Custom agents

This project is a Local RAG system built for the NYU Machine Learning course.

soccer video detection ai agent using YOLO, HRNET, OSNet model for team reidentifiaction, field keypoint detection, ball detection, ROI detection

Remote control for your local Cursor AI agent — monitor sessions, approve steps, and send tasks from your phone or Telegram while Cursor runs on your machine.

Agents for Kubesphere DevOps

The open source coding agent.

Laravel APM agent for Elastic v2 intake API

Framework for building data agent workflows

Restrict Django sessions to IP and/or user agent.

Memory and Context Orchestration for Coding Agents

Generates polyfills based on user agent strings

Code for "Planning Goals for Exploration", ICLR2023 Spotlight. An unsupervised RL agent for hard exploration tasks.

Friday is an Assistant BOT Built on Wechaty for Serving our Community

A Telegram bot written in Python to play the game BlackJack alone or with your friends

AI agent with RAG+ReAct on Indian Constitution & BNS

news collection--classification--storage--push

AI-Exchange Protocol (AIXP): A Communication Standard for Artificial Intelligence Agents

Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning (EMNLP2026)

Agent Waystation · Agent 驿站 — a stopover for AI agents, builders, tools, and field reports

A solution for Dynamic Spectrum Management in Mission-Critical UAV Networks using Team Q learning as a Multi-Agent Reinforcement Learning Approach

Code for Emergent Translation in Multi-Agent Communication

Dynamic decentralized task allocation algorithms for multi-agent systems using auctions and machine learning

Official implementation of MATPO: Multi-Agent Tool-Integrated Policy Optimization.

An open-source AI copilot built specifically for the messy, multi-stack reality of modern robotics development.

Socratic is a framework for building reliable vertical AI agents by letting human experts teach agents interactively, turning tacit domain knowledge into a continuously improving knowledge base.

A curated list of awesome resources for Google's Agent Development Kit (ADK)

🧨 TradeTrap: Are LLM-based Trading Agents Truly Reliable and Faithful?

A personalized web workbench for Hermes Agent with setup packs, artifacts, memory-aware onboarding, and local+remote model workflows.

LLM agent solving traces, leaderboards, and benchmark results across security CTF and hacking platforms

A powerful Obsidian plugin that integrates with Letta to provide a stateful AI agent that knows your vault contents and remembers your conversations

Serve markdown versions of your HTML pages to AI agents and bots

AI Play Minecraft

Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs

A project showcasing how to leverage AI coding assistants (Cursor, Claude Code, etc.) for accelerated NVIDIA DeepStream SDK application development using a curated agentic skill and structured prompts.

An AI coding agent that runs as a standalone desktop app for Windows, macOS and Linux, and as a VS Code extension. Chat with Claude, GPT and other models, approve diffs, rewind checkpoints, and use persistent memory, subagents, teams and MCP, powered by the Pi agent runtime.

项目描述：构建⼀个能够⾃动撰写多模态呈现、具备专业性和深度、数据融合与事实溯源、规范 有逻辑的各类⾦融研报的智能 Agent 系统。 主要负责：根据赛题思路，对目标公司生成金融研报，通过 LLM 获取目标公司的竞争对手，用 akshare 获取数 据源的的三大报表数据，通过 duckduckgo 获取公司信息、行业信息、股份信息等，通过设计数据分析师智能 体，包含三个动作代码生成和执行、收集图片、完成动作，用 pyplot 生成金融报表。最后通过 word 形式文件 展示多模态研报。包括目标公司财务状况、关键财富指标分析、财务问题等，在天池大赛 A 榜单获得前百。

Voice-powered AI assistant platform — connect any LLM, any TTS, with a live web canvas, music generation, and agent orchestration using openclaw. Install: npx openvoiceui setup

The execution contract for AI agents. Execution governance for software repositories, shared with humans and CI.

Local-first AI memory — runs offline on any machine with 8 GB+ RAM (SBC, mini PC, laptop, workstation). Zero-loss verbatim archive, knowledge graph, hybrid retrieval. Framework-agnostic, no cloud.

