Custom agents

Model Context Protocol (MCP) with Gemini 2.5 Pro. Convert conversational queries into flight searches using Gemini's function calling capabilities and MCP's flight search tools

A framework based on the Scheduler-Agent-Supervisor pattern

Basic setup with random user agents and IP addresses for Python Scrapy Framework.

The Python library with command line tools to interact with Dynabench(https://dynabench.org/), such as uploading models.

Lightweight, Rust-native AI Agent platform. Security sandbox from day one.

Add Siri like Native AI Agents in you App.

CodeSpirit is a revolutionary full-stack low-code + AI development framework that achieves backend-driven full-stack development paradigm through intelligent code generation engine and deep AI collaboration.

Cloud-native, durable state for AI agents: WAL+snapshots, watch streams, idempotency, leases, TLS/mTLS, capability tokens, Python/TS SDKs, Helm.

Python implementation of "Flocking for multi-agent dynamic systems: Algorithms and theory" by Olfati-Saber for multi-agent triangular formation.

카카오톡 대화 데이터셋

🤖 💬 A module-based, multi-channel chatbot framework (aka ebenos)

🤖 AI Dialer ☎️ – Autonomous Voice Agent for Appointment Scheduling 🗓️

Async-first meta framework for building enterprise-grade multi-agent systems.

A look-ahead multi-entity Transformer for modeling coordinated agents.

Quick setup for projects or repositories using Claude Code with built-in agents, ticket system, and planning tools.

A toolkit for painting agent-based mesoscale molecular simulations and illustrations.

OmniDaemon is a Universal Event-Driven Runtime for AI Agents, it's framework-agnostic, event-driven runtime that turns AI agents into production-grade, autonomous infrastructure services. It enables agents to listen, react, and collaborate across distributed systems—bringing true event-driven intelligence to modern enterprise environments.

AI Agent On-chain Living, Breathing Virtual World — where AI agents earn, trade, own property, and form social structures entirely on-chain.

Example Go external-data tool that connects Dify to Meilisearch for a movie-recommendation RAG demo.

[ICCV 2025] V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction

Official code release of AAAI 2024 paper SayCanPay.

Code for our NeurIPS'24 Dataset and Benchmark paper: Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation

Ralph Wiggum meet Kanban! Ralph style execution for [Claude Code, Codex, Pi, Cursor]. One task per iteration, automatic progress tracking, and git commits. Set it and let it run.

LLM-driven Linux operations assistant CLI with mandatory HITL safety, policy engine, runbooks, SSH guards, and audit trails.

Convert workflows into Agent Teams (Split Pane/Swarm) for Claude Code

Lightweight, local-first memory for AI agents. Hybrid vector + BM25 search, LLM-powered fact extraction, zero infrastructure — just pip install.

Browser based Interface for Generative AI. Chat/Agent/Taskmanager Hybrid.

ancient-chat-llm: A LLM which is proficient in Chinese culture 古语说： 一个精通中国文化的大模型

AI Coach Powered by Cole's Content (RAG AI Agent)

Haskell implementation of LangChain

Open-source, self-improving autonomous agent swarm🐇

A curated collection of influential surveys and papers on Retrieval-Augmented Generation (RAG), covering frameworks, evaluations, multi-modal extensions, and domain-specific applications.

MCAF is a framework for building software products together with AI coding agents.

Automated LLM Coding Tournaments. There can be only one (winning code solution from the competing AIs)

LLM-based autonomous world

CryptoAgent is a professional, enterprise-grade solution designed to fetch, analyze, and summarize real-time cryptocurrency data.

A vision-first browser agent with self-healing deterministic replay.

CLI for managing AI agent squads. Status, memory, goals, feedback, and dashboard for your autonomous agents.

Knox is a vigilant supervisor and management tool that ensures LLM teams rigorously develop reliable AI Agent programming extensions for VSCode and compatible editors.

Code and data for the paper: On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents

PARL (Parallel-Agent Reinforcement Learning) is a training paradigm that teaches models to decompose complex tasks into parallel subtasks and coordinate multiple agents simultaneously.

Standalone web app that visualizes Claude Code sessions as pixel art characters in a virtual office. Fork of pablodelucca/pixel-agents.

A comprehensive benchmarking framework for evaluating and optimizing CPU-centric agentic AI systems across multiple workloads, reproducing results from the research paper: "A CPU-Centric Perspective on Agentic AI"

[AAAI 2026 Oral] Automatic Multi-agent Communication Topology Design

Vibe Coding Framework - Full SaaS Development Team from A-Z with Brain, Self Improvement, Auto Development

Open-source metasearch backend, MCP server, and AI search API for LLM agents. Python FastAPI search gateway with Google search via SerpBase and Serper, multi-engine search aggregation, structured JSON output, provider fallback, deduplication, and SearXNG alternative architecture for agent workflows.

