Custom agents

A programmable Voice AI platform: SIP and WebRTC call control, multi-party mixing, recording, TTS/STT, and pluggable AI agents (ElevenLabs, VAPI, Pipecat, Deepgram) — all driven through a REST API, webhooks, and a WebSocket event stream

self-extending sandboxed agentic harness. a loop, two tools and an llm

Multi-agent macro trading bot: multi-factor stock scoring, momentum portfolio construction, backtesting vs SPY/Nasdaq, and live Alpaca execution.

多智能体 LLM 股票/加密交易决策台 —— 13 位 AI 分析师研究、辩论、风控压测,收敛出可追溯、可实时观看的交易决策。 | Multi-agent LLM trading desk: 13 AI analysts research, debate & stress-test risk to converge on one traceable, streamed stock/crypto trade decision. Not financial advice.

Implementation for Decentralized Multi-Agent Systems with Shared Context

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.

Open-source control plane for Codex projects: Git-backed context, visible agent progress, scoped MCP access, resumable work, and safe handoffs.

Planoda — the AI-native work platform that replaces Linear, ClickUp, Monday & Trello. Issues, boards, roadmaps & automations on one schema, with AI agents that propose and humans who approve. Try the live demo — no sign-up.

Auditable AI agent for electromechanical maintenance with LangGraph, RAG, fault diagnosis and human-in-the-loop review.

Deterministic-first execution engine for agent workflows in Go: the LLM extracts at the edge, a deterministic state machine decides. Zero dependencies, no-code JSON plugins, replayable runs.

A native macOS Keychain launcher for API keys used by local agents, SDKs, scripts, and backends.

okx trading bot okx agent mcp cli cryptocurrency okx api automated trading typescript okx trading bot model context protocol cursor ai trading crypto spot futures okx trading bot npm pnpm okx mcp open source quant defi cex okx trading bot algorithmic trading crypto bot okx trading bot okx api mcp okx trading bot crypto mcp

The Self-Evolving Agent Ecosystem — Trading agents that evolve through Darwinian selection and adversarial self-play

Needle MCP Server for easy RAG.Long-term memory for LLMs.

List of research papers of research papers investigating the user experience of AI-powered programming assistants (e.g., Copilot).

MCPcat is an analytics platform for MCP server owners 🐱.

A practical guide to building AI products end-to-end. You'll learn how to choose models based on product constraints, decide when fine-tuning is worth it, evaluate with real metrics, and build an agent that works in production. This project is in progress; chapters and code will land in stages.

Evaluation Framework for all your AI related Workflows

A complete voice AI starter app for LiveKit Agents with Node.js

AI Agent Nexus is an open-source platform for developing, testing, and hosting AI Agents, built with Streamlit and Gradio. It offers a user-friendly chat interface and focuses on teaching core concepts of building full-featured AI agents. The platform supports multipl AI Agent and assistant patters, and complements the book "AI Agents In Action."

Fully stealth chromium for AI agents.

AI agent to automatically check grammar and spelling on documentation files

The agent benchmark that scores the full stack — harness, config, and model — not just the LLM. Trace-based scoring, reliability metrics, configuration diagnostics.

Multi Agent Path Finding Algorithms

RVM — The Virtual Machine Built for the Agentic Age, in Rust.

Apollo ~ Deep Research Meta Agent

Open Source Implementation of Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution

Deep active inference agents using Monte-Carlo methods

agent-based reactive programming library for typescript

Code and links for over 25,000 trained Atari agents

Search Self-Play: Pushing the Frontier of Agent Capability without Supervision

A curated list of frontend Agent Skills installable via npx skills add

LiveMCPBench is a benchmark for evaluating the ability of agents to navigate and utilize a large-scale MCP toolset. It provides a comprehensive set of tasks that challenge agents to effectively use various tools in daily scenarios.

Fetch papers as agent-ready markdown — DOI/URL/title in, structured full text out. CLI · MCP · Skill.

