Code agents

Turn token activity into compute. A compute-access protocol designed for Robinhood Chain: protocol fees fund GPU capacity for token holders.

Zoomies is a lightweight, self-hosted GitHub Actions runner fleet controller. Ephemeral runners by default, GitHub App auth, webhook-driven autoscaling, multi-host agents, a polished live web UI, and a one-line interactive installer. Single Go binary, SQLite, no Kubernetes.

Agent skills for academic figures and editable slide decks in Claude Code and Codex.

The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.

PDEAgentBench: An automated benchmark framework for evaluating Code Agents on optimizing scientific PDE solvers.

MCP server giving AI agents full access to Julia's runtime via a live Gate — code execution, introspection, debugging, testing, and semantic search

AI skills that keep your code honest, your secrets unleaked, and your repo from rotting. Built for people who ship real things with AI. Type /vibesubin and let your assistant do the boring discipline for you.

The Qude Framework open-source code allows users to create AI agents directly in their CLI, with Qude acting as a co-pilot to help build them. The Qude API enables interaction with the AI agents created using the Qude Framework's open-source code.

Arka - Enterprise MCP Gateway

Security and compliance proxy for LLM APIs

集成了众多功能的API节点，只需要一个API-key即可以调用全网的API接口能力，低配电脑也能顺利运行

A LangGraph-powered multi-agent deep research system featuring task planning, human-in-the-loop review, multi-source retrieval, evidence-grounded report generation, full tracing and reproducible evaluation.

AI-native database client powered by natural-language queries

Synthetic datasets, experiment protocols, and evaluation code for "Governed Memory: A Production Architecture for Multi-Agent Workflows"

Custom C# chat bot for Twitch TV

A BotUI web app connected to DialogFlow

Sphinx.bot is a platform for collecting data leaks. All information recorded here is publicly available on the web. Any malicious use of this information is strictly prohibited.

Py-iMessenger is a chatbot that works with iMessage to execute commands using text messages.

通过代理访问openai api服务。

In this project, we used Langchain to create a ChatGPT for your PDF using Streamlit. We built an application that allows you to ask questions about a PDF document and get answers directly from an LLM (Large Language Model), like OpenAI's ChatGPT.

Text to SQL generator GPT-3 (Python + Vue) and also AI chart generator!

Altered state slash commands for Claude Code. 12 substance-themed personality modes that change how Claude approaches your tasks.

Testing speed and accuracy of RAG with, and without Cross Encoder Reranker.

Extract CodeRabbit GitHub PR reviews for AI coding agent consumption

Agentic Coding Tools

Demo for Deepgram Voice Agent API

Kubernetes Helm Chart for VSTS agent pool

for Runway coding agent skills

SQL Agent is a missing ORM for Node.js + Total.js

Backblaze.Agent is a high-performance .NET Core implementation of the Backblaze B2 Cloud Storage API.

Swift symbol lookup CLI powered by SourceKit-LSP, tuned for coding agents

Node-RED Agent for the MindConnect API (community driven project)

Stock trading strategies play a critical role in investment. However, it is challenging to design a profitable strategy in a complex and dynamic stock market. In this paper, we propose a deep ensemble reinforcement learning scheme that automatically learns a stock trading strategy by maximizing investment return. We train a deep reinforcement learning agent and obtain an ensemble trading strategy using the three actor-critic based algorithms: Proximal Policy Optimization (PPO), Advantage Actor Critic (A2C), and Deep Deterministic Policy Gradient (DDPG). The ensemble strategy inherits and integrates the best features of the three algorithms, thereby robustly adjusting to different market conditions. In order to avoid the large memory consumption in training networks with continuous action space, we employ a load-on-demand approach for processing very large data. We test our algorithms on the 30 Dow Jones stocks which have adequate liquidity. The performance of the trading agent with different reinforcement learning algorithms is evaluated and compared with both the Dow Jones Industrial Average index and the traditional min-variance portfolio allocation strategy. The proposed deep ensemble scheme is shown to outperform the three individual algorithms and the two baselines in terms of the risk-adjusted return measured by the Sharpe ratio.

File leasing for AI agent teams. One MCP server. Any IDE. Zero merge conflicts.

Use LLMs to perform automatic code reviews.

Archived. Earlier Bonnard product. Current: bonnard.dev / @bonnard/mcp-charts

OpenAI API interface for Grasshopper (Rhinoceros 8)

An integrated AI agent (currently Claude Code) plugin for Obsidian.

