Custom agents

A Practitioner's Guide to M(eow)ti Turn Agentic ReinfOrcement learning

Python library for building durable and scalable multi-agent orchestrations.

An AI bot with RAG capability for Topics, Chat & Customer Support in Discourse, with first class support for the big 4.

Genius - A Modern Next.js 16 SaaS AI Platform.

The AI agent script CLI for Programmable Prompt Engine.

An introductory guide to LangGraph, showcasing step-by-step development from basic chains to fully functional AI agents with memory. This repository provides Python notebooks to help you understand and experiment with LangGraph’s core capabilities.

Turn GitHub repositories into LLM tools. (ACL 2025)

AI4U is a plugin that allows you use the Godot Game Engine to specify agents with reinforcement learning. Non-Player Characters (NPCs) of games can be designed using ready-made components.

AI web scraper built with Crawl4AI for extracting structured leads data from websites.

Hands‑on hackathon challenges to build intelligent multi‑agent financial compliance workflows using the Microsoft Agent Framework

XML sitemap parser designed to extract and process millions of URLs while bypassing most modern anti-bot protections. Supports plain and compressed XML, unlimited nested sitemaps, multi-threading, multiple inputs, CloudScraper integration, fingerprint randomization, proxy/user agent rotation, auto stealth mode, and detailed monitoring.

Airut is a system for running Claude Code tasks from email and Slack. It handles workspace provisioning, container isolation, network sandboxing, session persistence, and cleanup — a secure foundation for autonomous agentic development.

A vault-specific agent equipped with agentic capacity, fast search, flexible commands, vault management, and terminals to "jump" into other CLI agents, such as Claude, Gemini, etc.

Evaluation kit for testing stateful agents

玄霖超脑 · 无量网络 v4 重构版— 66 模块6通道 AI 认知神经系统 · 装一次，你所有的 AI 工具从此共享一个永远不失忆的大脑。跨会话记忆 · 多 Agent 互通 · 自动代码审查 · 零配置

Give your AI agent persistent memory with markdown files. Starter kit from the video: My AI and I Share a Brain.

AI agent for trading on prediction markets (specifically, Omen on Gnosis and Polymarket on Polygon)

Autonomous driving traffic agent/scene simulation/generation

🦞 AI-powered job hunting agent — scrapes Boss直聘/LinkedIn, matches your profile, auto-applies. Built with OpenClaw.

🔥🔥🔥一个专用于手机操作的AI Agent。可独立运行，也可以作为扩展提供给其他Agent调用，拥有强大的工具调用能力，自带总结经验与学习，重复任务执行效率更高。

Git-backed long-term memory for AI coding agents

Skills for AI coding agents to integrate with the Jupiter ecosystem.

A MCP implementation of Frida that seeks to emulate Cheat Engine functionally to allow for seamless Game Hacking by AI agents

🔥 Hello, I'm Kian.

🧠 A native graph-based memory system for autonomous AI agents, featuring bio-inspired sleep-based memory consolidation and powered by KIP & AndaDB.

Build AI-powered predictive maintenance orchestration with Microsoft Foundry, multi-agent workflows, and MCP

Go-based tool for managing Telkomsel accounts via Telegram Bot, Terminal CLI, or MCP Server (for AI agents).

An app that assists authors in writing novels / short stories by leveraging Large Language Models (LLMs).

AI-assisted toolkit for making HTML5 games with LittleJS: the engine, templates, and agent instructions that work with Claude Code, Codex, Cursor and Copilot, so the AI builds your game instead of rebuilding an engine. Installable as a Claude Code plugin.

🛠️ 米家自动化极客版 AI Agent (SKILL & MCP)- 用自然语言创建复杂自动化规则

[ICML 26] An evaluation framework assessing long-context retention and long-horizon memory performance for agentic applications (AMA-bench).

Busybox-style Beacon Object Files for *nix post-exploitation. Reimplements common Unix utilities as BOFs for use in stripped environments (Docker containers, Kubernetes pods, minimal VMs) where no binaries exist beyond the agent / implant.

A review-first desktop habitat for running AI coding agents in parallel.

Production-ready entrepreneurship skills for Claude Code — marketing, sales, operations, finance, and leadership. 24 skills built by a founder, for founders.

