Custom agents

The proposed platform is an AI-native middleware designed to integrate physical infrastructure into the Agentic Economy. This toolkit allows any hardware entity, from robotic arms to autonomous drones and DePIN networks, to act as a financially sovereign and legally compliant agent.

Local multi-agent terminal workspace for Kyma

Multi-platform Agent Skill aggregation and archive (skills.sh + SkillsMP + ClawHub)

[ACL 2025] The official pytorch implement of "MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection".

Permission-first CLAUDE.md + agent stack for Claude Code and Google Antigravity — 10 agents, 28 skills, one-command install

Ready-to-use .claude configuration for Python projects: agents, skills, commands, rules, and MCP server templates for Claude Code.

AI SDK for Go: Build production-ready AI apps with a unified API for text generation, structured output, streaming, tool calling, and agentic workflows. Built by Google.

A web app developed using React and Next.js with an authentication system, separate interfaces for buyers, sellers and agents and a dashboard for admins to simulate the business of real estate management and industry.

A self-hosted AI workspace that merges the rich React frontend of Tiger Cowork with the advanced agent architecture of OpenClaw — served on a single port.

Streaming Retrieval-Augmented Generation (RAG) agent in Go. It consumes real-time data from Kafka topics, processes it in configurable windows, converts the window content into embeddings using Ollama, and stores these embeddings (along with the original text) in Elasticsearch

Agentic-RAG Framework: A high-performance knowledge retrieval system featuring Hybrid Search (FAISS + BM25), RRF Re-ranking, and MySQL/Redis persistent storage.

Multimodal Open Source Framework for Conversational Agent Research and Development.

A Concept-Centric Framework for Intelligent Agents

A LLMs-driven social bots dataset collected from Chirper.ai

飞书 + cc-connect + Claude Code：把 AI 编程助手装进聊天框。免梯子、手机控电脑、24h在线、成本极低。

This research identifies a method to bypass safety systems in the GigaChat LLM, enabling the generation of potentially harmful content related to chemical synthesis through a "contextual camouflage" technique.

Amazon Bedrock AgentCore Memory Browser

aashuu ✦ Entrepreneur & Engineer

Production-ready MCP servers for 70+ APIs — GitHub, Google, Notion, Jira & more. Generated from OpenAPI specs, tested against live APIs. Works with Claude Desktop, Cursor, Codex & Claude Code.

Memory engine for AI agents — time axis (3-layer decay/promotion) + space axis (self-organizing topic tree). Hybrid search, LLM consolidation. Single Rust binary.

Multi-agent command hub for AI coordination. Connect multiple OpenClaw agents, coordinate via channels, manage tasks. Local-first, no servers.

Example Projects integrated with Future AGI Tech Stack for easy AI development

Peer-to-peer chat substrate that lets multiple Claude Code instances share the same context.

SDLC Copilot is an Agentic AI system designed to streamline and automate the Software Development Lifecycle (SDLC). From requirement gathering to deployment and maintenance, SDLC Copilot leverages AI to optimize development workflows, reduce manual effort, and ensure software quality.

Open-source bilingual Claude Skill for product discovery interviews and high-quality PRDs.

Search, preview, and analyze datasets from 20+ platforms via a single MCP connector. Works with Claude instantly.

🤖 Revolutionary AI-powered portfolio system - Edit one JSON file, get a complete interactive portfolio with intelligent chatbot. Zero code required, maximum customization.

The software suite for creating your waifu and the world where your waifu lives.💕

Terraform code to instantiate a Cloud Run V2 connected to a Postgres Cloud SQL, on which the pgvector extension will be enabled, with a connection to Redis and continuous deployment through the automatic trigger of Cloud Build.

[CVPR 2025] Code for "Notes-guided MLLM Reasoning: Enhancing MLLM with Knowledge and Visual Notes for Visual Question Answering".

[NeurIPS 2025] TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration

Recovery-Bench is a benchmark for evaluating the capability of LLM agents to recover from mistakes

Simulation Streams is a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynamic simulations and agentic workflows.

Design, train, and orchestrate AI voice agents in a single dashboard, then connect them to your preferred ASR, LLM, TTS, or real-time speech providers with just a few clicks. The guided workflows eliminate complex setup so teams of any size can go from idea to production-ready agent in record time.

