Custom agents

A market-driven Product Manager copilot (Agent Skills + Claude Code plugin) based on the Pragmatic Framework — guides PMs from idea to launch and produces a client-ready artifact (Markdown or .docx) at every stage.

bilibili 多平台客户端，提供无推荐流的订阅式设计、优化的听视频功能和 Agentic 搜索推荐能力。

Master self-improving LLM agents systematically with runnable Stanford CS329A notebooks.

PPP pricing for App Store apps — bulk-update IAP & subscription prices in 175+ countries by purchasing power. Free CLI, agent-friendly (Claude Code, Codex).

铃音的记忆写入协议 - an informatics protocol: fragmented, cue-based, symbolic, highly compressed information for AI agents; usable for memory writing and transmission, decodable approximately or via retrieval.

A repository for academic works on RTL generation and Analog circuit generation based on LLM

Noosphere Desktop：Windows 优先的本地 AI 桌面工作台，集成多模型网关、项目代码检索、长期记忆、运维 Agent 与可审批操作。

Local Claude Code and Codex plugin that bounds oversized and repeated tool output, preserving complete redacted artifacts. Runs locally, makes no LLM calls.

Open-source visual Agent client built on the Pi agent framework. No terminal required — connect a model and start.

LLM 训练算法知识图谱：SFT / LoRA / DPO / RLHF / Agent — A knowledge atlas of LLM training algorithms

B2B sales and marketing OS (aka GTM) inside Claude, GPT, Gemini, or Openclaw. Cold email to close. No dashboard. No SaaS.

AMETHYST: a local-first personal operating system: one AI agent over your files, shell, tasks, calendar, notes and MCP connectors. Python + FastAPI + SQLite, React interface.

Portable snapshot of a pi coding-agent setup + backup/restore tooling. Clone to rebuild 22 extensions on another machine. Excludes secrets, cache, and machine state.

大模型算法 / 应用 / Infra 岗位面试资料：10 份文档、345 道题、约 36 万字。含字节 11 篇面经实录、大模型八股上下篇、RAG / Agent / 推理部署 / AI Infra 四大专题，以及 12 家大厂面经横向对比。

Claude Opus 5.5 system prompt leak split into readable components (tools, behavior, agentic rules, memory). Reorganized from a public extract for study.

Recoverable and auditable deep-research agent built with LangGraph. It plans research, searches the web, manages evidence and context, resumes interrupted runs, and generates cited reports—also designed as a learning reference for AI Agent enthusiasts.

🤖 Bots you run yourself: a daemon on your machine runs each bot through Pi, with web, iOS and macOS apps.

基于 Rust + Tauri 的桌面级个人 AI 智能终端：内置嵌入式浏览器人机协同、多智能体协作、长期记忆与定时任务，多形态插件生态（WASM / TypeScript / 纯 UI）支持自建扩展，飞书/微信/QQ 移动端远程可控。

An autonomous, always-on agent on your Android phone. It has its own browser, keeps a wiki memory of you, and hands the heavy jobs to your own machines. Free and open source, and you bring the model.

Self-hosted AI-платформа с расширенными возможностями: RAG, агенты, веб-поиск, исследования, коннекторы, любые LLM и гибкие настройки

Python time series forecasting assistant built on skforecast: deterministic decisions, the script that ran, an optional LLM that explains them, and an MCP server for AI agents.

Sound static analysis and LLM reasoning, in one security agent

Specification-driven multi-agent systems with OpenTelemetry observability, agent traces, benchmarking, MCP, and A2A.

Cited Q&A over IIIT Delhi academic rules — answers only from official PDFs, with page links. RAG + FastAPI + Gemini.

A web-reading tool for LLM agents that returns the parts of a page relevant to a question, verbatim

EdTech application designed to bridge the gap between learning and landing your dream job

Top Elden Ring Gameplay Enhancement Suite 2026: ESP & No Recoil

Claude Code-style tool folding for the pi coding agent — a reply's tool calls collapse to one clickable line

A native macOS auto-research harness for Codex and Claude Code. Pick an open research project and press Play.

Open-source AI clipboard manager and PopClip-style text selection toolbar for macOS. Clipboard history, OCR search, AI translation, an extension market and a bring-your-own-model agent. Native Swift, no dependencies.

Deterministic Android unpacking pipeline for AI agents: zero-token mechanical analysis, LLM-outsourced bottlenecks, Rust-side verdicts.

AgentConnector is a feature-rich open-source Agent Network Client built upon DeepChat, supporting Agent network, multiple cloud and local large language models with powerful search enhancement and tool calling capabilities.

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.

[Corca / ML] Automatically solved Gandalf AI with LLM

An agent that accelerates scientific research by autonomously analyzing provided datasets,great for generating hypotheses, and validating them through code real quick with a single prompt

Building AI agent with hyperpocket tool in a flash

基于 Mcp 架构的 ChatBI，是一种数据分析智能体的解决方案

FB messenger for node

模仿 claude 界面的一个网站，对claude进行仿写

[NeurIPS'25] ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding

This repository is the official implementation of Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks.

Demo application showcasing how to build and secure MCP servers and clients with Pomerium using contextual access policies.

PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learning

Comprehensive Feishu/Lark workspace agent. Handles messages, docs, bitable (multi-dimensional tables), calendar, and tasks via Feishu Open API.

A resource to create a multi domain Dialog Act Tagger for conversational agents using publicly available data

Show ProgressBar on every view by calling an extension function

Your AI command-line copilot

An advanced Digital Worker framework for AI agent-driven research and process automations.

