Custom agents

[ACL 2026 Main, SAC Highlight] FinSight: Towards Real-World Financial Deep Research. 🎯One ticker, one click, one publication-ready report.

A curated list of awesome resources for vibe coding

Skills for Claude Code — deep-research: systematic academic literature review

67 trading, DeFi, and quantitative finance Agent Skills. Works with Claude Code, Cursor, Codex, Gemini CLI, and 30+ other tools.

Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.

AI Agent Skills for Chinese Knowledge Workers: iMandalArt, FIRE, planning, and publishing workflows for Claude Code, Codex, and LLM agents.

一个Skill，主要目标是为后端和 AI Agent 求职者，从 GitHub 里筛出真正能写进简历、能经得起面试追问的项目，并基于源码证据生成简历项目包

（Spring Boot 3. X Microservices framework） 基于Spring Boot 3.X 的 Spring Cloud Alibaba / Spring Cloud Tencent + React的微服务框架。🔝 🔝 点个starrred 关注更新。Chat GPT(RAG、TTS、STT、LLM)

Using multi-agent Deep Q Learning with LSTM cells (DRQN) to train multiple users in cognitive radio to learn to share scarce resource (channels) equally without communication

An agentic research orchestrator for Go that is optimized to use free search & low-cost limited context window llms.

Awesome Devin-inspired AI agents

Persistent memory for browser automation AI Agents. Learns site knowledge automatically, updates after every visit, and gets better over time.

专为CTF设计的可扩展AI Agent，可自动解CTF题，也能与用户协作交互解题~

A Site Reliability Engineer AI agent that can monitor application and infrastructure logs, diagnose issues, and report on diagnostics.

See at a glance which tmux sessions have Claude/Codex working vs idle

2026 年编程导航 AI 编程实战新项目，基于 Vue 3 + FastAPI + yt-dlp + DeepSeek + Stripe 的 AI 万能视频下载总结器，支持 1800+ 平台视频下载、AI 视频总结摘要、思维导图生成、AI 问答、字幕导出、Stripe 国际支付。覆盖 SSE 流式传输、JWT 认证、SEO/GEO 优化。用一套教程掌握 AI 编程全流程，从需求分析到商业变现，不到一周学完，给你的简历增加竞争力

List of AI Hacking Agents

An open-source high performance execution engine for agentic workflows

Official Code Repository for the paper "Distilling LLM Agent into Small Models with Retrieval and Code Tools"

Hack AI/ML applications — CTF challenges for model attacks, LLMs and AI Agent exploitation.

AI App Bridge is a runtime bridge for AI agents to close the loop on mobile app iteration: inspect the running app, operate UI and WebView surfaces, collect structured runtime state, verify results, and continue improving the app.

A BLE-powered status light for Cursor Agent, using ESP32-C3 to visualize AI coding states such as thinking, busy, success, error, and waiting for user action. 基于 ESP32-C3 的 Cursor Agent BLE 状态灯，用红绿灯直观显示 AI 编程过程中的思考、忙碌、成功、错误以及等待用户操作 等状态。

这是一个专门接入Agnes免费模型API的skill，帮助新手排查和修复问题，也能直接在Agent工具中使用生图生视频，支持Claude code、Openclaw、Codex、Hermes等工具部署接入，所有信息基于最新的官方文档和说明。

Open-source operational advisor for ClickHouse — real-time monitoring plus AI-driven index/partition/materialized-view recommendations. Self-host or use the cloud.

Sento - Actor framework featuring actors and agents for easy access to state and asynchronous operations.

Agentic and LLM Programming in Scala

A curated list of Awesome-LLM-Ensemble papers for the survey "Harnessing Multiple Large Language Models: A Survey on LLM Ensemble"

Self-hosted search + markdown harvester for AI agents. SearXNG (100+ engines) + FastAPI + trafilatura. Tavily-compatible /search plus /extract with size presets and pagination. One-command Docker Compose.

One file. Your AI coding agent becomes a scientist. 30+ experiments while you sleep.

Skills, rules, and validation hooks that teach AI coding agents to generate correct UdonSharp code

Extract structured strategy specifications from quantitative finance research papers — Agent Skill for GitHub Copilot & Claude Code

Self-hosted AI roleplay chat platform you run on your PC or personal server, forked from Risuai

Open standard for software intent in the AI agent era.