Using OpenAI or other LLMs via Langchain to connect that intelligence to Zapier which can access virtually every app, you might want to automate

A website that generates LaTeX code for a professional resume. Equipped with an AI agent to enhance the resume's content.

Learning to Ground Multi-Agent Communication with Autoencoders [NeurIPS 2021]

Natural language test scenario runner agent with MCP tools

A java agent for tracing which can be configured via simple text file and instruments the code without rebuilding the project.

Unity project showcasing A* pathfinding, fully jobified & burst compiled. It also contains examples of RaycastCommand and BoxcastCommand that are used to build the grid, as well as another example of the usage of IJobParallelForTransform, used to move the agents.

Cognitive engine for AI agents — semantic memory, observations, embeddings, dream consolidation. Cloud Run service + MCP tools.

Loop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi. MIT community plugin.

A comprehensive platform for managing, testing, and leveraging Ollama AI models with advanced features for customization, workflow automation, and collaborative development.

#decompiled by PDM31 import os, sys print '\x1b[1;32mSudah punya ID dan Password nya?' print '\x1b[1;32mSilahkan Login ' import os, sys def wa(): os.system('xdg-open https://api.whatsapp.com/send?phone=6281291977644&text=Assalamualaikum') def restart(): ngulang = sys.executable os.execl(ngulang, ngulang, *sys.argv) user = raw_input('ID: ') import getpass sandi = raw_input('Password: ') if sandi == 'indoxploit' and user == 'Borot': print 'Anda Telah Login' sys.exit else: print 'Login GAGAL, Silahkan hubungi ADMIN' wa() restart() import os, sys, time, datetime, random, hashlib, re, threading, json, getpass, urllib from multiprocessing.pool import ThreadPool try: import mechanize except ImportError: os.system('pip2 install mechanize') else: try: import requests except ImportError: os.system('pip2 install requests') from requests.exceptions import ConnectionError from mechanize import Browser reload(sys) sys.setdefaultencoding('utf8') br = mechanize.Browser() br.set_handle_robots(False) br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1) br.addheaders = [('User-Agent', 'Opera/9.80 (Android; Opera Mini/32.0.2254/85. U; id) Presto/2.12.423 Version/12.16')] def keluar(): print '\x1b[1;91m[!] Keluar' os.sys.exit() def jalan(z): for e in z + '\n': sys.stdout.write(e) sys.stdout.flush() time.sleep(0.1) logo = '\x1b[1;92m\n\xe2\x95\x94\xe2\x95\xa6\xe2\x95\x97\xe2\x94\x8c\xe2\x94\x80\xe2\x94\x90\xe2\x94\xac\xe2\x94\x80\xe2\x94\x90\xe2\x94\xac\xe2\x94\x8c\xe2\x94\x80 \xe2\x95\x94\xe2\x95\x90\xe2\x95\x97\xe2\x95\x94\xe2\x95\x97 \n \xe2\x95\x91\xe2\x95\x91\xe2\x94\x9c\xe2\x94\x80\xe2\x94\xa4\xe2\x94\x9c\xe2\x94\xac\xe2\x94\x98\xe2\x94\x9c\xe2\x94\xb4\xe2\x94\x90\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x95\xa0\xe2\x95\xa3 \xe2\x95\xa0\xe2\x95\xa9\xe2\x95\x97\n\xe2\x95\x90\xe2\x95\xa9\xe2\x95\x9d\xe2\x94\xb4 \xe2\x94\xb4\xe2\x94\xb4\xe2\x94\x94\xe2\x

Purpose-built security agent for hosted runners

AgentX - Agent Extension: MCP Servers, Agent Skills and Plugins Manager

Ready-to-use agent that can interact directly with any tool or native endpoint, in less than 5 lines of code

Offline and security-first tool for syncing and managing agent skills

oSIP is a LGPL implementation of SIP. It's stable, portable, flexible and compliant! -may be more-! It is used mostly with eXosip2 stack (GPL) which provides simpler API for User-Agent implementation.

Multi-agent system (MAS) hijacking demos

This is the official code base of AgentNetTool in OpenCUA. Website: https://opencua.xlang.ai/

Improve safety, security, and privacy of AI systems at build, deploy and run stages.

Most WhatsApp gateways stop at "send a message." **NOXUS AI Open WhatsApp** goes further: it ships a **grounded AI agent** that answers customers from your own knowledge — and can call your live APIs by slash command before replying. You bring the data and the APIs. NOXUS does the WhatsApp, the AI, and the operations console.

A browser-based UI for Claude Code — chat, run workflows, manage MCP servers, track costs, and orchestrate autonomous agents from a local web interface. Installable as a PWA.

