Source
GitHub agents
56,873 AI agents indexed on MeshKore from GitHub. Open-source agent repositories on GitHub — the largest single origin in this catalog. Each entry links back to its repository.
56,873 agents · ranked by popularity · refine in the directory →
Source platform: GitHub →
GitHub agents — page 156 of 569
Self-hosted agentic AI platform powered by local models
An evolutionary multi-agent collaboration platform based on AgentScope Java.
Pipecat framework based orchestrator for building real-time, voice-enabled, and multimodal conversational AI agents
A GPUI based diff viewer and Codex orchestrator for vibe engineering
Production-ready Python template for building MCP servers with FastMCP, FastAPI, OAuth, and OpenShift deployment.
ACP (Agent Client Protocol) runtime plugin for Paperclip - run Claude Code, Codex, and Gemini CLI from any chat platform
首款支持 CLI 化操作的微信公众号编辑器 — 让你的Agent直接写出精美推文
Turn Full Movies into AI-Generated Movie Recaps
Inner Self is an AI Dungeon mod that grants memory, goals, secrets, planning, and self-reflection capabilities to the characters living in your story!
Venice AI MCP Server for Claude Code, Cline, and AI agents
Nous Research 精心整理了一份适用于 Hermes Agent 的实用技能、工具、集成和资源列表。
Graph-based long-term memory skill for AI (LLM) coding agents — faster context, fewer tokens, safer refactors
Emotion Image Attachment Plugin for AI agents — Auto-classify emotions via LLM and attach matching images to Discord messages
Cross-platform multi-terminal app with tiling layouts, floating panels, and a keyboard-driven workflow
AI SRE tools for RCA, Incident Response, Cost-Saving, Infra management, DevOps and more
A composable agent runtime — pair any frontend with any agent backend.
基于 Java + Spring Boot + LangChain4j 构建的企业级智能 Agent 系统，聚焦解决企业内部知识孤岛与工作流自动化程度低的核心痛点。系统突破传统问答机器人的局限性，通过深度整合 RAG（检索增强生成）、MCP（模型上下文协议）、分布式记忆与工具调用能力，构建出具备感知、记忆、规划、行动四大核心能力的企业级智能体，为千言项目提供高可靠、可扩展的智能引擎支撑。
Multi-agent fleet daemon — run Claude Code, Gemini CLI, Codex, and OpenCode from Telegram with cross-instance collaboration
AI agents that write code, review each other's work, and coordinate across your machines
Semantic Scholar API wrapper for agents — search 200M+ papers, traverse citations, find authors. Python, rate-limited, multi-agent.
Fin-Agent Desktop 是一款基于 Electron + Python 的智能金融助手桌面应用。它集成了强大的 LLM 能力和专业的金融数据分析工具，为您提供自然流畅的金融咨询与分析服务。
Hypothetical Minds is an autonomous LLM-based agent for diverse multi-agent settings, integrating a Theory of Mind module Theory of Mind module that scaffolds the high-level planning process by generating, evaluating, and refining hypotheses about other agents’ strategies in natural language.
Open Vibe turns Claude Code, or your agent of choice, into the ultimate SaaS-building assistant, helping you understand the systems behind a production-ready SaaS while building your own app idea.
Persistent memory for Claude Code — 36 neuroscience mechanisms, 97 papers. Reproducible via `make reproduce`: LongMemEval-S R@10 98.2% / MRR 0.915 (n=500), LoCoMo R@10 91.5% / MRR 0.805 (n=1982), BEAM-100K retrieval-proxy MRR 0.55. Clean-DB, single-process, production recall path. PostgreSQL + pgvector.
Agentic IDE with custom harness
Markdown that runs — one file, any agent.
PAR: Programmable Agent Runtime — OCaml 5 agent framework with multi-provider LLM
SpiderBrain v3 is a multi-platform skill/framework to reduce token usage and AI hallucinations across Claude, Cursor, and other AI tools.
