Custom agents

Jandal AI — Local-first Android AI assistant with on-device LLM inference, semantic memory, and extensible skill framework

This framework provides the architecture, assets and samples for creating own virtual agents, also called non-player characters (NPCs), in Unity.

MCP server exposing financial data using Yahoo Finance via yahooquery. Provides stock insights, historical prices, earnings, recommendations, and ownership info. Built for Zentickr AI tools and compatible with research agents or financial copilots.

All your AI subscription limits in one Windows tray popover. Claude, Codex, Cursor, Copilot + 14 more. Free, open source, no telemetry.

Lightweight agent framework for research PowerPoint generation, editable PPTX delivery, and rendered QA

Web research for pi with smart and safe tooling + agent system

Give every agent session its own VM. One command up, zero burn when idle.

Based on Hermes Agent's `llm-wiki` skill and Andrej Karpathy's LLM Wiki pattern; extended with multimodal ingestion and provenance hardening.

企业级多智能体AI管理系统 | 企业级智慧管理解决方案 | 基于MCP架构的财务分析、成本预测、知识管理、效能评估一体化平台|- 多智能体系统 (Multi-agent System) - MCP协议 (Model Context Protocol) - - AI决策支持系统 - 企业级AI应用 - Python + FastAPI + Streamlit

一个基于FastAPI和React的智能体系统，支持多智能体管理、mcp管理、知识库、聊天对话等功能。An intelligent agent system based on FastAPI and React, supporting multi-agent management, mcp management, knowledge base, chat dialogue, and other functions.

A multi-skill agent suite that gives any AI tool senior ServiceNow architect, governance, delivery, and development knowledge.

AI proposal-writing & deal-closing engine for Claude Code. Research a prospect, price the engagement (3-tier + ROI), define scope, pre-handle objections & generate client-ready PDF proposals. 14 skills, 5 parallel agents. Auto-builds from your GEO/SEO/reputation audit reports.

API-based skills for AI coding agents — one contract that works with Claude, Codex, Cursor, OpenCode, Gemini, Windsurf and Pi, and any MCP host.

A self-improving retrospective skill for Claude Code. One command makes your AI agents get better after every conversation.

This is a single NeuroDynamic Brain that can be adaptable across the agents , just point your claude or any agent session to load it one time.

免登陆一键保存小红书笔记到本地的 Skill，适用于 Claude Code/Codex/OpenClaw 等 agent

Search and memory across your AI coding sessions — one index over Claude Code, Codex, and Pi. Fuzzy-find and resume from the CLI, give agents recall via MCP, and get usage reports.

VidXP (Video eXPlain) - Video Indexing Engine. Search in videos in natural language. 👀 Connect your Hermes / Claude / OpenClaw agents, allow them to understand videos with low token cost.

A compact high-signal benchmark for evaluating frontier agents

An OpenClaw-based agent framework designed for college students.

A personal VM cloud for macOS: Virtualization.framework VMs, Ollama vibecoding agent, Cloudflare Tunnel publishing — one Go binary

LitReview Skill is an installable agent skill for end-to-end literature review generation. It helps agents conduct literature reviews with a well-designed and widely used review framework so the search process is broad, iterative, and less likely to miss relevant articles.

Use your X Premium or SuperGrok subscription in pi.

Agent-native, open-code Vue 3 components with independent palettes, themes, and gradient backgrounds.

Research capability for coding agents: multi-source corroboration, active discovery, logical-space thinking, structured output. Browser-first evidence.

A universal memory and wiki knowledge layer for AI agents — structured enough for automation, readable enough for humans.

Persistent RAG memory layer for AI agents - store observations, retrieve context by semantic similarity, self-prune on TTL

Autonomous Solana trading agent with in-enclave key custody and attested execution.

Solana liquidation hunter that scores real edge after oracle drift, keeper competition, and unwind friction.

Red-Team - AI Agent to Phish Employees based on Social Intelligence.

Your own personal data engineer for OpenClaw.

AI-powered Knowledge Base UI Kit built on Memvid - the video-based memory format for AI.

Official code of Attention-MoA: Enhancing Mixture-of-Agents via Inter-Agent Semantic Attention and Deep Residual Synthesis

WeChat-LLM: Build a LLM that Mirrors Your Chat Style Using WeChat Conversations / 根据微信聊天记录定制私人聊天机器人

Telegram Bot that greets people, powered by Cyclic. ⚡️

A minimal browser automation agent using Google's Gemini 2.5 Computer Use Preview model and Playwright for web browser control.

Autonomous arbitrage scanner - monitors price spreads across 4 Solana DEXes, evaluates paths with Claude, executes in milliseconds.

Template library for browser-use CLI

An intelligent AI Calendar app that sits on top of your Google Calendar - helps you manage your schedule via conversational AI capabilities. Schedule, manage, and reorganize your events naturally through chat.

The governance layer for AI agents — monitor reasoning, audit tool calls, and secure the loop through OHTTP privacy routing.

Turn any AI agent into an agile developer. Persistent sprint context for Claude Code, Cursor, Copilot, Codex, Gemini, Aider, Windsurf. Zero dependencies.