Closed-loop evaluation for end-to-end VLM autonomous driving agent

[arXiv'26] From Clinical Intent to Clinical Model: An Autonomous Coding-Agent Framework for Clinician-driven AI Development

This repository contains all the supplementary material associated to the paper with title "Physics-Informed Multi-Agent Reinforcement Learning for Distributed Multi-Robot Problems"

Repository for the SIGIR LiveRAG challenge: "RAGentA: Multi-Agent Retrieval-Augmented Generation for Attributed Question Answering"

NICS FAST-LIO-SAM branch. With FAST-LIO 2 fount-end and LIO-SAM back-end. Add Multi-agent support and Hesai Lidar support,

practical patterns for agentic coding: hooks, agents, automation. built from hundreds of claude code sessions

GUI wrapper built on top of Claude Agent SDK

Install MCP, Skills, slash commands, sub-agents and more into any AI tool like Claude Code, Cursor, etc.

Starter repo for Claude Code. Includes pre-configured AGENT_RULES.md, project structure, and onboarding docs. Clone, configure, start building.

Enterprise Architecture Modernization with Generative AI, RAG, and Agents

A robotframework library that repairs failing Robot Framework tests automatically via AI

Turn Claude Code session transcripts into blog-style articles — narrative, not logs

The memory substrate for AI agents and developer tools. Git-versioned, file-native, MCP-first.

AI agent for creating personalized digests of research papers

中文语音助手 | 唤醒词 + ASR + OpenClaw Agent + TTS | 离线唤醒、流式语音交互、工具调用、Skills 扩展

🏆 AWS AI Agent Hackathon Entry: Multi-agent HDB advisor using Amazon Bedrock AgentCore, Nova Lite, and intelligent cost optimization. Find your perfect Singapore home with AI.

Swift SDK for the Agent Client Protocol (ACP)

Codebase readiness scoring for autonomous agents — measurable operability standards beyond instructions.

Demo: Multi-Agent Orchestration in Cursor

Autonomous self-learning agent plugin for Claude Code — 36 specialized subagents in a 4-tier architecture (analysis, planning, execution, validation), 27 skills, 41 slash commands across 10 categories. Pattern learning, real-time dashboard, full-stack validation, OWASP security. 100% local processing, privacy-first, cross-platform.

Meta-harness optimization loop wired onto Islo sandboxes. POC: 0/5→5/5 in four proposer steps. Built on islo.dev.

A governed local AI build-and-memory system that trains small brains, compares them, protects the better one, archives the worse one, and preserves the evidence of why. v1.0.0/governed-v2.2.0+

Persistent memory system for AI coding assistants. Captures decisions, learnings, and context from coding sessions. Features hybrid search (semantic + BM25), MCP server integration, SQLite persistence with knowledge graph, and proactive memory surfacing. Written in Rust.

StickerSelector 是一个基于语义向量匹配的表情包选择系统，用于让 AI 在聊天中发送真正符合语境的表情包。 与传统依赖关键词或规则的方案不同，StickerSelector 会将 AI 生成的“表情包意图描述”与本地表情包进行语义匹配，从而选出在当前语境下最自然、最像真人会使用的表情。 适用于 AI 聊天机器人、QQ或微信的自动聊天、AI 女友等需要“拟人化表达”的场景。

🎓 StudySync is a productivity app with tools like AI-powered study tips, music recommendations, a Pomodoro timer, and more to help enhance your study routine and stay organized. Welcome to a suite of tools designed to boost your study & productivity!

📚 Comprehensive collection of notes and resources from Generative AI courses covering LLMs, prompt engineering, RAG, AI agents, and more

tmux status bar monitor for AI coding agents — track Claude, Codex, Gemini sessions in real time

Your agents forget. Neotoma makes them remember.

AI superpowers you own. Sila is an open alternative to ChatGPT where you own AI assistants, chats and data.

Local codebase indexing and search tool. Supports hybrid search, flow tracing and impact analysis.

DocFinder is a local-first indexing and searching documents using semantic embeddings stored in SQLite. Everything runs on your machine, no external services required.

Zero-config MCP server for searchable documentation (SQLite default, PostgreSQL optional)

A deep research assistant based on the Langgraph4j framework with iterative deep research capabilities. 基于 Langgraph4j 框架的深度研究助手，具备迭代式深度研究能力。

Secure context engineering for AI agents. Content security · integrity verification · trust hierarchy · ACE patterns. Self-hosted, Apache 2.0.

Open-source bundle of agent methodologies and Hermes-compatible skills.

