Custom agents

A modern full-stack personal website and content management system built with Next.js and Hono, featuring a monorepo architecture powered by Turborepo.

Autonomous multi-market trading agent for Hyperliquid

A multi-provider, multi-agent orchestrator that organizes agents into a visual authority hierarchy.

⚛ MOSAIC is a visual-first platform that enables researchers to configure, run, and compare experiments results across RL, LLM, VLM, and human decision-makers to co-exist in a multi-agent environment.

🛠️ Hermes Agent 体验增强补丁与扩展插件 | Non-intrusive patches for Hermes Agent (Token metrics, CJK native tables, menu localization, DB guards)

deepseek harness 2D and 3D CAD plugin

Benchmark of report fidelity for browser agents: does the agent's final report tell the truth about what it actually did?

Alchemi is a full-stack AI agents for de-novo molecule design, retrosynthetic pathway planning, and molecular simulation, powered by a GATv2 graph neural network, RDKit cheminformatics, and optional LLM reasoning. A Next.js laboratory dashboard sits atop an Express + tRPC orchestration layer bridging a Python FastAPI

Drop-in toolbar for any website — annotate the UI and capture selectors, computed styles, React component trees, and screenshots as an agent-ready prompt.

A local CLI for logging predictions before the outcome and checking whether your "80% sure" comes true 80% of the time.

Karpathy's LLM Wiki pattern as a minimal, agent-agnostic skill

Typed, confidence-aware agent skill routing with TypeSafe Jev.

A stress-testing benchmark for partial-completion evaluators in stateful multi-turn agents, focusing on temporary progress, rollback, and attribution failures.

Execution posture harness for Claude Code. Your coding agent stops one step early; Castra is the step.

AI agent task board for Claude Code, Codex, Gemini CLI and Grok Build: plan, approve, build and review inside JetBrains or VS Code, with state in .moe/ in your repo

Arbos is a coding agent for one project. Talk to Main, watch workers, keep the work in one place.

Open-source Agent Skills for GEO — 6 skills to diagnose, fix, and monitor AI visibility for your website. Works with Claude Code, OpenCode, OpenClaw, Codex, Cursor.

AI-powered trading skills for Claude/Gemini agents. Backtesting, edge research, market analysis, strategy design, and more.

Framework-neutral DOCX engine with React/Vue editors, Nuxt integration, and agent tooling

Add an agent to your app in minutes

Multi-Agent Research & Valuation Engine for Long-short A股多Agent投研分析系统 9位AI分析师 → 质量门控 → 多空辩论 → 风控评估 → 最终决策

Retrieval + inference offload for AI coding agents.

Persistent cognitive infrastructure for AI systems. 28 MCP tools — semantic memory, emotional processing, identity continuity, and a subconscious daemon. Built on Cloudflare Workers.

Swap, lend, trade perps, add liquidity, move SOL, read the market. One binary your agent calls, across every venue.

A realtime assistant for Mac and Windows. Talk to it and it answers aloud, shows your schedule and mail as cards, and hands longer work to an agent.

A native Windows desktop client for OpenCode 2 (Rust + GPUI). GPL-3.0.

An AI agent plays Baldur's Gate 3 on Linux through a Lua mod and an MCP server, seeing only what a player sees. Includes a model benchmark and a playthrough app.

Let your AI agents call and text your actual phone (iPhone or Android) — Claude Code plugin + agent skill

DeepSeek Harness 多 CLI 智能体侧栏插件：独立对话、账号管理、角色预设与任务续聊

Agent专用虚拟屏 An independent Android screen for AI agents, with authenticated MCP, live PiP and user takeover.

⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. Fail-closed by construction. dsh 生态第一个 System-1 决策插件

Pi 一站式扩展：并行子代理、自动修复的多模型审查、清爽界面 · All-in-one Pi extension: parallel sub-agents, self-fixing multi-model review, a calm UI.

⚡ Terminal HUD, hard budget breakers & prompt-cache leak alerts for AI coding agents (Claude Code, Cursor, Codex)

Verified catalog of 300+ APIs and MCP servers with opinions and statistics so that AI agents can call after a one-time API key/OAuth setup. JSON, llms.txt and an MCP server for agents.