10 installable Claude Code skills that turn your terminal into a GTM command center. ICP building, signal scanning, lead scoring, outreach sequences, battlecards. Built by Earleads.

Self-hosted & federated platform for AI IDE/Tools Rules and Commands via WebUI & CLI - Generate, browse, store, share AGENTS.md, CLAUDE.md, and more

Agent-first Memory Bank skill pack for Codex CLI, Claude Code, and similar runtimes.

A minimal, composable AI agent harness framework in Python.

Multi-tier firewall for AI agents — blocks prompt injections, jailbreaks, and scope violations. Local tiers first; LLM judge only when uncertain.

Airtap skill for agents like codex, claude, openclaw

Zero trust gateway for MCP servers. Aggregate, filter, and securely access MCP tools from anywhere without VPNs, open ports, or exposed endpoints. Built on OpenZiti, zrok, and Agora with cryptographic identity, mTLS, per-client isolation, and tool-level permission control.

Secure sandbox to run claude agents

📺 Control any smart TV with natural language. Play Netflix by name from your terminal. PyPI: stv · MCP server · LG/Samsung/Roku/Android

The enterprise-enhanced version of OpenClaw. ByClaw serves as a secure, scalable AI Agent Operating System with multi-tenancy and compliance features, providing the trusted infrastructure for large-scale organizational AI adoption.

A Claude Code skill that builds a persistent context system (atlas) for any git repository — directory trees, entrypoints, architecture docs, and agent on-ramp for fast LLM onboarding.

Money Atlas Skill.md (Claude Skill) For AI Agent A Genesis Protocol-powered intelligence system for financial markets, macroeconomics, and geopolitics. Core Systems - Genesis Protocol (First Principle + System Thinking) - SMC Layer Engine (Quant price structure)

Hermes Agent中文站- 中文实战入口：上手路径、国内落地、OpenClaw 共存迁移、排障参考与可下载方案包。

🦞 AI 量化交易系统 — 37 因子选股 · 8 层风控 · 同花顺数据大屏 · 全自动盯盘

Production-style LangGraph reference implementation for reliable multi-agent workflows with typed state, review loops, human approval, checkpoint-ready execution, and structured artifact delivery.

One of the early China-built lightweight Claude Code-inspired terminal coding agents, with autonomous execution, tool calling, custom agents, task control, and evidence-gated memory.

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.

Create or audit AI agent skills. Synthesizes source material bottom-up into strategic, interactive skills. Works with Claude Code, Codex, OpenCode, and 35+ agents.

闲鱼 Agent 化购物助理。LLM 可直接调用工具完成搜索、订阅管理、收藏及任意复杂页面操作；支持关键词订阅轮询、上新降价检测、LLM 推荐排序与 WebUI 管理。本地或远程部署均可，远程模式下 AstrBot 宿主机无需 Playwright。

A curated list of code-execution sandboxing solutions for AI/LLM agents

Godot automation for AI agents to build and verify projects through a CLI, Agent Skill, or MCP server, with structured results, headless operations, and live runtime control.

Production-grade Agentic RAG system for arXiv paper curation

Открытый бенчмарк LLM: какая нейросеть лучше пишет код 1С:Предприятие (BSL). Объективная оценка LLM по методике SMOP с реальным исполнением в 1С — Claude, GPT, Gemini, DeepSeek, YandexGPT, GigaChat.

Open-source community study guide for all six Databricks certifications (Data Engineer Associate / Professional, Data Analyst Associate, ML Associate / Professional, GenAI Engineer Associate). Aligned to the 2025-2026 official exam guides. Obsidian-flavoured Markdown; PRs welcome.

基于 KouriChat 的 Dify 集成情感陪伴机器人，支持微信，增强 AI 交互。

Claude Code best practices applied to application design. Interactive HLD/LLD visualizations, a DB-governed implementation example, and the same primitives as a runnable agent: the Governed Agent. LLM-agnostic, DB-governed, GDPR-ready.

