Framework
Custom agents
40,172 Custom AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
40,172 agents · ranked by popularity · refine in the directory →
Custom agents — page 220 of 402
Clojure libraray for Milvus
[NAACL Findings 2025] This is the official repository for SusGen-GPT.
A Retrieval-Augmented Generation (RAG) application for exploring Tokyo land prices using an interactive map
A modular framework for building complete AI solutions. It's mostly a Rust framework with a subset of it ported to Deno.
RAG application (backend & frontend) with sources retriveal and highlighting on the Databricks Platform
Fine tuned llama 3 models for context based question answering in bengali language.
AI Intelligence Platform -- knowledge graph + semantic search + reasoning + multi-agent debate in a single binary
An open-source AI system for TRIZ-based inventive problem solving with interpretable, step-by-step reasoning flow
小红书内容创作自动驾驶 — AI Agent 全流程自动化
"Solace AI: Your Empathetic Digital Confidant": Solace AI is an empathetic mental health companion that understands your emotions and personality to provide personalized support through natural conversations. It creates a judgment-free space where you can express yourself freely and receive compassionate guidance tailored just for you.
Hire a whole company with one plugin. 75 specialized AI agents across Engineering, Product, Infrastructure, Data, Security, Marketing, Sales, Finance, Legal, and People.
Move beyond prompts. Build verifiable, intent-driven Semantic Agents.
Making Backlogs 5 Min Hustle | CheatZ Making Exams Easy
Portable web-research and browser-automation SKILLs for Claude Code, Codex, and OpenCode — Playwright, Chrome DevTools, nodriver, and HTML-to-Markdown.
AI-Assisted Development Playbook & Task-driven development methodology for AI-agents.
A curated list of all things just-bash - ports, filesystem adapters, libraries, integrations and more
MCP server exposing 40 PM skills + 11 workflows + 8 utility tools (59 tools) via Model Context Protocol. In maintenance mode (v2.9.x line, latest v2.9.3; catalog frozen at v2.9.2 build). For new users, the file-based install from product-on-purpose/pm-skills is recommended.
🥊 sparkit: The CLI & Playground for SPAR — Run AI debates in your terminal or browser
Copy-paste curl|bash one-liners to install every tool in the Agent Flywheel ecosystem: 23+ CLIs for AI agent orchestration, memory, security, and development
AI-IQ: Persistent context system for AI coding assistants. AI doesn't need knowledge — it needs relevant context. Hybrid search (FTS+semantic), graph intelligence, zero config.
Safety benchmark for personal AI agents under realistic prompt injection. 120 test cases across 5 professional domains, 3 injection vectors, and 5 harmful action types. (arXiv 2026)
Scribe lets you install AI coding skills once and automatically distributes them to all your coding agents
Headless terminal emulator CLI powered by libghostty-vt
An open standard for multi-agent workflows -- from scripted pipelines to self-organizing teams. Declarative. Runtime-agnostic. Portable.
Tutor AI is a Multi Agent AI Tutoring System (FastAPI + React) that generates study content, question sets, and feedback—powered by Gemini and MongoDB Atlas Vector Search.
The system enables sophisticated coordination of multiple drones through natural language commands, visual inputs, and real-time environmental data.
A self-hosted code context engine for MCP.
Multi-agent AI orchestration system
Agentic Ops Framework
Human Delegation Provenance Protocol - cryptographic chain-of-custody for agentic AI
Open-source local-first AI desktop copilot with an expressive blob companion, voice and text commands, browser automation, app control, and community-driven capabilities.
Telegram bot that interacts with the local Ollama 🦙 to answer user messages
terminaldweller's IRC bot
A static web ui for llama.cpp server. The llama.cpp chat interface for everyone. base on chatbot-ui
A spoken English education chatbot based on ChatGPT/whsiper and gTTS.社恐人士的英语角
在线客服，chatbot，chat，ai，AI Chat，在线客服转人工，大模型聊天，大模型IM客服，可与FreeAICC电话呼叫中心整合。
An empathetic counselling chatbot. Retrieval-based, uses finetuned LMs for emotion identification and to boost empathy, novelty and fluency of the retrieved responses. Backend: Python, frontend: Javascript.
🌟 Full-stack app for real-time avatar streaming with HeyGen & Gemini AI. Built with React, TypeScript, Express, and Tailwind during a hackathon by Team "Bit by Bit"
Talking Graphs: Your Data Speaks Up
The E2E AI testing tool | No ML Overhead
Evals framework for Information Retrieval Systems
RAG-powered code search via simple REST API
HumanStudy-Bench: Towards AI Agent Design for Participant Simulation
Offensive security testing CLI for AI agents — 85 attack strategies (and counting) across 12 categories
Give OpenClaw the power to control your desktop — UI-TARS VLM-driven GUI automation
Black-box AI reliability certification via self-consistency sampling and conformal calibration
AI Clash / AI 对撞机：一次提问，多款网页 AI 同屏对比；支持中英文界面，内置 AI 裁判总结共识、分歧和最优答案。
Standardize your AI collaboration. AGENTS files for your AI. HUMANS files for you. And more...
Define a Go struct. Get a CLI that an agent can discover, call, sandbox, and debug. Flags, env vars, config files, validation, JSON Schema, MCP, structured errors, and WASM. Built on Cobra.
Run AI SDK agents in a terminal UI.
Offline RAM-first cognitive leer/coprocessor for AI agents and robotics. Solves "Context Abandonment" with 20-80ms latency using a dual-thread biomimetic memory architecture (ONNX + SQLite WAL).
A comprehensive AI & ML project portfolio from the University of Texas at Austin PG Program, demonstrating real-world data science and machine learning solutions.