An example of a chatbot built with Microsoft Bot Framework and featuring e-commerce capabilities via Moltin, Azure Search, Recommendations API, and LUIS

simulai is a Notion-inspired open-source and free conversational survey builder, powered by AI.

An example chatbot application built on the Letta API, which makes each chatbot a stateful agent (agent with memory) under the hood.

Run & debug workflows for AI agents running Dockerized tools in VSCode

Cortex: Advanced Memory System for AI Agents

AgentX is an experiment to develop autonomous agents so you can automate everything! This project is inspired by Auto-GPT, babyagi, SuperAGI, and other agents.

医疗问诊系统multi-agent框架

Multi-Agent Deep Reinforcement Learning for Task Offloading in GDMSs

【软件创新大赛国三】🧩 An open-source multi-agent framework for intelligent health management, powered by the Linkage ecosystem.

phpipam scan agent

ai trading agent using interactive brokers api

A text-grid web renderer for AI agents — see the web without screenshots

Simulation of reward tokens in a DAO ⚡️Employs multi-agent simulations and discrete-time Markov random fields.

Rag Agentic的一个雏形,用于研究学习

GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation

This project uses Deep Reinforcement Learning (DRL) to develop and evaluate stock trading strategies. By implementing agents like PPO, A2C, DDPG, SAC, and TD3 in a realistic trading environment with transaction costs, it aims to optimize trading decisions based on return, volatility, and Sharpe ratio.

Official code for the paper: InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews (previously: Do Role-Playing Chatbots Capture the Character Personalities? Assessing Personality Traits for Role-Playing Chatbots)

Augment AI agents with long-term memory through knowledge graph 🧠

Promptdesk is a tool designed for effectively creating, organizing, and evaluating prompts and large language models (LLMs).

GitHub tools and agents for the Vercel AI SDK, wrap GitHub's API as AI SDK tools ready to plug into any agent

Public implementation of "Multi-Agent Graph-Attention Communication and Teaming" from AAMAS'21

Portable multi-agent AI developer setup for Claude Code + Ollama. Role-based local LLM orchestration via Bash — plan, code, review, commit. Zero Dependency. Works with any language stack.

希望用代码为 waifus 绘心。

Agent Skills to empower developers building AI applications with Weaviate.

pytorch를 사용하여 텍스트 전처리부터 RAG, 에이전트, LLM 파인튜닝을 정리한 Deep Learning NLP 저장소입니다.

AirSim-based UAV Foundation Model Learning: Covering Agents, VLN, World Models, etc.

A memory system using mem0 for AI applications. Enables long-term memory for AI agents as a drop-in MCP server.

Deterministic and Agentic patterns for installing and maintaining successful production applications

Build agentic-MCP servers by composing existing MCP tools.

✨ Build dashboards with end-to-end version control. 🔋 CLI w/ batteries included, no infra required. Develop on your laptop for instant results, deploy changes safely (with automated checks), and keep every report trustworthy for stakeholders, analysts and agents 🤖

Inpact is an open-source AI-powered platform designed to connect content creators, brands, and agencies through data-driven insights. By leveraging Generative AI (GenAI), audience analytics, and engagement metrics, Inpact ensures highly relevant sponsorship opportunities for creators while maximizing ROI for brands investing in influencer marketing

The most comprehensive open-source product development system. 31 AI agents. 23 frameworks. Solo founder Day 0 → IPO.

PasLLM - LLM inference engine in Object Pascal (synced from my private work repository)

AutoMind: Adaptive Knowledgeable Agent for Automated Data Science

Flow Nexus is the first competitive agentic platform built entirely on MCP. Deploy autonomous AI swarms, train neural networks, and compete in coding challenges while earning rUv credits. Transform agentic engineering mastery into lived experience through gamified cloud development where agents spawn agents and systems improve themselves

CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework

AI code attribution for git. Track which lines were written by AI vs humans.

