Custom agents

The easiest way to use Claude Code with any LLM. Install the app, pick your provider, done.

Official code for paper "SPA-RL: Reinforcing LLM Agent via Stepwise Progress Attribution"

Context-Aware RAG library for Knowledge Graph ingestion and retrieval functions.

Ready made components for your AI agents

Task-Assignment Multi-Robot Warehouse (TA-RWARE): A multi-agent reinforcement learning warehouse environment for task-assignment optimisation

Research agents harness

MMORPG for humans and agents. In development. Powered by ElizaOS

[NeurIPS '25] GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents

【ACL 2026 Main】AgentMark: Utility-Preserving Behavioral Watermarking for Agents

CanvasAnvil is an AI multi-canvas creation platform for flowcharts, interior design, presentations, posters, infographics, and product storytelling.

AI voice assistant starter app for Flutter built with LiveKit

An opinionated C# Toolkit on top of Microsoft Agent Framework that makes life easier

Official Repo of Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents

AI-powered meme coin trading bot for Solana and Base that automatically scans new tokens, detects honeypots, calculates win probability, executes trades. Built in Go with a multi-agent architecture, real-time risk controls, and a web dashboard for monitoring. Designed for autonomous meme coin trading, Solana AI agents, high-frequency Web3 trading.

A collection of skills, agents, commands, and workflows for security researchers. Compatible with Claude Code, Claude Desktop, OpenCode, and other AI coding tools.

code intelligence on your CLI for AI agents. tell your agent to run `cm --help` and let it rip

就算有一套完全自动赚钱的工具，你也会经常盯着它。你跟专业交易员对比，差别在于是否看得懂。而EasyDeal 就是解决这个问题的一套框架，提供一组MCP工具，接入 openclaw、Claude Code, Fay等agent后，在MT5交易环境可以协同各种策略工作，监控策略的执行、为你解答各种问题、指导你做出突发处理，甚至直接帮你修改策略代码。

A .NET 10 port of graphify - AI knowledge graph builder for codebases using GitHub Copilot SDK and Microsoft.Extensions.AI

AI-powered mobile automation agent — describe what you want in plain English, AppClaw reads the screen, reasons, and acts. LLM-agnostic, open-source, zero telemetry.

Real-time gamified dashboard for monitoring Claude Code and Codex AI agents in a medieval fantasy setting

Go implementation of AI coding agent

Marketing skills for Claude Code — SEO audits and implementation, ad analysis, ad optimization. Free skills need no account. $9/mo for live Search Console, Bing & LinkedIn data.

Amplicode Agent Tools

'Personal AGI' that thinks on its own. Autonomous cognitive cycle, earned autonomy, 60+ tools. It decides what to do without being told.

Simple, flexible workflow orchestration for multi-agent AI apps, with YAML configuration, runtime safety, observability, and resume support.

闲鱼 CLI · 原生支持 MCP · 为 AI Agent 而生 | Goofish (Xianyu) automation CLI · MCP-ready · Built for AI Agents

The key that opens Opprime World — the first metaverse where AI agents are natives, not tools, not NPCs.

Dynamic evolution agent system with multi-session memory for realistic seeker simulation in psychological counseling.

Routing Architecture for AI Agents through Separation of concerns, applied to AI context windows instead of code modules.

A unified, 100% self-contained, open-source, and offline-first local AI agent workspace.

An AI writing skill that turns agent-generated drafts into clearer, warmer, more human documents by removing templated phrasing, markdown clutter, and generic AI tone.

An AI agent that collaborates with historians to extract structured datasets from primary sources, adapt to heterogeneous documents, and accumulate domain knowledge across sessions.

Code for Temporal Straightening for Latent Planning

公众号、抖音、小红书、知乎、快手等全平台媒体工作流。多渠道数据集成、灵感选题、文本创作/改写/重构、帐号跟踪、帐号分析、Agent 助手。

Context-isolated workflow automation for Pi coding agent

Native macOS app for Pi coding-agent. Browse, resume sessions, and run Pi terminal tabs locally or over SSH.

AI agent skill that remembers every technical decision & bug fix across sessions — and learns from them. v4.0, MIT. | 跨会话记忆的AI编程助手知识大脑

World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated

Lightweight file-based CLI API client with age-encrypted secrets, first-class GraphQL support and MCP server for agentic workflow.

Linked-Intent Development - a SDD methodology for agentic coding

Mac app to create context for agents: writing, reading, voice, terminal, bookmarks, and clipboard.

