Custom agents

memX: self-learning, self-maintaining memory plugin for AI agents; native support for claude code, codex, and openclaw

AI编程工具中文提示词合集，包含Cursor、Antigravity、VSCode Agent等多种AI编程工具的提示词，为中文开发者提供AI辅助编程参考资源。持续更新中文编程Rules和最新AI编程提示词。

Enterprise App Store and Google Play rejection compliance playbook: rejection maps, mistake taxonomy, 2026 enforcement and legal layer, a tested pre-submission guard, and an agent audit skill.

Give a coding agent a brief, not a chat, and it works on its own across sessions. Includes an example run: an open-world city built in a real game engine with no human help. In early development.

Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your strongest model for the hard parts.

Pytorch seq2seq chatbot

Self-hosted bridge that lets you interact with AI coding agents (Claude Code, Codex, etc.) from messaging platforms (Telegram, Discord, etc.) via the Agent Client Protocol (ACP).

The Official Repo for "Quick Start Guide to Large Language Models"

Bridge to Windows OpenSSH agent from Pageant. This means the openssh agent has the keys and this proxies pageant requests to it.

Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.

~3M live jobs from 36 ATS, enriched with LLM-extracted fields + embeddings, released CC0. Includes agent tooling to search them (hull -> learn -> rank).

MAX API Next 社区是由来自科研机构和高校的 AGI 爱好者组织发起、维护和运营的研究驱动型技术社区，聚焦 AI Models 与 Agents 治理方向，致力于建设面向 AGI 应用时代的开放基础设施。社区关注多模型与多平台接入、国产模型持续适配、AgentOps 工程实践、成本审计、权限与安全边界、私有化部署和长期运营优化，目标是把模型服务、Agent 应用、用户组织和上游平台之间的共性治理问题沉淀为稳定、可复用、可持续演进的工程能力。

REST framework for Delphi: JAX-RS style resources and routes, servers and clients, JWT, OpenAPI 3, FireDAC and Devart UniDAC/MyDAC/IBDAC, SSE, MCP servers for AI agents. Windows, Linux, Docker.

Official code repo for the O'Reilly Book - "An Illustrated Guide to AI Agents"

A simple agent framework that's capable of browser use + mcp + auto instrument + plan + deep research + more

Kubernetes operator for deploying and managing OpenClaw AI agent instances with production-grade security, observability, and lifecycle management.

A collection of agents that use Large Language Models (LLMs) to perform tasks common on our day to day jobs in cyber security.

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

The command center for AI agents such as Claude Code, Codex, and Gemini-Cli, making your agents ten times more efficient.

Diving into Reliable Self-Evolving Agents: A Survey

Spark-x2.5 open model series. Pushing the Limits of Agentic Capabilities in On-Device Models

AgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding.

Gort is a chatbot framework designed from the ground up for chatops.

Official repo for paper DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning.

3D rendered proc-gen world test. C++ homebrew voxel engine for agent-driven prodedural generation / world simulation

An AI research Agent for scientific innovation.

A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.

A curated collection of open source fintech libraries for payments, banking, and financial infrastructure.

A desktop pet for macOS & Windows that monitors your AI coding agents (Claude Code, Codex, Cursor, Gemini...) in real time, and grows as you code, feed it tokens, level it up, climb the leaderboard.

LiteReality-Agent: An Agentic System for Interactable 3D Indoor Scene Reconstruction

WeChat channel for DeepSeek Harness

Admin panels for humans and AI agents. Let agents search, update, and act on your data through built-in chat or MCP, with the same permissions as your team. Open-source and self-hosted.

Pocket Flow Project Template: Agentic Coding for Python

Production-tested templates for deploying multi-agent AI teams on OpenClaw with Telegram supergroup integration. 10 agent personalities, shared context workflows, bot-to-bot communication, and step-by-step AI-readable setup instructions. Built from a live 10-agent setup.

Master GitHub Copilot for C#/.NET development via this curriculum! Learn AI-driven paired programming, optimize your workflow, and write cleaner, faster code.

