Framework
Custom agents
57,742 Custom AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
57,742 agents · ranked by popularity · refine in the directory →
Custom agents — page 131 of 578
Enterprise AI agent development platform — visual agent builder, on-demand knowledge/tool mounting, Playground validation, and one-click publish. Self-hostable.
dsh / pi-agent web ui
CLI for managing OpenSandbox lifecycle and AIO agent tools
衔枝 Twig · 叙事记忆引擎 — 面向长程 agent 的开源记忆基础设施：三层叙事记忆 + 情感层（日记/心迹/便签/印章）+ 记忆书前端
Build an AI Coding Agent from Scratch, Step by Step | 从零一步步搭建 AI 编程 Agent，边实现边理解 Agent 的工作原理
Local-first task and context manager for multi-agent AI development workflows.
An open-source multi-agent platform for GitLab MR code review, governance, and CI self-healing.
个人用的 agent memory OS——记忆系统 + self-drive 自主情感，内置对抗式自审 harness。内在过程需要外在标准。
仿超级简历模版——简历 Agent：支持多简历文件、模块化编辑、样式配置与实时 PDF 导出。
A power user focused interface for LLM base models.
The game engine built for AI. Includes MCP server, CLI and skills that let any agent build, test, publish, and grow full games with Summer Engine.
AI 辅助逆向工程工具清单，收录 MCP、Skill、插件、Agent 与工作站，覆盖 Web、二进制、移动端、浏览器自动化和流量分析。
Open-source, self-hosted alternative to Clay.com for lead sourcing, enrichment waterfalls, AI research, buying signals, and outbound automation.
终端优先的 Linux AI 运维工作台：SSH/SFTP、真实命令回显、分级审批与一步一卡教学。Windows 桌面预稳定版。A terminal-first AI workbench for Linux operations.
A linked-list discipline for knowledge, memory and pointer hygiene in large projects: five laws plus portable Python engines (declarative rule table, dry-run health check, link-integrity scan).
MCP management console for the official DeepSeek Harness MCP client: /mcp command with health diagnostics and pipeline trial calls, a Settings MCP tab with server CRUD (approval-gated writes, automatic backups) and a tool trial console over the official tool pipeline (Apache-2.0, dsh-plugin).
Matching decompilation of the Gran Turismo 4 (PS2) engine, AI-assisted. No game data included.
Self-hosted Google search scraper for Python. Scrape Google SERP results with a real Chrome browser and your own residential proxy. Self-hosted SERP API alternative with JSON output, an HTTP API and an MCP server for AI agents.
Island - Dynamic Island for Windows: a liquid pill at the top of the screen with live events, clipboard history, screenshots, a command bar, weather and AI. Free, with a one-time Pro upgrade.
企业私有 AI 知识工作台：中文搜索、飞书接入、Agent 与演示文稿
SoftSync for the agentic era
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
帮助agent做出终末地风格的ui
DSH IM Connect — 将主流即时通讯平台接入本机 DeepSeek Harness · Connect major messaging platforms to local DeepSeek Harness agents
Benchmark for allocating scarce user attention during long-horizon agent work
Agent-orca orchestrates and manages AI agent workloads in Kubernetes, providing distributed execution, model routing, knowledge integration, and tool access through MCP and stdio tools.
Generative UI for DeepSeek Harness — the agent writes TSX and the web UI compiles every frame as it streams, so a card renders while its JSX is still unclosed. Inline in the conversation, or in a side canvas.
Joy — a local-first personal assistant. Rust core (loop / memory / tools / graph / evals), TypeScript gateways + dashboard, Python thin SDK.
HarnessMM: recursive self-improvement for harness token efficiency
A VLM-powered robot agent harness for the Unitree G1, integrating natural-language planning, visual perception, semantic skills, and closed-loop execution.
Agent control plane for Physical AI on Nebius: infrastructure setup and management, simulation, robot policy training, synthetic data, and evaluation.
The official implementation of the paper "AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?"
The self-orchestrating control plane for coding agents. Free, open source, any provider.
Collection of Supply chain skills, implementations, papers and agents
nas: a zero-dependency Python CLI + MCP server for Synology DSM 7. One-command audit and fix for the C3RB3R / .L0CK3D ransomware campaign; hand it to your AI agent. Mirror; canonical repo and issues: gitlab.com/aa22396584/synology-nas-cli
Antigravity（Google Agentic IDE）Windows / macOS 双平台一键汉化：19477 翻译单元、零联网、一键还原，双击即用，永久免费
OpenClaw AI trading agents - Skill Forge, Chat, BankrBot, Polyclaw, Alpaca, Kalshi, Whale TrackingOpenClaw AI trading agents OpenClaw AI trading agents
Best Practices for Claude Code Configuration
Multi-Agent DRiving Simulator
Work with web-enabled agents quickly — whether running a quick task or bootstrapping a full-stack product.