获取gpt-Codex-Agent-Identity 用shub2api反代无需手机接码

A reusable agent skills registry for Claude Code and Codex

贾维斯语音助手(JARVIS-Voice Assistant)，妈妈我再也不用羡慕钢铁侠了😭。

多智能体小说写作框架 | Multi-agent novel-writing framework — 每个角色都有自己的脑子,每一章都有质量门禁

A ready-to-use Obsidian vault for running an AI agent (Claude, Codex, etc.) as a personal OS: skills, grounding notes, and a self-improving feedback loop. Clone and open as a vault.

DeepSeek V4 特化思维链引导规范：we need to 句式，任意 agent 客户端可接入（纯提示词层）

Assessment-driven, local-first learning agent built on an observable Agent Runtime and eval harness—grounded ingestion, trace replay, HITL assessment, durable memory, and reviewable voice input.

论文到中国专利交底书的证据驱动多Agent生成、固定检查表审查与可追溯多轮改稿系统。

Silo — for developers juggling coding agents across many projects. Every workspace alive at once, switch instantly. 100% open source, free forever.

Microsoft AI Trainer 2026 LiveStream Slides & Presentation Deck Guide

Local document Q&A in your terminal — powered by on-device LLMs.

Learn DeepSeek Harness from scratch.

Production-ready prompt library for Claude coding agents. APEI methodology, ~35 specialist prompts, current Claude Code coverage, plus a /find-prompt skill that routes any task to the right prompt.

(Officially move to Lop Nur Twin) R.A.I.N. Lab is an experimental scientific-agent architecture that separates fast local judgment, independent probabilistic evaluation, multi-agent deliberation, evidence, and authorization into distinct computational layers.🐙(Predates Karpathy's AutoResearch)

这个项目最终形成了两个不同的知识系统，并用一个统一入口把它们连接起来： 1. 文档 RAG：处理制度、规范、说明和业务资料。 2. Code Wiki：处理项目源码、配置、符号、调用和架构事实。 3. Knowledge Agent：根据用户问题和当前权限，决定先查哪一类知识、是否换查询继续找、什么时候回答或拒答。 此外还完成了用户注册登录、工作空间、成员角色、邀请、离职数据交接、文档生命周期和代码项目管理。换句话说，它不只是一个“把 PDF 丢给大模型”的 Demo，而是一个有数据边界、有证据来源、有多步查询能力的内部知识工作台。

Evidence-driven autonomous SOC team on AgentTeams: hash-bound approvals, HMAC audit chain, rollback and reproducible attack scenarios — auditable governance primitives for agent infrastructure.

Autonomous Drosophila melanogaster (MaleCNS v1.0 / FlyWire) connectome agent playing Half-Life via biophysical LIF neural dynamics, 60x60 retina transduction, and DirectInput.

面向 AI 助手的数学建模竞赛技能：覆盖国赛 CUMCM / 研赛华为杯 / 美赛 MCM-ICM 的选题、建模、检验与论文写作自检

One GUI for native Claude Code, Codex, Cursor and more agents — manage them in one place, connect across devices. 一个 GUI，接入原生 Claude Code、Codex、Cursor 等 agent：一处管理，多端互联。

AI 桌面换装视频怎么做？把全网刷屏的「桌面动态壁纸换装」逐帧拆解，整理成一条可直接复制的提示词模板：一条提示词直出 30 秒成片，固定机位一镜到底，中文对白和字幕全部由模型生成，无需后期剪辑。适配即梦、豆包、Seedance 2.5 等 AI 视频工具，附火山方舟 API 脚本，并封装成 Cursor / Claude Code 可一键安装的 Agent Skill：说一句想法，它反过来采访你，自动写出精准提示词。

Codex CLI 版 pilotfish：GPT-5.6 分層（luna/terra/sol）的 multi-model orchestration，改編自 @Nanako0129/pilotfish / pilotfish for Codex CLI — multi-model orchestration with GPT-5.6 tiering

基于 C++23 与 Agent 架构的 OneBot 智能聊天机器人，支持群聊智能回复、跨会话消息共享、长期记忆、好感度、自定义工具扩展、MCP 及 Web 管理后台

Tu dis ce que tu veux, une équipe de vrais agents Claude Code se met au travail sous tes yeux, dans un bureau en pixel art. Gratuit et open source.

Microsoft AI LiveStream Series 2026: Ultimate PPT Resources for AI Trainers and Developers

Simple AI Chatbot Builder 2026: Create Smart Conversational Bots Fast

AdalFlow Alternative 2026: Auto-Optimize LLM Apps Without Code

A round dashboard for a 1st-gen Amazon Echo Spot: Kotlin shell on LineageOS plus a Windows tray agent. Clock, PC/GPU telemetry, ComfyUI, local voice, markets, weather art, Claude Code monitor.