OMem (Office Memory) — local-first memory that automatically ingests your real work (mail, calendar, notes, files) from where it already lives, into a Markdown wiki any AI agent can query. macOS today; Windows coming.

Agentic RAG 驱动的深度研究 Agent — Agent 自主拆解问题、选择检索策略、评估质量、自我纠正，最终生成带引用溯源的结构化研究报告。

Evaluating the Search Agent in a Parallel World

A mobile agent developed for Android, iOS, and HarmonyOS, allowing it to connect to Codex and other software on your computer so you can perform remote development and code editing from your phone.

Agent Skill that silently refines prompts for the currently running model

Checkpoint/rewind extension for the Pi coding agent. 1 checkpoint per turn, /rewind command, diff preview, safe restore, redo stack.

Release-oriented agent skill hub and CLI for analyzing repos, installing high-signal Codex/Claude Code/OpenCode skill profiles, and safely tracking managed files.

Let AI agents see and control Unity Editor through plain files. 25 commands, lens system, screenshots, texture catalog.

Visualize Pydantic AI agent workflows from Logfire traces as an interactive HTML diagram — tools, nested sub-agents, tokens and exact cost.

Agentic Kernel Optimization — advanced & eXtensible: a closed-loop, campaign-based multi-agent system for optimizing GPU kernels (benchmark-swappable; default flashinfer-bench).

Zero-dep agent workflows with structured approval gates and adversarial review.

NSE BSE Indian Stock Market Data MCP server — search, screen & analyze all 8,200+ NSE/BSE stocks with 52 tools: live quotes, financials, technicals, 326-ratio screener, FII/DII flows, options IV, IPOs & portfolio tracking. Works with Claude, ChatGPT, Cursor & any MCP client

OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames on LVBench.

AI 驱动的多领域安全分析 Agent 平台 —— 让 LLM 端到端完成安全分析

Claude Code와 Codex CLI를 위한 올인원 에이전트 앱

An Agent Client Protocol (ACP) server for Google Antigravity's `agy` CLI, built on Bun. Connects ACP-compatible editors to drive `agy` with live streaming and history replay.

Search global patents across WIPO, EPO, USPTO, CNIPA, JPO, KIPO and other authorities, together with scientific literature from PubMed, arXiv, Nature, Science and other major sources using natural-language, semantic, keyword and structured search.

Unified TypeScript runtime for Codex CLI, Claude Code, and OpenCode with typed events, lifecycle control, permissions, and task graphs.

The standard library for agent-built SaaS

A living atlas of AI companies, products, founders, investors, traffic signals, and research notes.

Local cognitive memory runtime for AI agents — durable recall, temporal versioning, provenance, contradiction governance, and portable encrypted storage. Pure Rust, offline-first, with no required LLM or cloud. Patent pending.

OpenClaw AI agent skill for automated TikTok and Instagram carousel growth. Pass any website URL to analyze brand, competitors, colors, value proposition. Generates 6 visually coherent slides and auto-publishes with trending music via upload-post API. Built-in analytics and learning loop. Free tier, no credit card. Larry alternative.

Know what to fix next — local .pm governance skill pack for AI coding agents (Spec Kit–inspired).

A hypervisor and sandbox cloud for self-hosting AI agents and RL

Tamper-evident audit trails for AI agents: hash-chained Runtime Records, dependency-free, verifiable by anyone.

Context7 documentation lookup skill for AI coding agents. Lightweight REST API wrapper with no MCP context overhead.

去除中文文本中 AI 写作痕迹的 Agent Skill（基于 blader/humanizer 与 op7418/humanizer-zh）

The open-source agent platform to build, distribute, and optimize AI agents — on infrastructure you own.

轻笺 - 免费的书签、笔记与云文件管理平台，内置 AI 助手，支持跨设备同步｜Free bookmark, note and cloud file manager.

Tackle is the runtime layer that lets AI agents operate inside your Laravel application — reading code, executing tools, running tests, and taking action, with safety boundaries enforced at the framework level.

MCP-based discovery and judgment layer for Korea’s open data portal—helping AI agents find, compare, and assess datasets with explicit evidence, JSON-LD/DCAT metadata, and versioned deterministic rules.

