Custom agents

BabyCommandAGI is designed to test what happens when you combine CLI and LLM, which are older computer interfaces than GUI. Based on BabyAGI, and using Latest LLM API. Imagine LLM and CLI having a conversation. It's exciting to think about what could happen. I hope you will all try it out.

Deploy AI chatbots, RAG systems, and agents in under 7 minutes on AWS.

Modular Discord bot using JavaScript and optionally Python and Lua.

Chatbot in russian with speech recognition using PocketSphinx and speech synthesis using RHVoice. The AttentionSeq2Seq model is used. Imlemented using Python3+TensorFlow+Keras.

Chatbot_CN项目中的Chatbot_rasa模块

🤪 Русскоязычный чат-бот для Discord на архитектуре Transformer

The Flask server that communicates with my FB Messenger chatbot

对SmartQQ API的C#封装。（由于作者懒出了一定境界现已停止维护）

Easily create LLM automation/agent workflows

Tensorflow Implementation of Multiple Landmark Detection using Multi-Agent Reinforcement Learning Paper

An enterprise-grade implementation of multi-agent systems using OllamaJS, featuring advanced orchestration, dynamic agent allocation, and seamless integration capabilities.

A ChatGPT-like app using Alibaba's Qwen3.5 models locally on the phone - with tool calling & vision

一个在Unity中实现的生成式人工智能代理规划框架。A planning framework for generative artificial intelligence agents implemented in Unity.

This repo provides guidance on setting up a bedrock agent to webscrape and internet search via action groups

The Lightest Shared Standard for AI Agents

🚀 MCP aggregator for batching multiple tool calls into a single request. Reduces overhead, saves tokens, and simplifies complex operations in AI agent workflows.

🤖 Community fork of Google's Gemini CLI for Qwen AI models. A powerful command-line tool that uses Alibaba Cloud's Qwen models to understand your code, automate workflows, and accelerate development. Features multilingual support (EN/CN), model switching, and web search integration.

Similarity detection for Github Issues + AI code reviews

Source code for paper:Multi-agent reinforcement learning for liquidation strategy analysis

Reducing Global Carbon Footprint based on Multi-Agent Reinforcement Learning - School of AI Fellowship Research

Architecture Details for CVPR 19 paper: Multi-Agent Tensor Fusion for Contextual Trajectory Prediction

XMPP agent framework

HoneyAgents is a PoC demo of an AI-driven system that combines honeypots with autonomous AI agents to detect and mitigate cyber threats. Features include intelligent threat analysis, automated deny list updates, and detailed natural language threat reports.

Multi-agent terminal app

A modern desktop application for managing Model Context Protocol (MCP) servers across multiple AI agents

LLM Agent Skill for YARA rule authoring and review

Multi-Agentic System Observability SDK

MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.

A demo application that uses Amazon SageMaker manuals and pricing data tables as an example to explore the capabilities of a generative AI chatbot.

Official Rust implementation of the UTCP

.NET (C#) Web App Framework Built For AI Coding Agents

Crawlbase MCP Server connects AI agents and LLMs with real-time web data. It powers Claude, Cursor, and Windsurf integrations with battle-tested web scraping, JavaScript rendering, and anti-bot protection enabling structured, live data inside your AI workflows.

An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Tasks

A2A-Native AI Agent Platform written in Go

一个基于多智能体协作的命令行工具，将你的原始想法自动推进为完整 PRD、技术设计、评审记录，并调度本地开发工具链完成交付。A multi-agent collaborative CLI tool that automatically transforms your raw ideas into complete PRDs, technical designs, review records, and orchestrates local development toolchains to deliver the final product.

Synode — A macOS & Windows desktop app where multiple AI models discuss questions as a council, with a master model delivering the final verdict. Follow up with any model via @mentions. Built with Tauri v2 + React + TypeScript.

A mini assistant to help you read paper quickly

QwenPaw（原 CoPaw 项目）的 Docker 部署方案，支持一键构建和运行，相比官方镜像更小。

Multi-Agent Deep RAG

輸入文字或圖片，LLM會找出適合的梗圖來回覆你

MAM: ModularMulti-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration

Private AI research agent — web search, document ingestion, RAG memory. Runs entirely in your browser.

从一个技术关键词出发，自动生成前沿技术领域的技术全景图谱。AI Agent Skill for Gemini CLI / Claude Code.

Local control plane for running AI agents with sandboxes, approvals, guardrails, credentials, and runtime health.

构建生产级AI智能体的12个工程原则。提供实用模式和最佳实践，帮助开发者构建可靠、可扩展的LLM驱动应用程序。（中文翻译版 by 云中江树）

Your AI Soul Companion. Self-hosted AI agent across 30+ messaging channels It can not only serve as an emotional companion in daily life (such as a lover or friend), but also help you complete various complex tasks like coding、training models through channels

👋 Claude Code & Codex harness insights dashboard — visual catalog and token analytics for skills, agents, plugins, hooks, memory, and more!

All things Copilot, Agents, MCPs, Skills, and coding related AI features for the Norwegian Government

Patterns of Multi-Agent System Architecture

Workspine: plan, execute, and verify AI-assisted work from files in your repo, across sessions and agents.

Supervised agent execution for software teams. Kanban-driven, tmux-native, test-gated.