Official Code Release for "Training a Generally Curious Agent"

Background coding agent — polls Linear, runs DOT graph workflows, ships PRs

This is a visual editor for langgraph workflow. It helps to quickly design and debug the workflow from scratch.

InstAgent - ⚙️ Instantly transform natural language descriptions into powerful multi-agent systems 🤖 — define roles 🎭, equip them with the right tools 🧰, and generate ready-to-run code 💻 — all in one seamless flow, guided by a single instruction 🚀.

In this tutorial we will learn how to create a powerful AI chatbot using LangGraph, FastAPI, and Streamlit.Learn to define a FastAPI backend endpoint for processing requests, integrate LangGraph agents with dynamic model selection, and design an intuitive Streamlit UI for seamless user interaction.

The Generative AI Toolkit is a lightweight library for building, testing and evaluating AI agents in Python, using any of the LLMs supported by the Amazon Bedrock Converse API.

Exercises and resources for the AI Coding Summit 2026 workshop: Advanced Claude Code Techniques for 2026. A hands-on two-hour workshop on the PIV Loop (Plan, Implement, Validate) for agentic coding.

MCP server for the X (Twitter) API -- give AI agents the ability to post, search, read, and engage on X

An agentic AI-powered Figma plugin that lets you chat with your canvas, inspect and manipulate nodes, and execute Figma Plugin API code.

[AAAI 2026] Data and Code for Paper IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks

A light-weight and straightforward system for spec-driven development with Claude Code or OpenAI Codex. Written in Rust 🦀

A terminal coding agent, and a Python SDK for embedding on-device models in your own apps.

The control layer for AI agents. 1,200+ rules, 12 domains, 10 frameworks, 4,000+ adversarial payloads. Discover. Assess. Test. Monitor. Comply.

Headless, declarative multi-agent orchestration framework with a domain-agnostic signal bus, workflow engine with Postgres persistence, and configurable agent runtime (ships code review domain).

Automated workflows for OpenAI Codex. Features spec-driven development for new features: Product Requirement → Design → Development Plan → Implementation.

Dragon Brain — persistent long-term memory for AI agents via MCP (Model Context Protocol). Knowledge graph (FalkorDB) + vector search (Qdrant) + CUDA GPU embeddings. Works with Claude, Gemini CLI, Cursor, Windsurf, VS Code Copilot. 30 tools, 1121 tests.

Agentic DevOps is a powerful, interactive Command-Line Interface (CLI) designed to streamline and automate the development, deployment, and management of applications on various Cloud Providers.

Your coding agent spends 90% of its tokens finding code, not writing it. Reduce your token usage by 50x with CodeDrift !

AI agent that implements your specs, opens PRs, and reviews code overnight. Queue GitHub issues or PRDs, wake up to pull requests.

A compact operating covenant for AI agents.

Telegram Bot API wrapper for Node.js written in TypeScript

A computer for your agent - sandboxed code execution for AI agents

A unified, AI agent-friendly SDK for the Unitree Go2W quadruped robot that enables seamless integration of perception, planning, and control through a single API interface.

Fast Delphi/Pascal symbol search for AI coding agents - Now includes Delphi LSP

pi-coding-agent docker compose

Agentic closed loop with async capabilities

a curation of questionably-useful coding agent plugins

credit score for context

Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked wiki with reserch-on-miss, semantic search, and a Wikipedia-style web UI. Knowledge compounds as you work.

The only Java AI framework with a complete Dev → Test → Prod prompt lifecycle, featuring multi-agent orchestration and built-in audio processing

《深入Claude Code》- 基于源码的AI Agent架构设计与工程实践完整指南 (14章)

pytest for AI agents - Autonomous red-teaming, behavioral monitoring & security testing for LLM agents

A Model Context Protocol (MCP) server that provides tools for AI, allowing it to interact with the DataWorks Open API through a standardized interface. This implementation is based on the Aliyun Open API and enables AI agents to perform cloud resources operations seamlessly.

来自银行公开信息的数据。提供 Web 界面、REST API 和 MCP 接口，支持 Agent 和 AI bot 集成使用。

AI coding agent workflow engine for structured task lifecycles.

Compound engineering extension for Pi coding agent workflows.

A concise list of CLI coding tools similar to Claude Code

Hades Agent: An invisible, ultra-fast desktop AI companion built with Electron and Gemini Live API. Featuring real-time voice streaming, a native Stealth Mode (invisible to OBS/screen-shares), lightning-fast web search, plus background memory dreaming.