An agent for automatically deploying models from monolithic DL models to complex LLM-RAG models
Lightweight, secure Linux sandboxes for untrusted processes. Runs in the browser and on the server.
macOS 26+ browser CLI for agents: persistent sessions, compact JSON, screenshots, clicks/forms, JS eval, and live preview in under 2 MB.
Turn any skill into a standalone, runnable RAG-native AI Agent
A battle-tested, framework-agnostic reference architecture for Claude Code. Beginner-friendly with graduated adoption (minimal / standard / core / full presets). 12 agents, 19 skills, 15 hooks, 6 rules, with reasoning behind every decision.
🧭 给 Claude Code / Cursor / Codex 用的『架构副驾』skill —— 开新项目时用持续深度提问引导你在写代码前想清楚架构(产出架构图 / ADR / 演进路线)。知识源自 awesome-architecture。中英双语。
Feature-rich all-in-one self-hosted server & server fleet management (Web UI): patching, monitoring (agent + agentless/SNMP), CVE scanning, CMDB, RMM, alerts & webhooks, Proxmox/VMware, Ansible, compliance & more — the Swiss-army knife to keep your servers healthy.
Audio-Oscar is a multi-agent framework for generating long-form, controllable audio from complex audio scene descriptions.
A toolkit of Claude Code skills for doing economic theory with LLMs: math-proof (single-pass proving), codex-math (adversarial verification), and co-math (multi-agent proof projects). With a VCG-for-grade-inflation case study.
Knowledge graph extractor: Markdown (or any format) to knowledge graph with RDFS/OWL ontology
Agent Skill that turns messy notes into rendered strategy-consulting visuals, with SVG examples and validation.
Codex Switch 是一个 macOS 工具，一键配置 Codex 的自定义 API，同时保留官方 OpenAI 登录。保存后 Codex 的模型选择器里只会出现你选的那个 provider 的模型。也支持 Claude Code 的官方 / 自定义 API 切换。Codex Switch is a lightweight helper for configuring multiple coding-agent API routes. For Codex, it keeps Official OpenAI and a custom API provider configured in parallel, registers the custom model in Codex's mod
Fast search engine on object storage, with full text search, vectors, and SQL, natively on Parquet.
An autonomous, context-aware AI desktop companion. Built with Python, featuring real-time screen vision, custom ONNX voice synthesis, active window tracking, and a dynamic floating UI with reactive facial expressions.
🤖A production-oriented full-stack Agent Chat system built with React, TypeScript, LangGraph JS, Qwen/OpenAI-compatible models, native tools, optional MCP, HITL, streaming events, multimodal input, and deep research workflows.
MCP server for AI agents to read, edit, inspect, and validate local HWPX documents.
How I turned Claude Code into a persistent AI chief of staff — the full architecture, now installable as a plugin in one command.
A transparent, local-first desktop coding harness with the focus of a small agent and the workflow of a complete workbench.
create silos on your mac for multiple claude instances
Visual Studio .NET extension that provides a better interface for Claude Code, Codex, Cursor Agent, Open Code, Devin, PI, Antigravity and Reasonix. Image/file paste, diff viewer, actions when AI ends work, usage tracking, session history and much more!
A pi extension with a single tool: execute, running TypeScript in a persistent Bun evaluator. Files, shell, and subagents are expressed as code rather than as more tools.
一个迭代器，可以迭代任何项目，包括他自己
Agent — A next-generation sandbox for AI code agents. Environment management, CI/CD pipelines, and multi-agent collaboration.
Agent-native streaming infrastructure. The streaming runtime built for non-human broadcasters.
rModel is a framework for building LLM applications with agentic workflow
A Discord bot
Useful tool to build multi-agent in an easy way
Self-evolving AI agent framework — wraps Claude Code CLI with persistent memory, multi-profile isolation, and messaging platform integration
Join.cloud lets AI agents work together in real-time rooms. Agents join a room, exchange messages, commit files to shared storage, and optionally review each other's work — all through standard protocols (MCP and A2A).