高考辅导Agent：基于 LangGraph 的多智能体框架，集成情感识别、RAG 试卷检索与个性化学习规划，为学生提供全方位的智能助学体验。

基于qq官方api开发的符合onebot标准的golang实现，轻量、原生跨平台.

Visualize your project's feature logic as a semantic flow graph — not call graphs, not import maps. AI writes the data, you see the story.

CVE hunting harness for Claude Code - 20 skills, 5-agent team, systematic vulnerability research with false positive elimination

Telegram-first control plane for supervised coding: plan requests, run agents, review evidence, and ship verified PRs.

This is a darkweb forums tracker that monitors forum posts and sends alerts to Discord

Idea-Catalyst is a metacognition-driven framework for helping humans and LLMs boost their creativity during the scientific brainstorming process.

Code samples for building AI applications on AWS with Amazon Bedrock, including Converse API, tool use, RAG with Knowledge Bases, guardrails, and a full agent built with the Strands Agents SDK.

Turn any website into clean, LLM-ready data. Open-source web crawler with stealth mode, distributed crawling, real-time WebSocket progress & Markdown output. Power your AI apps with GcrawlAI.

An image-first canvas for your local Codex agent.

Open-source email infrastructure for AI agents.

This course uses a deliberately vulnerable banking application to demonstrate common security vulnerabilities, their impact, and how to fix them. The application is built with Flask (backend) and React (frontend).

Local-first research tool with explicit fetch decisions, source evidence, and cited reports. CLI and MCP interfaces. Python, MIT.

Midra is an agentic prompt-to-code MIDI composition framework for editable and controllable music generation.

面向 AI 时代的数据可视化规范与工作流库 — specification & workflow library for AI-era data visualization

Hermes Agent skill for grading SOUL.md identity files with a research-backed rubric and public-safe field guide.

Agent-as-a-Judge grading framework for evaluating AI outputs/deliverables

Elevate your AI assistants (like Claude & Cursor) into autonomous cybersecurity experts. Pentester-MCP integrates 200+ pentesting tools via the Model Context Protocol (MCP) using a secure Docker sandbox.

Paper list for "From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms".

Multi-agent AI development templates for opencode

Edu-RAG：面向 K12 / 学科教育场景的轻量化 RAG 智能助教开源框架，依托教材、教辅知识库实现精准答疑、习题解析与个性化导学，有效抑制大模型知识幻觉，开箱即用快速落地 AI 教育应用

A Lisp with first-class LLM primitives, implemented in Rust

Absurdly fast embedded graph database with built-in vector search. Rust core, Node.js and Python connectors, GQL, graph algorithms, all in-process with no server.

Optimize LLM agent harnesses through tunable Formulas to dynamically enhance the agent, and improve those Formulas with optimizers based on collected agent rollout trajectories.

Evidence-backed growth decisions for AI-agent teams

Zero-token, on-device vision for AI agents — OCR, pixel-exact UI targeting, and face grouping on Apple Vision. Pure Swift, single binary, no dependencies.

Agent Skills and lightweight tools for clearer, more natural Vietnamese writing, translation cleanup, grammar checks, and style consistency.

A terminal AI agent you can fully undo - every file and shell action is snapshotted and reversible. Model-agnostic (any LLM), and connects to 1000+ app tools and MCP servers.

Solweaver: a Codex software team with GPT-5.6 Sol orchestrating Terra and Luna workers.

An autonomous Kubernetes SRE agent. It monitors cluster health, diagnoses issues, and applies fixes — with human approval required before any write operation.

Local-first Agent Skills for safe social-web workflows—starting with Douyin and designed around reusable browser adapters.

Run scripts, explore your genome, and get personalized explanations — all in natural dialogue.

Agent-native CLI for Adobe InDesign automation — 150 tools, HTML ↔ InDesign conversion, and structured JSON returns built for AI agents.

An AI chief of staff in plain markdown, in an Obsidian vault. It tracks your calendar, commitments, and rules, and hands you a morning brief. Version two: torn down and rebuilt smaller. Built on Claude Code, ADHD-first, open to anyone.

Decentralized Ed25519 Cryptographic Identity, Signed Message Bus, and Proof-of-Contribution Framework for AI Agents on Technocore ( Ecosystem)

Rewrite frontier research using allegorical structural mapping.

可视化 Agent 编排平台｜基于 DeepSeek Harness，支持 Workflow、Multi-Agent、元编排、MCP 与 Human-in-the-loop｜Visual AI Agent orchestration platform for workflows, multi-agent teams, MCP and human-in-the-loop

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

An index of Claude and agent skills for academic work, from literature search to peer review. Organized by where each skill fits in the research lifecycle; each entry notes its license and what it runs. CC0.

Make Claude the manager, not the coder: one skill that hands work to cheaper AI CLIs, verifies the results, and gets a second vendor to review.

OpenClaw 安全客户端 - Hook 注入/执行前审批/基线扫描

Self-hosted continuity memory for persistent AI identities across agents, models, and interfaces.

A framework for building synthetic worlds for AI agents. Useful for RL and evaluation environments.

Local-first cross-session long-term memory for DeepSeek Harness — 22 narrow tools, hybrid FTS5 + local-vector retrieval, evidence gate, provenance audit, SM-2 review. Zero external services, zero API keys.

Post-training robot planners with SFT and multi-turn RL across agentic robotics harnesses

Valorant 2026 toolkit for Ranked practice, agent planning, aim training, crosshair and sensitivity profiles, map preparation, FPS optimization and match analysis.