Custom agents

A human-dopamine-inspired AI agent skill that adapts effort, learns from feedback, and delivers the smallest verified solution.

Myna Recorder — a Windows macro recorder you can read and edit. Image anchors, an auto clicker, an AI assistant that writes macros, Agent mode (computer use, for short jobs) and a screen watchdog.

Open Source Roblox Studio AI Coding Agent Tools 2026: 35 MCP Server Scripts for Safe Edits

Real-Time Synchronized AI Agentic Assistant for Roblox Studio Automation and Scripting 2026

A dishwasher-loading game on a physical simulation of one real machine, built to benchmark language models and playable in a browser. The game inside is called Spotless.

Memora is the Memory-as-a-Service API for AI apps - durable, multi-tenant, versioned memory with vector + graph recall, callable from any MCP-aware agent.

An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine that drafts and verifies its own tokens.

Open-source alternative to Intercom, Fin and Linear. Support, projects, CRM, meetings, and docs in one workspace—with AI agents that use customer history to answer questions, plan work, and follow up.

DeepSeek Harness gate - per-turn persistent-operation counter: remind, instruct the model to stop, then ask for confirmation. Steps aside under sandbox/read-only modes; follows a live permission switch without restart. Verified on real hardware (full -> workspace-write -> read-only -> full). Crafted on an estimated 0.27 USD of model spend.

A TypeScript Agent Framework Driven by Tool Invocation

Govrix Scout — AI Agent Governance Diagnostic Tool (OSS)

A lambda function, a cloudformation template to get it running, and example templates showing how to use a custom resource (calling the lambda) to automatically calculate CIDR ranges for subnets based on the VPC range.

Leopard Chat UI - A Teneo Chat Client based on Vue and Vuetify

A deep learning ChatoBot build with nodejs and tensorflowjs

A PyTorch Implementation of japanese chatbot using BERT and Transformer's decoder

📢 Send system notifications when your AI Coding Agents (CLI-based) requests permissions or completes tasks.

Voice AI agent starter kit with Groq, Llama 4, and (optionally) Twilio

A web dashboard template for running and monitoring your OpenClaw AI agents. The SHAPE of Max HQ, for anyone building their own mission control.

Pocket Flow: A minimalist LLM framework. Let Agents build Agents!

The awesome agents in the era of large language models

LIGHT is a platform for text-situated dialogue research. We originally hosted LIGHT as a live game with dialogue models in a grounded setting. This repo contains all of the code to get the LIGHT game running, as well as reproducible code for the research projects along the way of getting LIGHT to wh

Golang AI agents framework

Data Questionnaire Agent Chatbot

Completely free opensource alternative to manus, openhands and cua

Run a Parallel Autonomous ML Research Organization on your OpenClaw instance.

Persistent, inspectable memory that grows and refines over time. Built on files. Owned by you.

Byte-Vision is a privacy-first document intelligence platform that transforms static documents into an interactive, searchable knowledge base. Built on Elasticsearch with RAG (Retrieval-Augmented Generation) capabilities, it offers document parsing, OCR processing, and a modern UI.

A solution of Multi-Agent Path Finding problem

[ICLR 2024] Trajectory-as-Exemplar Prompting with Memory for Computer Control

AxonFlow: Runtime control layer for production AI

🧬 ManBot — Multi-process AI platform with type-safe IPC and capability graph execution

MCP server to provide Sketch layout information to AI coding agents like Cursor

Multi-agent coordination for Pi - presence, messaging, file reservations

Aries agent test framework, with agent backchannel support

Specification for creating reliable LLM-based conversational agents

A (not too) Evil Chatbot 👹

AI Travel Planner 是一个基于 Spring Boot + Spring AI 的后端与 Vue 3 + Vite 的前端组合项目，面向智能旅游场景，提供 智能行程规划、多模态问答与个性化推荐 能力。 系统集成了 MCP (Model Context Protocol) 工具链，支持从 自然语言理解 → RAG (Retrieval-Augmented Generation) → 多 Agent 协同 → 个性化生成 的完整 AI 应用流程。同时配套 CSV 向量化预处理脚本，实现高效的数据清洗、向量化与检索。

This code accompanies the paper "Scalable Multi-Agent Model-Based Reinforcement Learning".

semantic search for your local files find by meaning, not keywords. 120+ file types, OCR, MCP server for AI agents. 100% private.