AI agent skills for Sealos — deploy any project, provision databases, object storage & more with one command. Works with Claude Code, Gemini CLI, Codex.

CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable.

A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with async tool calls and bidirectional recursive spawn.

Turn your team's AI coding sessions, GitHub code, and docs into one shared, searchable memory — a self-hosted git truth store you query right from your editor over MCP.

A Git-based package manager designed for AI-assisted development, similar to npm but supporting skills, agents, commands, hooks, and any AI resource types.

A unified anti-dead-loop toolkit for LLM agents — loop detection, budget ceiling, state stasis guard, and circuit breaker in one library.

a local-first workflow manager for AI coding agents

A structured audit playbook for LLM coding agents. One command runs 27 modules across security, dependencies, devops, architecture, performance, compliance, and UX, producing per-module findings, a risk register, and a prioritized remediation plan.

Generate AI-powered videos and images from the terminal using the `agent-media` CLI.

A repository for agentic world building to roleplay in. A world seed template is used for the pipeline and the output is a Silly Tavern ready character cards, world info and system settings.

MyKG Knowledge Graph Engine: Turn raw files into knowledge graphs with induced ontology

workbuddy/ codex skill , 一个让 AI 帮你 5 分钟深度调研任意中国城市周末玩法的agent skill, 寻找精神旷野：户外消费告别长途远行、装备内卷，转向日常低成本微沉浸；菜市场、城市老街成为年轻人精神微旅行目的地，CityWalk 演化成主题探索路线，日常场景即可实现情绪解压。

All-in-one AI 研究工作台：把 Codex / Claude Code / Cursor 变成有长期记忆的研究系统。wiki 摄入、研究闭环、快速筛选、假设追踪、播客、日报六大能力，零 API key 可跑基座。

Adaptive web research MCP skill for AI coding agents. pip install webify-mcp

Gemma models running 100% local on an 8 GB Jetson Orin Nano: voice assistants with RAG, multi-agent NPCs, live EN-JA translation, and a Gemma 4 voice + vision agent that decides when to look through the webcam. The demos from the Gemma 2 launch at Google Tokyo.

Indexed knowledge bases with command-line tools for agents.

CUA-Gym-Hub: mock web apps as reproducible RL training environments for computer-use agents

An AI driven debugging assistant specially designed for x32/x64dbg, it helps to double the efficiency of reverse engineering, vulnerability mining, and malware analysis, making it your intelligent copilot.

Practical, portable skills for agentic coding workflows — clearer diagrams, checked claims, safer GitHub releases, natural EN↔KO writing.

Real-time event-driven orchestration of dynamic resource allocation yields a highly scalable, intelligent, and autonomous enterprise agent broker.

A RAG system for Agent

Open-source GraphRAG domain knowledge layer: LLMs continuously distill scattered skill docs into a queryable, evolvable, human-editable two-layer knowledge graph — versioned, hot-swapped and rolled back via a GitOps pipeline like software releases, and served to AI agents over MCP. RAG, but with relational structure.

Comparison of memory systems for agents

pi-desktop Minimalist desktop GUI for the Pi coding agent — the same engine as the Pi CLI, in a clean visual interface. Multi-session chat, visual tool approvals, and custom themes.

Your feedback layer for AI collaboration. Point at anything on your Mac - text, screenshots, web elements, or voice - and your agent reads and resolves your comments over MCP.

Personal portfolio showcasing my projects, skills, and experience as a Fullstack Developer.

Technical books and research dossiers about the infrastructure that gives AI agents private workspaces, controlled execution, durable state, and safe publication.

A stock picking tool that has 21 legendary investors like Warren Buffet, Peter Lynch, Michael Burry etc debate every stock pick and show you exactly where they agree, and where they don't. The second opinion your investment portfolio actually needs. No API key needed

全网首个中文字体专业知识包：可商用中文字体库（授权三级分类）、场景×气质选字矩阵、中英混排与排版规则。让 AI 选中文设计字体不再甩给你一堆 Inter / Chinese font selection agent skill: license-safe free commercial CJK fonts, scene-based selection matrix, CJK-Latin pairing rules. Works with Claude Code / Cursor / Kimi / Codex.

