Custom agents

Self-hosted AI Agents for your whole team — on your infrastructure, your models, around the clock.

Run agents like a company. AgentOS is the native control plane for OpenClaw — manage agents, tasks, models, context, approvals, and runtime visibility from one place.

The agent behind VYNN AI, a personal AI financial analyst with 5K+ users. Ask any market question; code computes every number and every claim is sourced.

the extensible, customizable, self-documenting, real-time multi-agent computing environment

Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over a local LLM wiki with on-device embeddings and an MCP server.

(ICML 2026) Self‑Evolving LLM Agents through an Experience‑Driven Lifecycle

A toolkit for turning internship materials into resume-ready bullets and interview-ready project narratives, with achievement auditing, JD-based ranking, AI-heavy phrasing checks, and structured interview prep outputs.

Ray Fernando's collection of Skill files for AI coding agents. First up: running-bug-review-board, a real-user QA workflow with a Bug Review Board (BRB) feedback loop.

Self-hosted AI visibility (AEO) stack. Track how ChatGPT, Claude, Gemini, and Perplexity cite your domain. Join it with Search Console, GA4, Bing, server-side traffic, and paid. Agent first.

A curated list of awesome genomics and bioinformatics agentic skills, MCPs and benchmarks for Claude Code, Copilot, Codex, Cursor, Gemini CLI, etc

A collection of structured AI agent skills that enable Claude Code, Cursor, GitHub Copilot, and other AI coding assistants to create, operate, debug, and govern Harness CI/CD workflows through natural language.

Recreate any web animation from a screen recording. A motion-design plugin: analyzes motion (timing, easing, stagger, loops) and rebuilds it as GSAP / CSS / Framer Motion / Lottie code.

AgentRadio: Passive Awareness for Long-Horizon Multi-Agent Collaboration

An open-source profiler for AI agents that analyzes token usage, cost, latency, and optimization opportunities across LLM workflows.

Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.

Desktop GUI for the omp coding agent: parallel sessions, visual tool calls, model/provider management, and usage analytics.

让 Agent 通过对话直接操作你的商城、SaaS、CRM 或 ERP 后台，同时保留原有权限、审批与审计。Self-hosted hub for agents operating existing business systems safely.

TradingView MCP server: search indicators and strategies, fetch Pine Script source. Works with Claude Code, Claude Desktop and Cursor. No API key needed.

Your durable workspace across AI agents.

Self-hosted multi-model deep research system that fuses independent research agents into evidence-grounded reports.

A curated collection of papers and resources on voice agents, from spoken interaction to autonomous task execution.

Anywhere GPT, the ultimate mobile app with seamless AI assistance 💻 at your fingertips! Say goodbye to screen-switching! 🔥📱🤖

🤖 聊天机器人示例，定制聊天机器人，聊天机器人语料导入导出

The best-benchmarked open-source memory system for AI coding assistants

A production-grade methodology repository for building AI-native applications using iterative sprints, where AI coding agents are primary implementors and humans are architects, reviewers, and decision-makers.

OCode is a sophisticated terminal-native AI coding assistant that provides deep codebase intelligence and autonomous task execution

Bomberland: a multi-agent AI competition based on Bomberman. This repository contains both starter / hello world kits + the engine source code

Fully featured .NET library in C# to build MTConnect Agent, Adapter, and Client Applications. Pre-built Agents with Windows Installers. Support for Windows and Linux. Supports MTConnect Versions up to 2.7. Supports .NET Framework 4.6.1 through .NET 10

Web UI for Ollama built in Java with Vaadin, Spring Boot and Ollama4j

The first real-world AI hedge fund framework in crypto, fully open source!

A Deep Thinking RAG Pipeline to Solve Complex Queries

Launch Koishi from your desktop

Legal Research Copilot Example Solution built with Generative AI capabilities of PostgreSQL on Azure

Cliptolution剪辑进化，面向视频编辑和创意制作的ai agent

A reference blueprint for building persistent, multi-agent Claude Code setups with Telegram and Discord.