🤖 The most comprehensive directory of AI agent frameworks, platforms, tools, and resources - hundreds of curated entries covering open-source, no-code, enterprise, and autonomous solutions. NEW Boilerplates!

Run AI coding agents in Podman or Docker

[AAAI-2026] Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning

HanaVerse is a interactive web UI for chatting with ollama with a lively 2D anime character Hana. Star it on GitHub!

SPARC is an intelligent ROS2 Humble-based pick-and-place robotic system integrating MoveIt, YOLOv8-OBB, and Isaac Sim. It enables real-time object detection, motion planning for Franka Panda and UR5 arms, and natural language control via an Ollama-powered chatbot—making robotic manipulation smart, interactive, and human-friendly.

Official code for the paper: WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

Give AI agents safe access to your database.

EdGameClaw: Convert any learning material into a game-based course — powered by AI.

OpenBrowser is an open-source, AI-native browser built on Chromium — a truly privacy-first alternative to ChatGPT Atlas, Perplexity Comet, and Dia.

Multi-agent codebase audit for Claude Code — 12 specialized personas with epistemic discourse and bias removal for high-fidelity findings

A minimal, composable Go library for building AI agent applications.

Human-driven multi-agent dashboard for Claude Code, Codex, Gemini & OpenCode. Web UI, project wiki, shared content, and MCP-based agent messaging — see every agent, coordinate manually, intervene instantly.

A fast, portable CLI tool for synchronizing AI agent configurations across multiple AI coding assistants using symbolic links.

ATM-Bench: A benchmark for long-term personalized memory QA spanning ~4 years of multimodal data (images, videos, emails). Features referential queries, evidence-grounded answering, and multi-source reasoning. Paper: "According to Me: Long-Term Personalized Referential Memory QA"

Fin-Agent Desktop 是一款基于 Electron + Python 的智能金融助手桌面应用。它集成了强大的 LLM 能力和专业的金融数据分析工具，为您提供自然流畅的金融咨询与分析服务。

A complete skill set for Arco Design, enabling AI agents to accurately use Arco Design when building React applications.

Self-tuning multi-agent AI trading system. 8-source signal fusion, Bull/Bear/Judge debate on Claude Opus 4.7, Kelly + ATR position sizing. Python · Kalshi + Polymarket adapters.

Projx — A CLI tool for scaffolding production-grade projects. Pick your stack (FastAPI, Fastify, React, Flutter), get a fully wired template with auth, database, CI/CD, and E2E tests. Update anytime when templates improve.

Claude Code skill that deploys any web app, API, or agent to the internet — strict pre-deploy audit, preview → prod flow. Bilingual EN/ES. By @soyenriquerocha · Tododeia.

基于 AgentScope Java SDK 的智能代码审查 AI Agent，同时作为 AgentScope 框架学习教程。涵盖 ReAct 模式、工具系统、多 Agent 协作等核心概念。

Effect building blocks for agentic ai

The ATLAS Agent helps answer questions about the MITRE ATLAS Framework by leveraging the ATLAS Knowledge Graph.

Excel VBA integration for VS Code - Tree View / Full Direct VBA Read+Write / LiveShare Compatible / Direct Agentic AI Integrations

A curated collection of ready-to-run automation prompts for real-world workflows.

ATHENA-R1: AI agent for treatment reasoning over a biomedical tool universe

Evidence-grounded veterinary research workbench with local RAG, bounded LLM agents, auditable tool use, citations, abstention, and human review.