:speech_balloon: Easy way to create conversation chats

Tactical AI Workspace Monitor & EDR

A chatbot implementation compatible with MCP (terminal / streamlit supported)

PyTorch implements multi-agent reinforcement learning algorithms, including QMIX, Independent PPO, Centralized PPO, Grid Wise Control, Grid Wise Control+PPO, Grid Wise Control+DDPG.

This is the website formally known as Terragon Labs. It was a remote background agent orchestrator for running Claude Code, Codex, and other coding clis in the cloud.

Organization-as-Code for autonomous AI agents. Brain-inspired memory that grows, consolidates, and forgets. Multi-model (Claude/Codex/Gemini/Cursor/Ollama).

Accelerate marketing content creation with an AI-powered multi-agent system using Microsoft Foundry.

AI 大模型应用/Agent工程师学习面试大全（Agent Dev Roadmap）

LLM-powered toolkit for skill analysis, AI interviews, resume scoring, and job structuring. Automates professional skill taxonomy and interview processes with adaptive difficulty.

Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments (ACL 2026)

Search & analytics data as infrastructure — MCP server for Google Search Console, Bing Webmaster Tools, and GA4, designed for AI agents and automation.

A repository to keep track of all the code that I end up writing for my blog posts.

A web UI Project In order to learn the large language model. This project includes features such as chat, quantization, fine-tuning, prompt engineering templates, and multimodality.

head/tail for structured data - summarize/preview JSON/YAML and source code

Official implementation of GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents

Enterprise Security Data Pipeline Platform (SDPP) — Real-Time Threat Detection + Deeply Integrated LLM Agents

A fast, native browser automation CLI built from the ground up for AI agents, powered by Chrome DevTools Protocol. 63 commands covering navigation, interaction, screenshots, accessibility, network mocking, visual diffing, test generation, and more — all from a single binary.

Agent-native investment research workspace for evidence-tracked, refreshable investment theses across equities, earnings, macro, and portfolio review.

understory — memory that grows. Self-wiring, plain-markdown memory for AI agents (MCP + local models + a living graph).

Companion app to control coding-agent harnesses from phone or desktop — OpenCode, PI, Oh My Pi (OMP) and Claude Code supported

An Elixir API for calling Node.js functions

A comprehensive suite of tools, built to liberate science by making the creation, evaluation, and dissemination of research more transparent, affordable, and efficient.

The Selenium for Chatbots - Bots Testing Bots

Generalist Software Agents to Solve Soware Engineering Tasks

A modern desktop application for exploring, managing, and analyzing vector databases

Install, manage, and share skills across every major coding agent — Claude Code, Cursor, Copilot, and more.

Open-source toolkit for the QVeris capability routing network: CLI, MCP server, Python SDK, skills, and REST API docs for agents to discover, inspect, call, and audit real-world tools.

All materials needed to follow along with the Spec-Driven Development with Coding Agents course, built in partnership with JetBrains

System audio capture + multi-provider ASR + local-first AI review workspace. Floating live captions, 12 ASR backends, 60+ languages, AI summary/chat/mindmap, Open API, MCP server, and Agent Skill.

Persistent Agent Workspace — AI agents that remember, collaborate, and never start from zero.

Age of Agents — watch your AI coding sessions grow a peaceful pixel-art realm. Run it with npx age-of-agents.

Documentation and Wiki for SEPIA. Please post your questions and bug-reports here in the issues section! Thank you :-)

The chatbot framework for your serious projects

ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations [COLM 2025]

Official repo for "LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs".

This is a WhatsApp AI bot that uses various AI models, including Deepseek, GPT, DALL-E, Gemini and StabilityAI, to generate responses to user input.

This is a multi-agent path planning(also known as Multi-Agent Path Finding, MAPF) algorithm package for ROS/ROS2.

Planning docs and PRDs for the Claude Code Agentic RAG Masterclass video series. Build a full-stack AI app with Python, React, and Supabase.

Official Implementation of MultiWorld: Scalable Multi-Agent Multi-View Video World Models

ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engineered designs for agentic system.