Fast, accurate Android decompilation for humans and AI agents.

Code for Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements

A terminal-native multi-agent coding agent with parallel subagents, persistent memory, Tree-sitter code intelligence, repository-aware reasoning, web research, and built-in verification.

Use Cursor CCE and bounded Cursor Agent execution from Codex, Claude Code, Grok Build, or Pi, with an independent Grok Build Supervisor.

Agent workflow for deadline-bound execution with evidence gates

面向 VC/PE 投资人的 AI 调研工作体系：7 步流水线 × 三方案（A 企业 / B 行业技术 / C 混合）+ 9 项执行规范 + 8 套模板 + 工具脚本 + 5 个真实案例与长期记忆库，让「看公司、看行业、看赛道」从凭经验变成按流程

Shared inboxes for human + AI teams Route the work, automate it, integrate it with anything, and hand it to a person or an AI teammate who sees it through. Refined over 24 years, with a built-in harness for AI teammates -- each with its own mix of knowledge, skills, and tools.

Design skills for coding agents.

Local-first memory engine for coding agents (Claude Code/Cursor/Codex): SQLite+FTS5 retrieval, versioned bi-temporal memories, full-session capture, zero dependencies, MCP server

Real-time monitor for Claude Code CLI sessions. Desktop app with a menu bar tray, built with Electron, React and TypeScript.

MCP server and CLI that crawls websites for AI agents: finds the answer page 2x more often than Crawl4AI, 10x cheaper per answer than letting Claude crawl.

RTX 5070 Ti Laptop 12GB 跑 Qwen3.8-27B：NInfer + KVMem、256K 逻辑上下文、RAM KV、MTP、快速缓存续接与 dsh 本地 Agent / 搜索 / 浏览器。含源码、Windows 部署及实测。

Sandbox for AI coding agents (Claude Code, opencode, pi): runs each project in an isolated microVM with host-side secret injection. Linux/KVM & macOS.

Fault-injection toolkit for testing the resilience of LLM calls and agentic workflows.

SAMS - Scalable Agentic Market Simulator, a next gen AI finance automation paradigm, suitable for high frequency scenario while built for continuous learning and more sophisticated market simulation.

Build and deploy PolyAI voice and chat agents from your terminal. Sign up free at studio.poly.ai, then pip install polyai-adk.

AI Agent Gateway - an open-source gateway that secures, governs and observes AI agents' MCP tool calls and LLM traffic

Contextual Memory Virtualisation (CMV): git-like snapshots, branching and trimming for AI coding agent context. Demonstrated with Claude Code.

Multi-platform IM channel bridge with unified message abstraction for AI agents and bots

Connect your people, tools and data with your custom AI agents. ZAQ is an open source collaborative and sovereign agentic operating system

Understand Your Agents. Turn agent logs into interactive maps and stories. Explore decisions, replay the work, and get answers linked to the original evidence. For coding, research, and creative workflows.

Grok Bot companion for T3 Code.

MCP server for controlling TouchDesigner from AI coding agents

Disposable Linux microVMs on your own machine, for AI agents.

The unified API for autonomous companies. Ship a real business — website, backend, payments — from one terminal.

A lightweight AI browser automation agent framework

[ISPRS 2023]Official PyTorch Implementation of "GATraj: A Graph- and Attention-based Multi-Agent Trajectory Prediction Model"

the claude agents/commands I'm using

Verified agent runtime for Kimi Code. Stable daily-use core with alpha orchestration surfaces; release-gated and evidence-gated workflows. | Kimi Code向け検証済みエージェント実行基盤。日常利用コアは安定、オーケストレーション面はalpha。

The Arknights Theme QQ Group Chatbot Based on Angelina Frame

GPT2⚡NCNN⚡中文对话⚡x86⚡Android

A dysfunctional programmer's guide to making things in Hoon.