AI agent skills for Upwork freelancers, from a real Top Rated Plus playbook. Free, open, community-written. Not affiliated with Upwork.

A Codex Skill for coordinating focused custom subagents across development, research, analysis, documents, data, and content work.

Agent Markdown Language

Just Another Telegram Ai Chat Bot Written In Python With Pyrogram.

💡✨ Zotero, RAG, MCP, and deep research

{ "releases": { "2.0.4": [ "[Fixed] Refresh for Enterprise repositories did not handle API error querying branches - #7713", "[Fixed] Missing \"Discard all changes\" context menu in Changes header - #7696", "[Fixed] \"Select all\" keyboard shortcut not firing on Windows - #7759" ], "2.0.4-beta1": [ "[Fixed] Refresh for Enterprise repositories did not handle API error querying branches - #7713", "[Fixed] Missing \"Discard all changes\" context menu in Changes header - #7696", "[Fixed] \"Select all\" keyboard shortcut not firing on Windows - #7759" ], "2.0.4-beta0": [ "[Added] Extend crash reports with more information about application state for troubleshooting - #7693", "[Fixed] Crash when attempting to update pull requests with partially updated repository information - #7688", "[Fixed] Crash when loading repositories after signing in through the welcome flow - #7699" ], "2.0.3": [ "[Fixed] Crash when loading repositories after signing in through the welcome flow - #7699" ], "2.0.2": [ "[Added] Extend crash reports with more information about application state for troubleshooting - #7693" ], "2.0.1": [ "[Fixed] Crash when attempting to update pull requests with partially updated repository information - #7688" ], "2.0.0": [ "[New] You can now choose to bring your changes with you to a new branch or stash them on the current branch when switching branches - #6107", "[New] Rebase your current branch onto another branch using a guided flow - #5953", "[New] Repositories grouped by owner, and recent repositories listed at top - #6923 #7132", "[New] Suggested next steps now includes suggestion to create a pull request after publishing a branch - #7505", "[Added] .resx syntax highlighting - #7235. Thanks @say25!", "[Added] \"Exit\" menu item now has accelerator and access key - #6507. Thanks @AndreiMaga!",

Create custom DevOps AI agents that understand and manage your infrastructure.

🌟 Learn Large Language Model development through hands-on projects and real-world implementations

🤖 CLI for creating Claude Agent Skills with progressive disclosure validation. Built for Claude Code to use when humans ask it to create skills.

Create amazing Stable Diffusion prompts with minimal prompt knowledge. A vicuna based prompt engineering tool for stable diffusion

AI-WeChat-Mater 是一个开源项目，旨在将人工智能能力深度集成到微信生态系统中，提供自动化消息处理和智能交互功能。该项目支持多微信账号管理、智能AI对话、定时任务执行和全方位数据分析。

An open source chat bot architecture for voice/vision (and multimodal) assistants, local(CPU/GPU bound) and remote(I/O bound) to run.

카카오톡 ChatGPT AI 챗봇 빌더

Lightweight and declarative sandboxing for AI agents on Linux and macOS using Nix.

OpenKIWI (Knowledge Integration & Workflow Intelligence) is a secure, multi-channel agentic automation system.

OWASP Foundation web repository

The Best Agentic Marketing Swarm in the World

IntelliJ IDEA code coverage agent

File-First Agent Orchestration. Readable agents. Inspectable state. Predictable costs.

Agent skills for Heptabase CLI.

[ICLRW 2026 Best Short Paper Award] Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning

Simple robots.txt template. Keep unwanted robots out (disallow). White lists (allow) legitimate user-agents. Useful for all websites.

Find that one coding agent session you want to get back to!

Pytorch code for ICRA'21 paper: "Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation"

Canopy - the open-source agent workspace runtime

Ralph is a small runner around GitHub Copilot CLI (standalone) inspired by the“Ralph Wiggum” technique: run a coding agent from a clean slate, over and over, until a stop condition is met

A 股数据与量化 Skill，零配置开箱即用，完全免费。提供实时行情、历史 K 线、分钟线、技术指标与基础策略分析，内置多数据源自动切换；同时集成模拟舱 Skill，支持信号生成、模拟下单、持仓管理与交易结果反馈，适用于 Agent、策略研究与自动化交易系统

This open-source project & guide shows you exactly how to implement Canvas UX pattern + LangGraph human-in-the-loop workflows in your AI apps.

MyShelf is an experiment to create a GenAI utility to track reminders, memories, random adhoc information, shopping lists, and more.