Kubernetes enhancements for Network Topology Aware Gang Scheduling & Autoscaling

Vibe-Blog is a multi-agent AI assistant that turns a single prompt into a 10,000-word technical article. It combines deep research, smart illustrations, Mermaid diagrams, code integration, and professional formatting to transform complex technologies into clear, engaging content, making daily long-form publishing effortless.

中文 Claude Desktop / Claude Code 桌面客户端：中文界面、本地 Code 工作区、GitHub 导入、权限守卫和 Artifact 预览。

AI-assisted trading desk for short-term technical analysis on stocks & ETFs via Robinhood MCP. Deterministic Python engines score each asset on a three-pillar framework (Trend · Momentum · Macro-Sentiment) using EMA, RSI, MACD, TRIX & Bollinger Bands. The AI fetches data; the scripts compute; the human approves every order.

The #Python framework for connecting AI agents to any onchain app on @solana-labs 🤖🐍

This project provides a FastAPI wrapper for interacting with Google Bard, a conversational AI by Google. It allows users to send messages to Google Bard and receive responses through a simple API.

🚀 ERA Connect by VYNECT™ — The evolution of secure WhatsApp automation ERA Connect is part of the VYNECT™ ecosystem, offering a premium solution for safe, ethical WhatsApp automation and testing using direct WebSocket communication. Automate conversations, simulate interactions, and manage messages with maximum speed, security, and stability

A month-long, open-source AI Agent Hackathon — open to all builders and dreamers working on agents, RAG, tool use, and multi-agent systems.

The visual communication layer between humans and AI agents. Capture, annotate, render diagrams, and organize with AI — powered by Electron and Ollama. macOS & Linux.

淘宝算法逆向，淘宝api，websockets自动运营，淘宝AI Agent基座

Documentation-first project planning agent skill. Generates specs, implementation plans, tasks, and single-shot prompts for coding agents. Compatible with Claude Code, Cursor, Codex, and 40+ agents via agentskills.io.

A self-hosted, secure, feature-rich memory system for AI agents and assistants. Provides intelligent fact extraction and deduplication, with an artifact store for detailed content.

Pre-build idea-to-spec workflow skills for Hermes Agent: turn rough ideas into design docs, implementation specs, and Superpowers-ready build handoffs.

Universal command-line tool for managing iOS and Android devices, simulators, emulators and apps

Open-source platform for multi-agent AI orchestration, real-world asset tokenization, and institutional-grade workflow automation. Includes OAuth 2.1 MCP agent management, a 44-field RWA schema, Stripe subscription billing, and a Cryptographic Airgap architecture designed to integrate with AetherNet QUAS post-quantum settlement.

👋 欢迎来到 ChatGLM 创意世界！你可以使用修订和续写的功能来生成创意内容！

🏭 AI agent platform with skills for protein engineering, the noob-friendly AI tutorial tool for life science professionals.

An extension suite that turns Pi into a multi-agent orchestration platform

Master AI inference, AI agent harness systems, and hardware engineering — then design a physical AI chip. That is the goal.

Local-first Memory OS for personal AI assistants with L0-L3 memory, Wiki++ knowledge, skill routing, and TokenLess context compression.

CLI sáng tác tiểu thuyết AI đa agent — Bản tiếng Việt của voocel/ainovel-cli

11 Claude skills for SEO: page audits, linkbuilding, article writing, E-E-A-T audits, semantic gap analysis, link building. Methodology from Koray Tuğberk, Kyle Roof, and Lily Ray, plus a generation-time anti-AI-slop ruleset. Production-tested at InhouseSEO

A Claude Code plugin that reverse-engineers clean behavioral specs, test vectors, and acceptance criteria from any codebase, producing a provenance trail so a fresh team can reimplement without inheriting the original's internal structure.

Agent-native mathematical modeling workflow skills for Trae, Claude Code, and Codex, covering problem parsing, modeling, code generation, evidence checks, paper writing, and Word delivery.

An open-source, extensible, self-hosted agent workspace with multi-runtime support for Codex, Claude Code, and more, plus reusable local apps for custom interfaces and services.

PTT 八卦版問答中文語料