AI Agent examples with TypeScript
Statistical evaluation framework for AI agents
Superzent - an agent-first workspace built on Zed
Turn one-off AI collaboration prompts into long-running repository governance. · “把一次性的 AI 协作提示，疏导成项目里长期可运行的治理体系。”——Dayu Harness Skill（大禹治库.skill）
the credit score for context.
Build knowledge graphs from biomedical literature and query them with an LLM agent
"Open-source toolkit (Python Library, Registry API, CLI) for secure, decentralized AI agent interoperability using A2A/MCP."
A multi-provider AI coding agent with the persona of a Tech-Priest
Agentic coding harness with persistent memory and a REPL body. Built on Ori Mnemos. Open source must win.
MedSync-AI helps patients manage medications and health routines with an AI assistant. It supports reminders, symptom logging, adherence tracking, and quick insights, while keeping data privacy in mind. Built with modern web/mobile tooling and modular services to integrate with wearables and EHR/health data sources.
Instant, local access to complete Base44 documentation with AI assistant integration
An open-source AI chat interface designed to be private, customizable, and simple to use.
RAG-based question answering system on MS MARCO with retrieval, reranking, evaluation, and reproducibility checks.
Official ServerlessClaw: The authoritative autonomous AI agent swarm for AWS. Zero idle cost, self-evolving, and infinite scale. Powered by OpenClaw.
Trend Devourer 👗✨ AI-Powered Visual Style Analyst
Give AI coding agents (Claude Code, Cursor, Aider, Codex) a structured autonomous loop with guardrails — boundaries, 5 verification gates, 3-layer self-reflection, and autonomous remediation. pip install ouro-loop. Zero dependencies.
An MCP server that gives coding agents instant insight into any Git repository — no guessing, no hallucination.
Reproducible evaluation for AI coding agents. Multi-turn scenarios against Claude Code, Codex, Copilot, Cursor, Gemini CLI, Goose, OpenCode, or any custom agent you plug in; verify behavior with rule checks, workspace diffs, multi-judge LLM consensus; pin reliability with pass^k variance across trials. Git worktrees, optional Docker sandbox.
Profine automatically profiles and optimizes PyTorch training jobs on real GPUs, delivering measurable speedups and lower GPU costs before teams waste days tuning configs by hand.
A personal Cloudflare-hosted development environment. Work lives in conversations, not terminal tabs.
Stop prompt injection catastrophe! Run your AI Agents in secure isolated environment now.
A 7-Pillar AI+Human SDLC methodology — 10 stages, 5 quality gates, 18 SOUL roles. Tool-agnostic, MIT, battle-tested.
Rassam is an agent that lets you create flowcharts and convert them to code and vice versa, all in one place.
A Go symbol and call-graph database backed by SQLite. Query symbols, callers, callees, blast radius, dead code, and interface implementors as structured JSON — typed code navigation for AI agents (MCP) and humans.
Collection of Claude Code Agent Skills for founders, indie hackers, and growth engineers
Agent Skill for generating deployable system prompts for AI agents
Open-source autonomous multi-agent AI platform. Dockerized agents driven by Claude or Codex, orchestrated with Temporal workflows and coordinated via Telegram.
HyDRA: Hybrid Dynamic RAG Agents, An advanced, agentic AI framework that transforms Retrieval-Augmented Generation from a static pipeline into a dynamic, learning reasoning system.
Chatons is a desktop AI workspace for coding and project workflows: it lets you chat with multiple AI providers, pick scoped or full model lists, manage skills/tools, and keep conversations organized in one place.
A Python-based project demonstrating integration of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) for enhanced AI-driven applications. Includes code examples and tutorials for leveraging APIs and RAG techniques to build intelligent systems.
开源、用户自有、运行在个人 Cloudflare 账号中的 AI 记忆层。
AI coding assistant rule manager for Claude Code, Cursor, and Codex. Load only the rules you need.
A plugin that simulates an AI agent orchestration layer on top of RisuAI.
Waifu for hermes-agent. Dashboard plugin with multi-emotion support.
AI-assisted orchestration for bug bounty hunting. Automates security tools for reconnaissance and analysis with real-time Telegram alerts.
Multi-agent research orchestrator for Claude Code — decomposes any question into parallel workstreams, monitors agents, and synthesizes results
Chat-first toolkit for teachers to plan complete courses and lessons with multi-agent workflows, template-based artifacts, and MARP slide generation.
Standalone MCP server that gives AI agents full GUI control over macOS — screenshots, mouse, keyboard, apps, clipboard, and multi-display. Zero private dependencies.
Agents at Scale Marketplace for ARK (Agentic Runtime for Kubernetes)
A full-stack AI assistant built on Amazon Bedrock AgentCore. This sample demonstrates how to build a feature-rich, self-hosted AI assistant that leverages AgentCore capabilities like managed runtimes, sandboxed code execution, and persistent memory.
Workshop about agentic AI using JunOS and Linux MCP servers
Workspace Architect is a zero-friction CLI tool that provides curated collections of specialized agents, instructions, and prompts to supercharge your GitHub Copilot experience.
OpenClaw4J is a modern intelligent Agent framework built on Java 21 and Spring AI. Inspired by the OpenClaw project，OpenClaw4J 是一个基于 Java 21 和 Spring AI 构建的现代智能 Agent 框架,受到 OpenClaw 项目（开源精神与经典重构）的启发，本项目的目标是为 Java 开发者提供一个灵活、可扩展且功能强大的 AI 机器人/Agent 开发底座。
C# local LLM chat completions library using ONNX Runtime, compatible with Microsoft.Extensions.AI
A modular AI-driven RPG engine powered by LLMs, featuring RAG-based consistent memory.
MiniMax Code Review for GitHub Actions
Web application explaining how LLMs work using D3.js + GSAP
Enterprise-grade AI Agent system for code generation, analysis, and orchestration