Transformer模型训练的单轮对话聊天机器人

Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval

Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTTP API. Works with Cursor, Claude Code, Codex, and any MCP-compatible agent.

DecisionBox connects to your data warehouse, runs autonomous AI agents that write and execute SQL, and surfaces validated insights and actionable recommendations — without you asking a single question.

Multi-Agent Step Race Benchmark: Assessing LLM Collaboration and Deception Under Pressure. A multi-player “step-race” that challenges LLMs to engage in public conversation before secretly picking a move (1, 3, or 5 steps). Whenever two or more players choose the same number, all colliding players fail to advance.

rtfmbro provides always-up-to-date, version-specific package documentation as context for coding agents. An alternative to context7

Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers

基于Qwen2+SFT+DPO的医疗问答系统，项目中使用了自定义的 SFTTrainer/DPOTrainer/TRPOTrainer用于训练，其次，项目还调用各种知识库工具（neo4j, milvus, LDA, 等）进行自动化训练数据生成。另外，使用 vllm 用于推理和部署训好的模型, 该模型会通过 vllm API 来接入一个基于 embedder + Reranker 的 RAG 系统。另外还参考 MDAgents 论文实现了一个多智能体会诊系统，同样也支持 vllm api 接入。

Memory Agent monorepo

Minimalistic server (written in C) and a python3 client to allow calling native functions on a remote host for automation purposes

The AI Agent Kit for Solana Devs

MantouAI—— 让Obsidian变身智能助手

Security plugin for OpenClaw agents - prevents secret leaks, PII exposure, and destructive command execution

Sandboxed shell agent with access to LiteParse

The Unreal ML Agents Toolkit is an open-source project that enables Unreal Engine games and simulations to serve as environments for training intelligent agents using deep reinforcement learning. This project is a port of Unity ML-Agents, adapted to work within Unreal Engine.