Always-on English review and improvement layer for any AI agent (Claude Code, Cursor, Windsurf, Copilot, Gemini CLI). Teaches better English without changing your intent.

Argolink-focused agent workflows and provider-neutral integration for GPT-6 Sol.

AI agent skills for converting HTML/CSS UI designs into native Delphi FireMonkey (FMX) interfaces. Supports Codex, GitHub Copilot, and other AI coding agents.

Indian market (NSE/BSE) adaptation of TauricResearch/TradingAgents: multi-agent analysis, a market scanner, and a web terminal over the original CLI. Research and education only, not financial advice.

多电商平台爬虫数据竞品分析(amazon,ebay,ozon,otto,temu等)基于 LLM 的电商竞品分析 Agent，支持 12 大平台自然语言驱动的竞品搜索、数据采集、AI 评论摘要、CSV 导出，并将结果持久化到 MySQL 数据库供历史趋势分析。

曾仕强 AI Agent Skill，基于曾仕强书籍，电视节目及公开演讲等材料构建的大模型知识库 Skill 资源库。完整收录中国式管理全集 23 册、易经、周易、道德经、论语、财神文化、大易管理、三国智慧、家风家庭教育等人情世故与国学管理文本，全部整理为标准化 Markdown，完成实体书名与电子版别名映射、书目勘误、缺本标记。可直接用于 RAG 检索、LLM 微调、AI 蒸馏、Agent 调用、Obsidian 知识库构建、本地大模型私有 Skill 调用。覆盖修己安人、持经达变、领导统御、人际奥秘、亲子教养、易经中道思维、企业管理等场景，内置心智模型、口语范式与幻觉约束机制，规避 AI 编造输出，为 AI 提供准确的曾仕强国学思想输出素材，适合国学 RAG、私有大模型、中文 Agent

Drive a real Telegram account from an MCP client: chats, messages, media, secret chats, communities, folders, admin rights, invite links and Mini Apps, with multi-account routing and an approval safeguard.

A real Debian Linux terminal and AI coding agents (Claude Code, Codex, Gemini CLI, OpenCode, Cursor, Pi) on Android tablets and phones. No root. Free and open source.

Five Claude Code plugins, Python stdlib + git. ar-board: judge agent proposals one by one on a local board; the agent keeps your reasons. publish-check: scan a repo's history for personal data before it goes public. tidy-board: delete stale branches, worktrees, and stashes only on approval. Plus doc, handoff, and TODO tools, and a status line.

29 free GEO/AI-search Agent Skills plus an installable CLI for audits, citability, AI crawlers, prompt packs, owner maps, Claude Code and Codex. MIT.

Agent skills, 15 original character cards and a calibrated AI-flavor detector for roleplay card authors. Skills run in Claude Code / Cursor / Codex / Gemini CLI; cards import into SillyTavern and Foreverse (Android).

Autonomous framework for long-running agents: a charter guides Claude Code, Codex or Pi through an actor, critic and scribe loop for hours.

A PPO-style Agentic RL framework without a separate critic model and multiple rollouts

CopilotJ: A Conversational Multi-agent System for Intelligent and Efficient Bioimage Analysis

Offline AI research assistant for Android. Answers from Wikipedia and other reference packs on the phone, with citations. Gemma 4 runs on the Pixel 10's Tensor NPU (first word in about 2 s); other phones use llama.cpp. No INTERNET permission.

A template for building apps with a small fleet of Hermes Agent profiles: one coordinator, six specialists, two human approval gates.

Agent-driven hardware-in-the-loop engineering method: Claude Code skill, swarm orchestration, generator-first KiCad PCB pipeline, CadQuery CAD, firmware-in-the-loop, web CAD/PCB viewer. Source-available (HIL-ASA-1.0).

OpenMolt lets you build programmatic AI agents in Node.js that think, plan, and act using tools, integrations, and memory — directly from your codebase.

A TypeScript service that bridges DingTalk / Feishu / Telegram messages to local AI CLIs (such as codex and claude).

Official Repo for Chat AI

Autonomous AI C2

This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DPO and KTO.