Multi-agent AI discussion CLI for structured debates between LLMs

29 essential agentic design patterns for building intelligent AI systems

DreamGraph is a graph-governed conceptual development environment (CDE) that turns plans, architecture decisions, and project knowledge into auditable execution through a persistent cognitive graph.

Open-source, self-hosted multi-agent AI infrastructure for teams and apps with support for cloud and local models, tool integrations, workflows, and automation across business systems including Slack, ERPNext, Discord & Gmail.

ClickUp CLI for AI agents

openJiuwen DeepSearch is a knowledge-enhanced deep search and research framework with industry-leading chunk-level citation and traceable reasoning capabilities, delivering precise agentic search and research abilities.

Whiteboard tldraw diagrams (.tldr) from natural language with 6 presets and vision-based self-check. PNG/SVG export, multi-agent.

A collection of skills for AI agents (Kiro, Cursor, Windsurf, Claude Code, and others). Each skill is a reusable module that teaches the agent to perform complex tasks with context, structure, and best practices.

General Purpose Evaluation and Simulation Environment for all your AI related Workflows

Communication for AI agents: stable identity, durable mail and chat, and wake-up events across sessions, runtimes, machines, and organizations. MIT, self-hostable.

Standardized tool schemas and SDKs that expose Sciverse Open Platform retrieval capabilities to LLM agents.

轻量、自托管的多入口 AI Agent 机器人｜QQ 官方 / OneBot 11 / NapCat / 微信｜Rust｜Memory / RAG / Todo / Tool Calling

financial agent api with multi-agent framework for scalable AI systems focusing on financial intelligence, RAG pipelines, observability, and secure governance. ACP Openclaw, Gemini CLI, Opencode

Dex trade agent kit which AI-powered trading toolkit with two standalone packages

AI-first Turborepo monorepo where Claude Code, Cursor, Copilot, Gemini CLI, Kiro & Windsurf read one AGENTS.md handbook and ship identical, production-grade code. Next.js 16 dapp, React 19 admin SPA, Astro landing, Connect-RPC backend — TypeScript strict, deployed to Cloudflare.

A GPU-rendered, terminal-first workspace: Agent framework, real shells, IDE, Markdown, and multiplayer — one Rust engine.

DeepSeek Harness 原生桌面端 · Linux / macOS / Windows · Rust + Tauri

AI-native cross-platform database workbench for developers and data teams.

Agent Workflow Engine for AI agents over MCP — per-step directives, completion conditions, and JSON-Schema validation. Self-hostable (Apache-2.0).

Open-source, evidence-driven MCP server for RTL simulation debugging: correlate VCS/Xcelium logs, VCD/FSDB waveforms, SystemVerilog/UVM source, hierarchy, and connectivity to trace failures to root cause.

AI csapatod, ami fut amíg te alszol.

A Curated List of Coding-agent that treat a program as the executable intermediate representation for Policy, World, Editor and beyond

Open-source mobile SSH/Mosh terminal and native AI workspace for Android and iOS.

Say it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model

Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.

Open-source, model-independent Agent Skill for evidence-based software reconstruction with REA. Optional integration, portable installer, and validation workflows.

SOTA Distributed LiDAR SLAM @ IEEE T-FR'26

Assessing the reliability, accuracy, and safety of large language models, RAG pipelines, and AI agents.

Benchmark local LLM serving by replaying real agent trajectories

Native macOS terminal for running, monitoring, and reviewing parallel Claude Code and Codex sessions.

A low-poly 3D office that shows your AI coding agents' live status — idle agents sneak off to play Minecraft (no tokens used).

A privacy-first guardrail for LLMs and RAG pipelines. SurrogateShield detects, redacts, and reconstructs sensitive PII data on the fly while defending against adversarial attacks.