Cyber-Zero: Training Cybersecurity Agents Without Runtime

The issue tracker your AI agents are missing. Think Linear or Jira, but for your Claude Code..

Fully automatic AI research agent for Geoscientists, Remote Sensing researchers, and GIScientists. Features harness engineering, GeoBenchmark (OLS/GWR/MGWR), journal templates, and MCP servers.

Curated collection of OpenClaw agent personalities — SOUL.md, AGENTS.md, IDENTITY.md configs

A structured Claude Code workflow to reformat research manuscripts for any journal's submission requirements without altering scientific content, created by Chen Zhu 朱晨 | 遗传社科研究.

Headless Ghidra MCP server — giving AI agents deep reverse-engineering capabilities.

MCP-powered Home Assistant conversation agent that solves entity context limitations through dynamic discovery instead of full entity dumps

De Chat a Sistema Cognitivo — 40-slide presentation on building AI agent systems with SDD orchestration, Engram persistent memory, and modular skills architecture. Gentleman Kanagawa Blur theme.

Official Agent Skills for the OpenData platform

[CVPR 2026 Highlight] WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning

AI股神Skill，改造了“麻省理工学院”开源的多agent股神框架，我用AI扒出了他们的核心源码，总结出了5个金融分析团队、8个核心agent提示词。用扣子封装成了一个人人可用的skill技能包。我们只要输入股票代码，AI就能模拟人类金融团队的运作模式，自动分析大a数据、并将舆情情报、板块涨跌、技术面、资金流动等多维度的可视化报告，自动推送到你的电脑上。用AI帮你彻底读懂市场行情！

Reusable GitHub Action that reviews Terraform PRs for security, cost, and style using a LangGraph multi-agent system, posting a single severity-ranked comment.

保姆级教程：通过 VPS + v2ray-agent + Clash 获得干净海外 IP，降低 Claude / ChatGPT 封号风险

Model-driven development for coding agents. Plan changes in a shared responsibility model mapped to your code; your agent reads, modifies, and implements it through a built-in MCP server.

基于 LangGraph 和 FastAPI 的电商 AI Agent 框架。从 RAG 知识库到复杂的退货业务流的智能客服系统。

Comprehensive collection of 133+ specialized AI subagents for Claude Code covering the entire software development lifecycle

Agent Skill for Android development with Kotlin and Jetpack Compose, covering modular architecture, Navigation3, Gradle conventions, dependency management, and testing best practices.

MCP server that orchestrates language servers into agent-native workflows. 65 tools, 30 CI-verified languages.

Fast, lightweight, local-first Windows launcher to search apps, files, content, OCR text, clipboard history, browser history, Git activity, settings, commands, and AI agents from one shortcut.

The open source taint analysis tool for the AI era. The analyzer you can customize and self-host, built so AI agents drive your security analysis without burning tokens on every scan. AI-ready open source alternative to Semgrep Pro and CodeQL.

Official Webflow Agent Skills

Agent-friendly GPU profile-query CLI

Build your go-to-market engine with coding agents instead of a $2K/mo tool stack. Interactive onboarding, 10 educational chapters, GTM-OS skeleton, templates, and Python scripts.

Pi's Heartbeat - Schedule recurring and one-shot main agent or background prompts with cron-like functionality

A curated list of awesome Skills, resources, and tools for customizing coding agent workflows.

31 natural-language prompts that prove one primary agent can stand up, drive, and tear down a whole fleet of AI coding agents and terminals inside cmux.

Self-hosted terminal browser multiplexer for persistent shells and coding agents on Windows, macOS, and Linux.

面向招投标场景的本地化 RAG 标书解析、资质匹配与红线提醒助手

High-performance embedded off-heap storage engine for Java, built on memory-mapped files. Map/List/Set/Queue beyond the JVM heap, plus an AI memory layer with hybrid vector + BM25 search.