Another Agentic Framework

Isometric architecture diagrams as code — text DSL in, design-grade 2.5D SVG out. Agent-first: LLMs can discover, generate, and validate the DSL.

An independent .NET implementation of a Neo4j-backed memory provider for AI agents. Persistent graph-native memory for Microsoft Agent Framework, with GraphRAG interoperability for Neo4j.

Auditable multi-agent A-share factor research, knowledge base, long-only backtesting, AutoCombine and QuantCombine.

一个纯前端的 AI 角色语音聊天网页，5 个模型版本可选（Claude/DeepSeek/Gemini/GPT/Grok）

Six security outcomes an enterprise must achieve to run AI agents, and the controls that evidence them. A draft for public comment.

Agent-driven proactive memory CLI for AI agents — autonomously recall, maintain, and evolve persistent, source-grounded knowledge across sessions.

Autonomous LLM-driven Among Us simulation with memory, social reasoning, pathfinding, sabotage, emergent behavior, and real-time React/PixiJS visualization.

Python SDK for vector search, semantic search, RAG, embeddings, and AI agents on Oracle AI Database

OMP-native pstack and orchestration skills for multi-agent coding workflows

Universal academic document & thesis engine for AI agents and engineers.

🚀 The Complete AI Roadmap (2026) | Free YouTube Courses, Machine Learning, Deep Learning, LLMs, GenAI, RAG, Agents, Projects, Deployment & Career Guide

Retro DOS / Turbo Pascal 7.0 TUI frontend for the Pi coding agent

OpenTechNotes là kho tài liệu IT miễn phí, tổng hợp kiến thức nền tảng và kinh nghiệm thực chiến. Nội dung được tóm gọn, dễ hiểu và cập nhật thường xuyên để hỗ trợ học nhanh – hiểu sâu

Fully Automated Agentic AI Web Agency Built Around Claude Code

Sonetto，LLM Agent。屏幕之内的我会认真记住你的每件小事，陪你写代码、复习考试、聊番剧，偶尔也陪你聊聊日常。你倾注心血在做的事情，我也会认真对待。

A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference

A painted music video for "Functional Emotions", made by Claude Opus 5.5: custom GPU brushstroke renderer, storyboard, and 7 parallel chapter agents.

Self-hosted memory server for AI agents. Share context across Claude Code, Codex, OpenCode, and ChatGPT over MCP.

Less harness. More model. A lightweight local AI assistant. / 极简 harness 的本地全能 AI 助理。

Best Roblox Luau Bug Checker and API Verifier 2026 DevForum MCP Tool

Roblox Studio Live Sync 2026: Open Cloud WebSocket Agent for Real-Time Playtest Hot-Reloading

Find the skills your coding agents load, see which agents can use each one, and count how often you use them

Chat with the videos you've saved: evidence-backed answers with timestamps that jump back to the source. Browser extension + MCP, self-hostable. 和你收藏的视频对话，答案带时间戳，一键回到原视频。

从游戏客户端反推服务端协议并复现可部署服务端 (Agent Skill)。Unity/UE/Cocos, IL2CPP/Lua/JS…

Open source list of roblox skills for AI agents

Agent capabilities, domain knowledge, and execution plugins for Ascend inference engineering (Codex, Claude Code, Kimi Code).

用 Claude Code／Codex 搭配 KiCad 10 設計 PCB、交 JLCPCB 製造的工作流程：流程文件、專案範本、JLC 客服溝通 skill、生產稿比對腳本與範例設計

Agentic coding, in your control

nnInteractive as a tool for AI agents: say what to segment, the agent does the rest (Claude Code, Codex, any MCP client)

Tool for porting OEM specific apps on every devices (Manual + AI Agents)

Agent Skills plugin for a persistent LLM-managed markdown wiki — ingest, cross-reference, cited queries and lint with 5 stdlib scripts

A highly configurable discord bot that provides both utility and entertainment.

Code repository for AI Builders Bootcamp #1