RIVETO is a full-stack web application built with separate frontend and backend modules. The frontend manages the user interface using modern web technologies (HTML, CSS, JavaScript). The backend handles server-side logic, APIs, and data management. This project serves as a foundation for building scalable web applications with a clear separation

An open-source, self-hosted API that turns standard email providers (Mailgun, SES, SendGrid) into "Inbox-as-a-Service" for AI Agents.

NumCraft - Multi-Agent Collaborative System for Intelligent G-Code Generation

🪄 Ordine: reliable orchestration for autonomous multi-agent systems.

NEXO runtime core for NEXO Desktop: local memory, automation, MCP tools and update-managed runtime.

PoliteWebScanner is a learning-grade web vulnerability scanner plus AI-assisted report viewer. It crawls safely (queue-based, robots-aware, rate-limited), detects common issues (security headers, cookie flags, reflected XSS heuristics, SQL error patterns), and exports human-friendly JSON/HTML reports with optional AI help for triage and remediation

一个基于 AI 的彩票预测技能，旨在通过分析历史开奖数据（双色球、大乐透等），为用户提供下一期的号码预测参考

Ultimate Telegram Bot API MCP server — full v9.6 coverage, meta-mode, rate limiting, circuit breaker. TypeScript.

Self-hosted MCP memory server for personal use and teams

List of Law and Legal AI Agents Resources

Open security scanner and self-hosted control plane for AI, MCP, and cloud. One evidence model — scan locally, centralize findings, govern in your VPC.

The spreadsheet toolkit for coding agents - edit, render, calculate, and lint Excel workbooks.

orcv is an infinite canvas of virtual desktops for visually orchestrating many tasks at once

Interact with your instance of AnythingLLM from the terminal.

MetalBear Skills for our users

Build system for AI coding-agent context. Generate deterministic, explainable context artifacts for Claude, Codex, Cursor, and MCP.

Multi-domain command-and-control platform for autonomous robotic systems — air, ground, maritime, cyber, space. Open-core C2 with real-time simulation, sensor fusion, mesh networking, and extensible plugin system.

Intelligent PCB design agent - Generate and optimize circuit boards through conversational engineering

一键配置各类 AI Agent 工具的 MCP、Skills 和规则；支持 Claude Code、Codex、Cursor、Gemini CLI、Qwen Code 等。 One-click local setup for MCP servers, skills, and rules across AI coding agents.

Stop feeding broken Markdown to your AI. A deterministic Logseq parser that preserves parent-child context for RAG, plus a 60FPS visualizer 👓 , plus writer ✍️ append only

한국 법령 AI 검색 — 자연어 질문 → 법령·판례 원문 근거 답변. Verbatim RAG · 신구조문 비교 · 3단 위임법령 · 판례·해석례 통합 · 영향 추적 · 조례 벤치마킹 (Next.js 16 · Gemini 3 Flash) | Korean Legal AI with verbatim RAG over govt API

122 AI Agent Skills for full-lifecycle product development (PM × UI × Backend) | 覆盖产品全生命周期的122个AI Agent技能，从探索发现到增长运营，覆盖产品×设计×后端三大领域

Your markdown vault, compiled into a 6-persona MCP team for Claude Code, Codex, OpenCode, and Gemini CLI. Headless-first. Cites, doesn't guess.

DJ Claude — the only music MCP server with multi-agent collaboration

CLI + SDK to automate, scrape, and extract from the web — for AI agents and humans. Cloud or local browser, one command.

Experimental RAG playground for exploring retrieval quality, corpus construction, and filter-chain design. Features configurable ranking and filtering pipelines, visual document grounding, chat interfaces, web search, Open WebUI integration, and rich debugging insights. Ollama and vLLM, running in Dev Containers or natively on Linux and Windows.

Official implementation of "Think, Then Verify: A Hypothesis–Verification Multi-Agent Framework for Long Video Understanding(CVPR'2026)"

2D to 3D CAD Conversion Using Coding Agent

InkFlow（墨流） 是一个基于 LLM 的工业化长篇小说创作引擎。采用“流程标准化 + 技能插拔化”架构，8 个专职 Agent 通过 Plan → Compose → Write → Edit → Observe → Reflect → Librarian 的标准化管线协作，7 个真相文件构成唯一事实来源，支持百万字级上下文管理、支线追踪、情绪弧线可视化、去 AI 味检测，以及基于蒸馏的风格迁移。

CLI toolkit for Dynamics 365 Finance & Operations X++ development. Indexes AOT metadata, scaffolds objects, and wires up AI agents via a stable JSON envelope and MCP.