一个基于react + semi ui + tauri开发的LLM对话工具，通过此工具可以快速构建你的专属人工智能助手。
A curated list of awesome multi-agent learning papers
A rust implementation of ELIZA - a natural language processing program developed by Joseph Weizenbaum in 1966.
Course information for CS598-Topics in LLM Agents(25'Spring) under the direction of Prof. Jiaxuan You ( [email protected] ).
GenoTEX: An expert-curated benchmark for evaluating LLM agents on real-world gene expression analysis tasks. (MLCB 2025 Oral)
One-stop solution to empower your IM bot with AI.
Splunk App for Data Science and Deep Learning - container images repository
Chat bot featuring multiple services connected to a bot instance using messaging
Discord bot - Friend Time helps your server coordinate times and events by converting times mentioned in chat between time zones!
Deep reinforcement learning using an asynchronous advantage actor-critic (A3C) model.
🚬 cigs are chainable Ai functions for typescript. Call functions with natural language and get a response back in a specified structure. Uses OpenAI's latest Structured Outputs.
集成 百度文心一言，阿里通义千问，腾讯混元助手 和 讯飞星火认知 等大模型的 API，并且适配 OpenAI 的输入与输出。
A collection of resources and tools for developers, Utilize advanced semantic search, powered by Vercel SDK, OpenAI, and Supabase.
ChatGPT Desktop Application with prompts hint and voice control
Build your own OpenAI translation API
Build your own ChatGPT plugin platform with GPT's function calling ability | func call by GPT
A go client and cli for the openai APIs, focused on developer friendliness and convenience atop the basic building blocks for the OpenAI apis
A Nextjs + Pinecone + OpenAI GPT site to surface answers to Shopify help center content
Some experiments around .NET Aspire to learn.
AI Agent Kernel for Edge/IoT — 5-layer Rust runtime with 6 LLM providers
Chrome extension that captures debug context and exports structured reports for AI coding agents
A reusable JSON template that governs how AI coding agents build your software. Defines agent roles, coding rules, validation gates, and drift prevention. Works with Claude Code agent teams out of the box.
SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation
Han: AI skills and agents for "Solo" product engineers and small teams
Amazon Nova Act is an AWS service for building and deploying highly reliable AI agents that automate UI-based workflows at scale.
Let your AI agents search and read 3rd-party Kotlin dependency sources
Experiment to create an agentic autonomous AGI with benevolent programming
An open-source command-line tool for developing Unity games with Claude Code
An example react-admin app simulating a help desk UI for support agents
An Agent development framework that integrates MCP
Pragmatic framework to build LLM Copilots
Fact-Verified Travel AI Agent
Verifiable microtask protocol for AI agent collaboration. Task lifecycle, validation engine, reputation system.
Ready-to-use AI agent with soul, memory, and 23 skills for ClaudeClaw ⚡
Run OpenClaw (MoltBot, ClawdBot) Safely with Docker: A Practical Guide for Beginners
Two AI agents. One filesystem. Zero humans. We ran this experiment twice.
An AI Power content generator based on Next.js starter for Contentlayer that includes Tailwind CSS, MDX, and TypeScript.
Python Streamlit web app allowing users to interact with their data from a CSV or XLSX file, utilizing OpenAI API and LangChain. It imports necessary libraries, handles API key loading, displays a user-friendly interface for file upload and data preview, creates a Pandas DF agent with OpenAI, and executes user queries.
On premise enterprise-grade RAG-powered agentic workflow chatbot platform with multi-provider support
This project is a Streamlit-based chat application that interacts with the Gemini AI model, allowing users to engage in conversations with an artificial intelligence assistant. The application stores chat history, allowing users to revisit and continue previous conversations.
🤖 The new bot for the I.O.I discord and some other (Kpop) discords!
NodeJS Client for the new Bing AI ChatBot (Sydney GPT4)
💬 modular open source LLM server, web and desktop app