Slides Skill：让 AI Agent 生成可编辑 PPTD + PPTX，并附带本地浏览器编辑器 Slides skill for AI agents — generate editable PPTD + PPTX with a local browser editor

Testing and observability for multi-agent delegation, MCP tools, permissions, sandboxed actions, prompts, and workflow replay.

Run the pi coding agent as a service — triggered on demand, on a cron schedule, or by a GitHub or GitLab issue, comment or pull/merge request — in a container you control, with a durable queue, a spend cap, and a live admin panel.

Autonomous CrewAgents Optimization Tool implementing Autonomous Dynamic Resource Allocation with enterprise-grade Auto-Scaling capabilities

Persistent memory and continuity for long-running AI agents.

Hosted MCP server and 12 marketing skills for Claude and Codex. Give your agent live web analytics, A/B tests, funnels, heatmaps and paid-ads attribution resolved to Stripe revenue.

Workshop for IT/Ops teams to learn how to manage AI agents on Microsoft Azure.

🔥 DeepSeek Harness 插件中文导航：热门项目、适用人群、安装命令、贴心 Tips 与避坑指南

对话即创作 · AI Agent 驱动的小说写作工作台 ｜ Chat to create — an AI-agent-driven novel-writing workbench

Open-source Agentic workflows built using Rust

Continue unfinished work across coding agents with portable handoff bundles.

Local semantic code intelligence, project memory, and workflow context for AI coding agents.

Go全栈开发工程师的AI随笔

AI-powered paper review assistant.

This repository contains the code for the paper "EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval"

Local-first Proton Mail MCP server and CLI via Proton Bridge. Search, draft, send and organize mail from Claude Desktop, Claude Code or any MCP client. 96 tools, read-only and send-to-self modes.

Local-first MCP coordination hub for multi-agent teams, with durable messaging, handoffs, governance, and observability.

mo-code 是 mortis 从零实现 Claude Code 核心功能的实验项目，目标是实现一个可运行、可解释，并重点研究安全边界的终端 Coding Agent。

A research workspace where an agent works beside you: chat, PDFs, notebooks and files in one dock, plus custom panes the agent builds on request.

Sub-millisecond query routing & cost-aware execution for GraphRAG architectures. Adaptive-AtomRAG is a highly optimized conditional routing gateway designed to resolve the latency and cost bottlenecks of heavy Atom-Entity Graph (AEG) RAG systems.

Xiaoman (小满) — a conversation-first, local-first personal finance AI agent · FastAPI + LangGraph + React · data 100% local · MIT

Better Agentic Development Environment

The trust layer for your AI agent on any platform. Trace and evaluate your agent. Full Observability. Run Model portability analysis. Autotune your agent.

An Agent Skill for Android phone control via ADB: observe, act, and verify. For Pi, Codex, Claude Code, and OpenCode.

SakugaCut 是一个 LLM Agent 驱动的短视频自动剪辑系统：上传用户素材和可选的参考视频，系统学习参考视频的叙事结构、段落功能与包装节奏，再只使用用户素材生成成片。

面向中国专利实务的 AI Agent Skill，将技术想法、文档和代码转化为专业技术交底书，支持自适应信息采集、专利语言规范化、附图生成与 Word 导出。

An open source prototype sandbox for designers and product managers who build.

让你的Deepseek harness成为一个统一的agent入口，轻松接入codebuddy、claude code、opencode、qoder | Make your Deepseek harness a unified agent gateway for easy integration with CodeBuddy, Claude Code, OpenCode, Qoder, and more.

This repository contains a comprehensive set of development rules, standards, and AI agent configurations designed to work seamlessly with multiple AI coding copilots. The setup is portable and can be imported into any project to provide consistent, high-quality AI-assisted development.

Structured SOUL evolution framework for AI agents — experience, reflection, governed identity updates, and visual timelines.

The Self-Evolving Agent Ecosystem — Trading agents that evolve through Darwinian selection and adversarial self-play

Cross-platform compatibility layer for AI agent skills — pre-flight dependency checks, MCP-native, works with Claude Code, Cursor, Codex CLI, OpenCode and more

AI writing studio for large-scale content.

基于人工智能标记语言 (AIML)和开放域问答(WebQA)的深度智能对话模型