CAIPE: Community AI Platform Engineering

面向硬件产品PCB方案设计的AI Agent，Agent会自动帮你进行需求确认，实时分析国内外各类芯片技术方案，进行器件选型，下载datasheet，输出BOM表，计算价格，输出模块原理图，最终整合成可落地技术方案。

Native Android app for your Hermes Agent

Annotate terminal text, review documents and agent replies in Herdr, and send the feedback straight back to the agent.

EMERGE-Policy: A Robot Mind Emerges Beyond a Single Policy

Let your AI agents ask each other for help, over Tailscale. Wherever they run.

a13n - Build, run, and manage AI agents at scale on your own infrastructure. Open source, with a built-in harness, durable execution, multi-provider support, and a management console. Built With Love 💜 @converge-ai-labs

Netbox agent to run on your infrastructure's servers

One task, one agent, delivered. The open-source platform for task-driven autonomous AI agents.OpenCow assigns an autonomous AI agent to every task — features, campaigns, reports, audits — and delivers them in parallel. Full context. Full control. Every department. 🐄

Run AI agents on your Android phone — no terminal, no CLI, just a guided setup.

[ICLR 2025 Spotlight] The official implementation of our ICLR2025 paper "AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs".

MCP Toolkit for Flutter AI Agent Driven Development (MCP/CLI + custom client side tools) - via closed feedback loop (visual & semantic snapshot) and high client side customization adaptable for any Flutter app. Nowadays it is often called as agentic harness.

QVAC - Local AI SDK and libraries for building private, cross-platform, peer-to-peer AI applications. Run LLMs, speech-to-text, translation, and more locally on Linux, macOS, Windows, Android, and iOS.

Linux sandboxing that doesn't get in your way

Semantic code search and context engine for AI coding agents.

Open agent skills by VESTI: vesti-memory and vesti-handoff

Audit pháp lý website theo luật Việt Nam (BVDLCN 91/2025, TMĐT 122/2025, ANM 116/2025, AI 134/2025) cho Claude Code, Cursor, Copilot, Windsurf, Cline

[ICML2025] Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

Stream-Omni is a GPT-4o-like language-vision-speech chatbot that simultaneously supports interaction across various modality combinations.

LibreFang is an open-source agent operating system written in Rust. Live demo: https://flyio.librefang.ai

Open-source, desktop client/UI build to harness Claude Code, Codex and any other Agent accepting Agent Client Protocol. Run multiple AI coding agents side by side with rich tool visualization, MCP integrations, built-in terminal, git, browser and just about anything else you may need.

Multi-agent end-to-end application - General-purpose artificial intelligence agent for multimodal agent collaboration

Security testing toolkit for AI Agent: curated SecLists wordlists, injection payloads, and expert agents for authorized pentesting, CTFs, and bug bounties

Can AI agents resolve production incidents?

Run coding agents without babysitting them. Keep jobs focused, bounded, checked and accountable from start to finish. Finally run your agents swarms overnight and get your time back.

Desktop app for the pi coding agent: streaming timeline, Git review with hunk staging, session tree, native UI for pi extensions. Windows · macOS · Linux. pi 编程 Agent 桌面客户端

A Ghidra agentic reverse engineering skill.

All your machines, one app. For you and your AI agents: agent sessions, desktops, files, logs and GitHub across your Macs, Linux and Windows machines, with an MCP server.

Turn ChatGPT into a local agent runtime. Operate your computer, use local tools, discover MCP servers, and delegate work to your own models through one MCP connection.

该仓库主要记录 LLMs 算法工程师相关的顶会论文研读笔记（多模态、PEFT、小样本QA问答、RAG、LMMs可解释性、Agents、CoT）

Linux post-exploitation agent that uses io_uring to stealthily bypass EDR detection by avoiding traditional syscalls.

An agent skill for managing isolated execution environments

Tab(ter)minal, a Cloud-Native terminal and ACP agent workspace for desktop, tablet, and phone.