[stays mad] 反PCL宣传库。Anti PCL propaganda. 大陆修宪香港恶法台湾武统朝鲜毁约美中冷战等都是王沪宁愚弄习思想极左命运共同体的大策划中共窃国这半个多世纪所犯下的滔天罪恶，前期是毛泽东策划的，中期6.4前后是邓小平策划的，黄牛数据分析后期是毛的极左追随者三朝罪恶元凶王沪宁策划的。王沪宁高小肆业因文革政治和情报需要保送“学院外语班“红色仕途翻身，所以王的本质是极左的。他是在上海底层弄堂长大的，因其本性也促成其瘪三下三滥个性，所以也都说他有易主“变色龙”哈巴狗“的天性。大陆像王沪宁这样学马列政治所谓"法学"专业的人，在除朝鲜古巴所有国家特别是在文明发达国家是无法找到专业对口工作必定失业，唯独在大陆却是重用的紧缺“人才”，6.4后中共信仰大危机更是最重用的救党“人才”。这也就是像王沪宁此类工农兵假“大学生”平步青云的原因，他们最熟悉毛泽东历次运动的宫庭内斗经验手段和残酷的阶级斗争等暴力恐怖的“政治学”。王沪宁能平步青云靠他这马毛伪“政治学”资本和头衔，不是什么真才实学，能干实事有点真才实学的或许在他手下的谋士及秘书班子中可以找到。王沪宁的“真才实学”只不过是一个只读四年小学的人，大半辈子在社会上磨炼特别是在中共官场滚打炼出的的手段和经验而已，他和习近平等保送的工农兵假“大学生”都一样，无法从事原“专业”都凭红资本而从政。六四学运期间各界一边倒支持学生，王沪宁一度去法国躲避和筹谋，他还加入了反学运签名，成为极少有的反学运者仕途突显，在六四和苏联垮台后中共意识形态危机，江泽民上台看上唯一能应急的王沪宁聚谋士泡制的"稳定统一领导"和之后的"新权威"谬论。左转被邓小平南巡阻止后，王策划顺邓经济改革却将政治改革逐步全面终止和倒退，泡制“三个代表”为极左转建立庞大牢固的红色既得利益集团。因此六四后各重大决策和危机难题都摆在中共中央政策研究室王沪宁桌面上，使王沪宁成了此后中共三朝都无法摆脱的幕后最有决策性实权的人，中共中央政策研究室是王为其野心巨资经营几十年，聚众谋士的间谍情报汇总研究的特务机关和策划制定决策重要机构与基地，王沪宁本人和决定其仕途关键的首任岳父及家属就有情报工作背景。中央政研室重要到王沪宁入常后为了死抓这中共情报与决策大权，宁可放弃国家副主席和中央党校校长。后再加个除习外唯他担任的中共几核心领导小组之一的“不忘初心牢记使命”主题教育工作小组组长。此后他把持的舆论必将以宣传“不忘初心牢记使命”为主，打造众所周知的所谓“习思想”其实是”王思想“。王自从主导中央政研室开始决策后，策划中止邓小平的与美妥协路线回归毛极左的反美路线。帮助前南斯拉夫提供情报打落美机放中使馆引发炸使馆事件，以此掀起六四后唯一的全国大规模游行并借此反美而起家。后又帮江泽民提供法轮功会是超过中共组织的情报，策划决策镇压迫害开始并没有把矛头指向江的法轮功群体，策划决定阻止党内外近三十年来平反六四的呼声。致远黑皮书马拉松程序员易支付英语台词文字匹配美团点评各业务线提供知识库团队共享阿里云高精Excel识别德讯 ·吉特胡布薄熙来黑科技习近平讲话模拟器习近平音源黑马程序员MySQL数据库玉米杂草数据集销售系统开发疫情期间网民情绪识别比赛996icu996 icu学习强国预测结果导出赖伟林刺杀小说家购物商场英语词汇量小程序联级选择器Bitcoin区块链 技术面试必备基础知识 Leetcode 计算机操作系统 计算机网络 系统设计 Java学习 面试指南 一份涵盖大部分 Java 程序员所需要掌握的核心知识 准备 Java 面试 首选 JavaGuide Python 1 天从新手到大师刷算法全靠套路 认准 labuladong 就够了 免费的计算机编程类中文书籍 欢迎投稿用动画的形式呈现解LeetCode题目的思路 互联网 Java 工程师进阶知识完全扫盲 涵盖高并发 分布式 高可用 微服务 海量数据处理等领域知识后端架构师技术图谱mall项目是一套电商系统 包括前台商城系统及后台管理系统 基于SpringBoot MyBatis实现 采用Docker容器化部署 前台商城系统包含首页门户 商品推荐 商品搜索 商品展示 购物车 订单流程 会员中心 客户服务 帮助中心等模块 后台管理系统包含商品管理 订单管理 会员管理 促销管理 运营管理 内容管理 统计报表 财务管理 权限管理 设置等模块 微信小程序开发资源汇总 最全中华古诗词数据库 唐宋两朝近一万四千古诗人 接近5 5万首唐诗加26万宋诗 两宋时期1564位词人 21 5 首词 uni app 是使用 Vue 语法开发小程序 H5 App的统一框架2 21年最新总结 阿里 腾讯 百度 美团 头条等技术面试题目 以及答案 专家出题人分析汇总 科学上网 自由上网 翻墙 软件 方法 一键翻墙浏览器 免

A Collection of High Quality research papers and open-source projects about LLM-agents

🚀 A framework for Context Engineering using Google Gemini. Move beyond simple prompting and learn to systematically provide context to your AI coding assistant for more reliable, consistent, and complex software development.

Use WeChat to route messages to Claude Code or Codex.

The Vibe Coding++™ platform - orchestrate multiple AI agents, experiment with isolated attempts, ship code you understand. Multi-agent kanban with MCP integration.

Panel-based personal assistant with a plugin architecture for productivity workflows. AI agents share a workspace of notes, lists and other panels with the user. Supports Claude Code, Codex, and pi CLI agents with text and voice interfaces. Extend with custom plugins or use built-in plugins exported as skills with CLIs.

Recursive Language Models for Claude Code — process arbitrarily long inputs via recursive sub-agent delegation

ClawMax is OpenClaw to the Max! 🚀 A web orchestration layer for OpenClaw agents, teams, workflows, and templates.

Official Implementation of Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution

Agent wallet infrastructure — encrypted keys, policy enforcement, credential proxy, auth platform. Self-hostable, multi-tenant, open source.

The Map Everyone's Missing: LLM Knowledge Engineering in 2026 — First unified guide connecting RAG, Context Engineering, Harness Engineering, Skill Systems, Agent Memory, MCP, and Progressive Disclosure

Automated Benchmarking of LLM Agents on Real-World Software Security Tasks [NeurIPS 2025]

Welcome to the central repository for the **Antigravity** ecosystem. This project houses a collection of AI Agents, Task Skills, and Coding Rules designed to enhance autonomous coding workflows.

专注于中国商品期货市场的AI分析系统