A coding agent for the browser

Robot Memory - Persistent memory system for AI robots. MCP Server + hybrid search + spatial retrieval.

The system of record for AI. Models commoditize, trust doesn’t.

X Intelligence CLI — search, monitor, analyze, and engage on X/Twitter. Single Rust binary, 2.5MB, <5ms startup. AI agent skill.

API Documentation for the Agent Era

Mira

Secure SSH access for AI agents via MCP. Execute commands across your server fleet with policy enforcement, network controls, and comprehensive audit logging.

Forensic Observability for AI Agents

AI Agent实现的自动化的长视频切片工具；Automated long - video slicing tool implemented by AI Agent

The unified web layer for AI agents. Search (8 engines), stealth browse, auth, and act on 24 platforms. One npm install, self-hosted.

A visual, no-code interface for creating AI agents with Google ADK. Supports both cloud and local Ollama models with multi-tech stack integration.

LLM Engineering Claude Skills

DetectPack Forge turns plain-English behaviors or sample logs into production-ready detection packs — Sigma, KQL (Sentinel), SPL (Splunk) — plus tests and a response playbook, mapped to MITRE ATT&CK, fully powered by Gen AI.

Luann (fka TypeAgent) allows you to create many LLM based agent(Various types of agent,scale up)

DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents

Agents code for Multi-Agent Connected Autonomous Driving (MACAD) described in the paper presented in the Machine Learning for Autonomous Driving Workshop at NeurIPS 2019:

Implementation of the paper: "Aurora: A Foundation Model of the Atmosphere" in PyTorch

A Retrieval-Augmented Generation (RAG) system that leverages Google's Agent Development Kit (ADK) and Qdrant vector database via MCP server.

My set of skills and agent files.

Integrate the Agentic Commerce Protocol (ACP) into your servers

MCP server for HTML file preview and analysis - Has been weird with OS but good on Cline so WIP

A script for OBS that shows lagged/skipped/dropped frames and other data on your stream and/or in chat.

KOOK TypeScript SDK

This is all in one chatbot. When you start conversation it sees your face and identifies if it has previously talked to you(Not supported in latest versions). It also checks for your emotion in between conversation. This emotion data is then used to help you whenever it detects you are sad or angry. It can search anything you ask on the internet.

Chatbot Template using React, Vite, Tailwind CSS

Build Webex ChatBots in JavaScript

A GPT-2-class language model trained from scratch on OpenWebText with the intent to augment AI Transformer-model education and reverse engineer GPT models from scratch.

Node.js client for the Telegram messenger Bot API

AddChat Codeigniter is a Codeigniter chat application. Live chat widget that also includes multi-user chat, group permissions, customer support chat. Download now.

It’s my portfolio, reimagined as a chat conversation, answered by AI.

👨🏽‍⚖️ LegalEngine - qqmbr team - Junction2017

Wrapper around llama-cpp-python for chat completion with LLaMA v2 models.

probability & possibility

chatbot coded in videos part wise

bard-api-node is a Node.js library for interacting with Bard, an AI Chatbot developed by Google. Bard is based on Google's Large language model (LLM), LaMDA, which is designed to generate human-like text and images in response to prompts.

Starter bot using Botfuel Dialog

A Chat package for flutter

Contains interesting projects like Cat face detection, cat face recognition, code generation, Building chatbot, finding similar documents, image segmentation, UCI credit card, anomaly detection, MNIST etc.

A RiveScript chatbot written in Go that supports Slack and XMPP.

AI Based ChatBot built using Django (python back-end and html, css, js front-end)

Chatbot based Seq2Seq model with bidirectional rnn and attention mechanism with tensorflow, trained on Cornell Movie-Dialogs Corpus and deployed on a Flask Server

The Hugging Face API wrapper for Delphi leverages cutting-edge models to deliver powerful features, including object detection, music generation, text classification, sentiment analysis, image segmentation, speech-to-text transcription, and text generation.

Facebook Messenger chatbot boilerplate on node/express/mongodb/redis powered by wit.ai

A Windows 95-esque desktop experience with a chat app being the main highlight. Built with create-react-app.

A simple chatbot built using dialogflow and flutter

A framework for writing Nextcloud Talk chatbots with every language that supports gRPC.

NLP Cloud serves high performance pre-trained or custom models for NER, sentiment-analysis, classification, summarization, paraphrasing, intent classification, product description and ad generation, chatbot, grammar and spelling correction, keywords and keyphrases extraction, text generation, image generation, code generation, and much more...

A framework that allows anyone to create an Urbit Chatbot with only a few lines of code.

基于Nonebot2的QQ机器人不正经开源仓库

ChaiDocs AI powers ChatGenie, your go-to Chrome extension for instant access to programming docs and blogs from ChaiDocs website.

An implementation of ELIZA, Weizenbaum's classic chatbot.

AI: Search engine using RAG course examples

A sophisticated Retrieval-Augmented Generation (RAG) system that combines advanced document processing with intelligent retrieval mechanisms to deliver accurate, context-aware responses from multimodal data sources.

Code for Retrieval augmented text-to-SQL generation for epidemiological question answering using electronic health records