🎉 Congratulations! This work has been accepted for publication as a Findings paper at ACL 2026! Mistake Notebook Learning (MNL) is a novel, training-free memory framework that enables Large Language Model (LLM) agents to systematically learn from their mistakes

A place to store jailbreaks, results of some prompts, or helpful utilities

tensorflow+bert+seq2seq 周公解梦。AI遇上玄学，说出你的梦境(dream)，模型自动解析decode梦境的征兆。类似聊天机器人(chatbot，QA)，你问我答。

🔥 Token-efficient JSON alternative for LLMs & agentic AI — same data, fewer tokens. Python · JS/TS · Rust · Go · C++

A comprehensive resource designed to help developers effectively use AI tools to develop websites, apps, and other projects.

A useful drawer for MacOS. chatting, clipboard, webscraping, window managing, shotcuts. built with Rust and ai-sdk

Algorithm for prioritized multi-agent path finding (MAPF) in grid-worlds. Moves into arbitrary directions are allowed (each agent is allowed to follow any-angle path on the grid). Timeline is continuous, i.e. action durations are not explicitly discretized into timesteps. Different agents' size and moving speed are supported. Planning is carried out in (x, y, \theta) configuration space, i.e. agents' orientation are taken into account.

开源 AI 命令行工具，将多模型 AI 智能体、智能工作流和规格驱动开发带入您的终端。（An open-source AI command-line tool that brings multi-model AI agents, intelligent workflows, and spec-driven development directly into your terminal.）

Enable AI to control your PC. This repo includes the WorldGUI Benchmark and GUI-Thinker Agent Framework.

Lightweight C++ LLM agent framework

agentic terminal application

[CVPR 2025] MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation Distillation

PodAgent: A Comprehensive Framework for Podcast Generation

A powerful AI observability framework that provides comprehensive insights into agent interactions across platforms, enabling developers to monitor, analyze, and optimize AI-driven applications with minimal integration effort.

A concise Claude reference bundle for developers, covering commands, MCP servers, plugins, tools, workflows, and agent frameworks in one place. Designed for fast discovery and practical integration.

Multi-agent system for generating Meta/Instagram ad creatives using Claude SDK and Nano Banana MCP

Connect AI assistants to your ERPNext instance via the Model Context Protocol (MCP) using the official Frappe API.

Mycelium is a shared workspace for AI coding agents and the people who run them.

Swarm-native terminal platform for AI coding agents: real-time pane capture, change-point pattern detection, transactional policy-gated automation, a JSON/MCP robot API, and a fail-closed operating envelope — on its own vendored terminal engine, with a native iOS client that attaches to your Macs.

Agent Skills Hub is a global library of AI agent skills that work across OpenClaw, Claude Code, Gemini, Cursor, Antigravity, and more.

让 AI 主动记错题、自我迭代的协作机制 · A framework that makes your AI reflect on its own mistakes and stop repeating them

Portable , scalable , secure AI Agents

OKF-powered knowledge context for Claude Code — injects your project's knowledge base at every session

AgentCat is an analytics platform for MCP server owners 🐱.

Workshops are secure, fast, and composable development environments that come agent-ready.

All-in-one Docker/Podman image: hermes-agent + hermes-webui + hermes-dashboard in a single container

First-tree routes work to the right agent, gives it the same context your team has, and loops humans in only when the rules say so. Lives in your GitHub. Open source.

Field-tested, open-source skills for Hermes Agent.

Growth Marketing OS | Mahmoud Omar — open-source AI marketing prompts, Claude skills, agents & growth playbooks (EN + AR)

数万行散落的 Claude Code、Codex 与 Pi JSONL 会话，索引至同一个 SQLite 中：
Agent 可通过 CLI 实现毫秒级查询，用户可通过 App 直观浏览｜Past Claude Code, Codex, Pi sessions -- queryable by your agent, browsable by you

Local-first, spec-driven SDLC workbench with governance gates, knowledge graphs, and MCP for AI coding agents.