Generate a compact codebase index for AI assistants — saves 50K+ tokens per conversation

A Fork of Rikkahub with an overhauled UI and feature additions

Skills for Film and Television Creation Agents|31 个影视创作评估策划Agent Skills｜AI影视自动化工作流｜竖屏短剧长剧IP改编｜情节题材提炼｜剧本小说IP创作策划评估｜人物小传｜拉片人物剧集故事五元素分析｜大纲生成｜

Zenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.

deepseek标配coding agent、原生支持模型路由、CodeGraph代码图谱、OCR截图识别、自动上下文压缩、最佳工作模式选择，workflow等功能，从根本上节省Token

通达信A股行情协议 Python 库，MCP，支持快照、分时、逐笔、K 线、集合竞价等接口、量化数据接口，支持MCP给Agent用

DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.

Stop AI agents from doing things you didn't ask for.

A curated list of awesome Agent Skills for automating legal work

Salesforce's curated collection of agent skills for building applications. Optimized for Agentforce Vibes, compatible with all AI tools.

An opinionated AI-native workflow for evolving modern Java Enterprise SDLC practices through reusable Skills, Agents, and MCP servers.

Context management for long-context LLMs, agents, and vibe coding. Instantly build context for an entire repo, selected files, folders, and GitHub issues to generate structured AI-XML context with real-time token counting.

A recursive coding agent inpired by RLMs

App Store Connect from your terminal & Agents. A Swift CLI for managing your iOS and macOS apps on App Store Connect. Submit versions, manage screenshots, track builds — with full AI-agent support via CAEOAS affordances.

LLM-powered trading agents that turn plain natural language into a five-pillar strategy: Trend, Mean-Reversion, Momentum, Volume, and Risk. Each strategy is hosted, self-evolving, configurable through 30+ tunable parameters, and bit-exact between backtest and live execution. Built for simulated Hyperliquid perpetuals.

MARVIS-Agent: all-purpose credit risk agent for model development, validation, data processing, feature engineering, and strategy workflows.

🖥️ A local-first desktop workspace for private agents, local models, runtime visibility, and local/cloud routing.

Nova — YouTube growth agent for OpenClaw. Competitor scanning, channel analysis, idea generation, script writing, performance tracking, feedback loop. Self-installs in 5 minutes.

Autonomous agentic AI for CRA (Cyber Resilience Act) compliance: scans repos, triages findings, opens Jira tickets, and auto-fixes vulnerabilities via PR.

一套面向游戏 UI 设计的 Cursor Agent Skills 工作流，覆盖原型视觉生成、风格切换、页面延展与组件拆解，并通过 Spec-Kit 文档、视觉契约和资源清单保证多页面一致性与可交付性。

AI agent for end-to-end software development, from requirements to operations.

Open-source, self-hostable alternative to ChatGPT and NotebookLM — agents, skills, MCP, and cited knowledge in one AI workstation. Your models, your infrastructure. Free to use GPT 6: https://SourceWeft.com/

Open-source AI Employee Platform — Create AI employees that collaborate with your real team in WeCom, DingTalk, and Feishu, just like hiring a few more colleagues.

Super performant RAG pipelines for AI apps. Summarization, Retrieve/Rerank and Code Interpreters in one simple API.

Reliable Automation Agents at Scale

Reflexion: an autonomous agent with dynamic memory and self-reflection

AgentCoder: multi-agent code generation framework.

deep, reliable and confidential coding-context

一款提供Agent Skills安全扫描和可视化管理的桌面应用 | A desktop application that provides security scanning and visual management for Agent Skills.

Agent skills that make AI coding assistants write production-grade robotics software. ROS1, ROS2, design patterns, SOLID principles, and testing — for Claude Code, Cursor, Copilot, and any SKILL.md-compatible agent.

Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable specs and evidence in your repo. Works with Claude Code, Codex, Gemini, OpenCode, and plain CLI.

Transform any idea into a running AI-powered company