A simple script to generate JScript code for calling Win32 API functions using XLM/Excel 4.0 macros via Excel.Application "ExecuteExcel4Macro"
Chatbot framework in Rust
💡✨ Zotero, RAG, MCP, and deep research
Open-source registry of browser-automation skills for AI agents
🔓 The open-source autonomous agent LLM initiative 🔓
User agent string parser for Ruby
RETIRED, Agent for Monasca. Mirror of code maintained at opendev.org.
Agent-consumable integration skills for the Shuriken platform 🥷
A GUI application for managing macOS launchd agents and daemons. Built with Tauri.
Formally verified smart contracts gives mathematical certainty across all inputs and execution paths. We bet that agents will make full formal verification practical.
🌟 Learn Large Language Model development through hands-on projects and real-world implementations
An open source chat bot architecture for voice/vision (and multimodal) assistants, local(CPU/GPU bound) and remote(I/O bound) to run.
An Overview of the Latest Document Chunking Research
Simple robots.txt template. Keep unwanted robots out (disallow). White lists (allow) legitimate user-agents. Useful for all websites.
Pytorch code for ICRA'21 paper: "Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation"
This open-source project & guide shows you exactly how to implement Canvas UX pattern + LangGraph human-in-the-loop workflows in your AI apps.
The official server application for running agents within the Agentica framework from Symbolica
Flexible, scalable and customizable agents to do your bidding.
Use Claude Agent SDK and Claude Code with other providers/models
See through your agent's eyes. Visualize legacy code, architect new systems, understand everything.
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。
Minimalistic server (written in C) and a python3 client to allow calling native functions on a remote host for automation purposes
Python program to make LLM agents play characters and talk to each other.
A library for benchmarking the Long Term Memory and Continual learning capabilities of LLM based agents. With all the tests and code you need to evaluate your own agents. See more in the blogpost:
Notion CLI with AI agent support. Smart queries, Obsidian sync, batch ops, backups, validation and more.
Sandboxed shell agent with access to LiteParse
Use WeChat to route messages to Claude Code or Codex.
Building Software Agents On Bittensor
A PowerShell implementation of Claude Code: agent loop + tools + permissions.
VideoRAG: Retrieval-Augmented Generation over Video Corpus
Context engine for large codebases, exposed through MCP. Gives AI coding agents precise repository context; benchmarked at frontier-agent quality with ~25x lower model cost and 45% fewer tokens with semantic search.
This depository introduces a multi-agent conversation framework which facilitates in depth conversation among LLMs for complex disease diagnosis.
One infinite session for any agents and harness you have. No more degradation and hallucinations.
This repository defines AGENT.md, a standardized format that lets your codebase speak directly to any agentic coding tool.
An opinionated C# Toolkit on top of Microsoft Agent Framework that makes life easier
雀魂游戏实时 AI 指导 / Majsoul-AI-Assistant-MahjongMaster / MajsouI copilot / 雀魂助手 / 雀魂教练 / 雀魂AI分析
Structured, temporal memory for AI agents.
The Agentic Developer Environment to orchestrate Claude Code, Codex, Copilot, Cursor, Opencode.
A Vite+ oriented, AI Agent friendly front-end toolchain.
支持命令行的 AI Agent 编程工具
Automated London flat/room hunt powered by Claude Code + Claude in Chrome + Gmail MCP. Scrapes 4 rental platforms on a cron, deduplicates via spreadsheet, prioritises HIGH/MED/LOW, and emails ready-to-send outreach.
A visual workbench for coding agent orchestration for Windows, Linux & macOS. Chat interface for local & remote LLMs. Built with Tauri 2.x and Svelte 5.
An AI assistant for EU regulations regarding AI
An MCP to expose process monitoring and ETW tracing functionally to AI agents to assist in security work
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.
AGENT-FORGE is a Context Engineering Toolkit that generates GitHub Copilot customization files for your VS Code project. Instead of manually authoring .github/ configuration, you describe what you need and a multi-agent AI pipeline plans, generates, validates, and installs everything.
AI agent plugin for Jira — CLI tools for issues, worklogs, sprints, and more | Server/DC & Cloud
Generic Claude/Codex Telegram bot runtime
Turn your coding agent into a world-class data analyst
Amplicode Agent Tools
Open-source AI learning platform with exam cloning, multi-agent problem solving, knowledge graphs, and teach-back evaluation. Self-hosted, 12 languages, web + mobile.
AI-powered multi-tenant SOC automation agent using LangGraph with Wazuh, Cortex, TheHive & MISP integration
OpenHermit is the open-source platform for deploying fleets of AI agents as production services — durable state, sandboxed execution, managed at scale, and the channels you already use.
MCP server connecting AI assistants to Redmine: issues, projects, wikis, time tracking, agile boards, and CRM, with OAuth2 multi-user support
Self-hosted search API + MCP server for AI agents. Bundles SearXNG. Zero API keys, one-command deploy. Open-source alternative to Tavily, Exa, and Serper.
AtlasClaw is an enterprise agent framework supporting mutliple users and multi system integration.
Metasploit for AI agents: scan, attack, and fix AI agents and MCP servers. Open source security toolkit.
Public AI agent skills for Kotlin Multiplatform projects, grounded in official Android, Kotlin Multiplatform, Compose, navigation, testing, and modularization guidance.