyer workflow automation.

AI run the shop. Humans set direction, agents execute.

Shared system prompts, tool definitions, and API provider management for macOS AI agents

ov — Agent-first CLI for Obsidian vaults. JSON-only output, schema introspection, --dry-run safety. Built for AI agents.

MCP-first browser primitives for AI agents — real eyes and hands on the web. Local-first. Vendor-agnostic.

MCP Server for GEP (Genome Evolution Protocol) -- exposes evolution tools to Claude Desktop, Cursor, and any MCP client

76 AI-agent security skills for Kali Linux tools — pentest, red team, forensics, OSINT, and more. Machine-readable skill definitions by Red Hound InfoSec.

Autonomous AI coding agent — local-first, any language, any LLM. 24/7 daemon with task queue, heartbeat monitoring, cron scheduling, multi-agent roles, and web dashboard.

Structured, phase-gated architecture design powered by Claude Code. Enforces decision gates, challenges assumptions, and produces documented architecture decisions.

🚨 Autonomous AI SRE agent that investigates Docker incidents while you sleep. No more 3am log diving. Self-hosted, security-first, open source.

Get personalized advice from 5 product management experts by analyzing Lenny's Podcast transcripts

APIMesh — 23 pay-per-call web analysis APIs + 16-tool MCP server with autonomous API generation. Security audits, SEO, tech stack detection. x402 + Stripe MPP payments.

Flask-based web client for Letta AI agent framework with chat interface and agent management

43 production-ready skills for AI coding agents. Works with Claude, GitHub Copilot, Cursor, Windsurf, and Zed.

A Python MCP Server that converts ComfyUI workflows into parameter-configurable tools for AI agents. | 将 ComfyUI 工作流转化为参数可配置的 MCP 工具，供 AI 代理通过自然语言驱动图像与视频生成。

CatClaw - Privacy-first local AI agent desktop app. Chat, automate, and manage AI channels (WeChat, Feishu, Telegram, DingTalk) without cloud dependency. Powered by OpenClaw.

Full Stack AI Powered Blog App using MERN Stack, Google Gemini and ImageKit API

A general-purpose AI assistant

Multi-agent AI system with sandbox isolation, role-based execution, and configurable resource controls

A complete offensive security workflow for AI coding agents. Penetration testing, security assessment, and secure code review skills for webapp, API, infrastructure, and Android targets.

Open protocol, SDKs, and documentation for HMG — Agent Memory That Actually Works

Proof-backed AI agent for checking suspicious job posts, recruiter messages, and apply links, now live with case study and pilot intake.

Thousands of templates to get you started. Simplify your automation tasks with ready-made solutions tailored to your needs. Find workflows for Telegram, Discord, Gmail, AI, and hundreds of other integrations. Build your first workflow,

Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.

Everything-as-Plugin framework for AI multi-agent simulation. Change the config, run a completely different world.

Community-driven repository of reusable OpenClaw agents and sub-agents with validation workflows, fixtures, and tests.

Canonical BEAM SDK for agentic coding runtimes in Erlang and Elixir. One unified API over Claude Code, Codex, Gemini, OpenCode, and Copilot, with shared sessions, threads, MCP, hooks, telemetry, and backend-native escape hatches.

Memory infrastructure for AI agents!! store, recall by meaning or association, ingest documents, and track beliefs in one Python library.

Build Rust CLIs that AI agents can discover, call, and learn from. No MCP server needed.

Multiple AI agents working together in simple, collaborative chat workspace by Typescript.

LaraClaw is a Laravel-based multi-agent AI orchestration framework, loosely modelled after OpenClaw.

Context governance kernel for LLM agents. Predicts entropy, blocks hallucinations. Pairs with opencode-dcp. llm, llm-agents, opencode, opencode-plugin, context-governance, anti-hallucination, claude-code, cursor, typescript.

Do MCP tools serialize in Claude Code? Empirical study: readOnlyHint controls parallelism, IPC overhead is ~5ms/call. Reproduces #14353.

Autonomous multi-agent system that runs businesses end-to-end. Evaluate ideas, staff custom AI teams, bootstrap ventures, operate 24/7 — all from markdown files.

Local acceptance gate for coding agents: blocks false-green done until task-scoped proof is rechecked.

Real-time visualizer for Claude Code multi-agent activity. Timeline, task graph, and agent views powered by hooks.

awesome list of multi-agent security resources