A visual history of the opportunities Brazilian developers miss. Three Claude Opus 4.7 agents read your work, crawl the world weekly, and write a personal 90-day plan with honest why-you reasoning. Open source, AGPL-3.0.

Chat component for Python Dash

📚 Build knowledge bases for RAG

A unified Model Context Protocol server for MiniMax CLI (mmx)

Connect to your favorite LLM model to use common language and request your favorite movies or tv shows that will be directly requested with Overseer

A Continual Multi-agent RL testbed based on Hanabi

[ICML 2021] DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning

Code for the paper "World of Bits: An Open-Domain Platform for Web-Based Agents"

Bing Ai Chat Copilot By Golang

Tana 是一只史莱姆桌宠，工作、学习搭子。

Codingbuddy orchestrates 29 specialized AI agents to deliver code quality comparable to a team of human experts through a PLAN → ACT → EVAL workflow.

MCP tools for Novyx governed actions, shared memory, audit, rollback, and evidence workflows.

🥋 Multi-agent research skill for Claude Code | 10 個 AI Agent 協作研究 | 10 AIエージェント協調リサーチ — AI Dojo series

Ontology-based MCP server that analyzes database schemas (PostgreSQL, Snowflake, ClickHouse, Dremio) and generates RDF/OWL ontologies with SQL mappings for fan-trap-free Text-to-SQL.

The first open-sourced personalized agent

Project-agnostic, composable AI workflow automation via pi packages and Claude Code plugins.

A modern multi-platform note-taking application built with Electron, featuring local data storage for complete security and control.

任性推是一个消息推送机器人，用来通知自己消息的免费服务，目前支持QQ、Telegram两个平台。通过调用API接口，实现机器人给你发送消息的功能。通俗易懂点就是有什么重要通知需要及时知道，可以让任性推第一时间给你发消息。

Twitch bot facilitating a variety of fun and useful commands

ChatGPT 交个AI虚拟朋友（CP）吧 👥

Bot that tracks the New Answers to Old Questions tool and reports the flag worthy answers.

https://youtu.be/7hQhPMPNY6A

A Ros Package for Human-centered Interactive Intelligent Humanoid Robots

Production-ready local deployment of Cheshire Cat AI that delivers enterprise-grade features

A really smart chatbot public for everyone.

A Concourse resource that can trigger and pass parameters to jobs using slack

A react chatbot built on GPT-3 that corrects your errors

🔊😊 A fastapi voice-assistant framework to quickly prototype LLM-powered voice assistants in <5 minutes.

A simple swift app for MacOS/iOS to test large language models (LLM)

a tiny, exploitable chatbot that can use tools

A WhatsApp Multidevice Bot Created By CH Haseeb.

Key value memory network implemented using keras

Network Analysis through LLMs for Knowledge Extraction

A "chat with your data" example: using a large language models (LLM) to interact with our own (local) data. Everything is local: the embedding model, the LLM, the vector database. This is an example of retrieval-augmented generation (RAG): we find relevant sections from our documents and pass it to the LLM as part of the prompt (see pics).

AI Demo 项目，一个专门为希望学习和探索人工智能（AI）技术的开发者准备的实战案例集合。

Smarter context for Claude Code — semantic rule injection that learns what you need

TheNZT is a powerful multi-agent finance query processing system designed to process and respond to finance-related queries efficiently. Leveraging advanced LLM multi-agent collaboration, it provides intelligent solutions for Finance, Company-specific, and Market-related queries.

LLM agent system for HCI research question co-creation, brainstorming and ideation

Personal autonomous agent powered by Gemini CLI. Orchestrates scheduling, persistent memory, MCP tools, and multi-channel messaging.

Builds Puppet Master and multiple Puppet Agent Nodes using JSON config file.

Joint Multipath++(2nd) for Sim Agent in waymo competition 2023 of CVPR workshop

An open source benchmark for Multi Agent Reinforcement Learning

simulation alignment negotiation governance arbitration multi-agent-systemsmulti-agent orchestration orchestrator mediation ai-safety human-in-the-loop audit-logs reproducibility prompt-injection

MAKGED is the first multi-agent framework for collaborative error detection in knowledge graphs.