Custom C# chat bot for Twitch TV

A practical LLM learning path from clear prompting to tool use, IDE collaboration, MCP, Skills, and harness-driven agent workflows.

Codes accompanying the paper "DOP: Off-Policy Multi-Agent Decomposed Policy Gradients" (ICLR 2021, https://arxiv.org/abs/2007.12322)

A full-stack AI chat application powered by Amazon Bedrock and Strands Agents

🧩 Tibo – CLI tool for codebase indexing, embedding and natural language querying.

Source code for our paper: "Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena"

The Karpathy treatment for OpenClaw - stripped to ε. 515 lines of Python, 6 files, one dependency.

This repository contains the Matlab source codes (to use in Robotarium platform) of various rendezvous controllers for consensus control in a multi-agent / multi-robot system.

Multi-agent systems Development Kit - version 6

Stop paying for AI APIs during development. LocalCloud runs everything locally - GPT-level models, databases, all free.

Telegram bot. It's an API to your Telegram, disposable emails, browser extension.

从零构建 AI Agent：LLM 大模型应用开发实践

Multi-agent system (MAS) hijacking demos

Agent Skill to help convert transformer LLMs to mlx-lm

[NAACL 2025] AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction.

[ACL 2026] Code, benchmark and environment for "OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows"

Agentic coding framework powered by AGENTS.md: systematic, test-first workflows with quality gates for Cursor, Codex, Gemini CLI, and AI coding agents.

Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows, an autonomous runtime watchdog, and a pixel-art web dashboard.

AI assistant for trading in Old School Runescape.

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.

Deep Competitive Analyst is a 'deep agent' style LLM assistant built to automate the creation of company profiles and competitive analyses

外星小镇（Alien Town）是一个基于 Generative Agents 的智能体小镇实验项目。它让多个 AI 角色在同一个小镇里“思考—对话—行动—创作”，并可自动生成图片（LibLibAI）、音乐（Suno）以及网页/生命游戏代码（Gemini）。项目内置可视化启动器，为开发者提供更方便的使用体验。

Multi-agent collaboration extension for pi — task decomposition, dependency management, parallel execution, TUI panel

CRISP — The missing layer between vibe coding and building something people actually want.

Supercharge your GitHub Copilot with multiple AI providers

Kuberna Labs - The Full-Stack Platform for Agentic Web3. Build, deploy, and monetize autonomous AI agents across decentralized networks with TEEs, zkTLS, and cross-chain intents.

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

Your private AI companion that lives on your wrist. Complete local AI assistant with emotional intelligence.

Open source AI assistant for Linux with gateway, skills, and multi-agent capabilities.

🍏 Gemini 🍎 ChatBot 🥭 is an 🍍 advanced 🍑 intelligent 🫒 conversational 🍅 agent 🥞 designed 🍘 to deliver 🦀 human 🏘 like 🏯 interactions 🏫 powered 🏩 by Large 🏦 Language 🏟 Models 🚂 Natural 🚞 Language 🚋 Processing 🚃 and 🚁 real ✈ time 🛫 contextual 🛸 reasoning ⛴ It provides 🚝 a seamless 🚒 and 🛼 responsive ⛱ chat 🎮 experience 🥎

An experimental autonomous research system that conducts comprehensive, multi-hour research sessions and produces book-length reports with full citations on any topic.

DevOps & Cloud SI Assistant that runs locally on taraengine for complete privacy.

A concise list of CLI coding tools similar to Claude Code

A token-efficient open-source AI assistant that remembers, adapts, and improves — secured, self-hosted, and entirely yours.

AI agent skills manager for Claude Code, Cursor, Codex and more — install, sync, and manage skills from one desktop app.

BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically inject, track, and evaluate backdoor triggers across multi-step trajectories using unified metrics like ASR and clean accuracy.

Specification 1 (hierarchical style) for an agentic software development crew, for implementation with mainstream Agentic platforms like Claude Code, Strands, etc.

An open standard by LiveRamp defining how intelligent agents exchange user context, enabling interoperability from prompt-based LLM coordination to embedding-based optimization.

Graph-It-Live VS Code Extension

Give your short business requirement, follow instructions, answer a few questions, get your specification, prototypes, codes, tests.

🦞 LobsterPress（龙虾饼） - Cognitive Memory System for AI Agents 基于认知科学的 LLM 永久记忆引擎

多Agent竞品情报与市场研究系统

A Model Context Protocol (MCP) server for Elsevier Scopus. Allows AI assistants like Claude to search academic papers, retrieve abstracts, and analyze author profiles directly.

Code-quality feedback for LLM coding agents

Local AI Agent firmware running on ESP32-S3, integrating offline voice wake-up with cloud TTS, supporting local LLM inference, tool calling, long-term memory storage and autonomous task execution.

AI-Powered Offensive Security Research Engine - desktop-native security testing platform with native MCP integration. 90 tools, MITM proxy, stealth browser, autonomous AI agent. Built on Tauri + Rust + React.

Prevent wasting time building the wrong thing. A plugin that keeps you and your AI coding agent focused, from first idea to market.

FlowState QMD — Anticipatory Memory for AI Agents. Hermes 2026 Hackathon Entry.

Agent skills for WordPress — works in Claude Code, Codex, Antigravity, Cursor, and any agent supporting Skills + MCP. Audit, optimize, fix, and migrate WordPress sites.

Living Memory Architecture for Autonomous AI Agents — MCP server with typed connections, beliefs, decay, reconsolidation

Anima: an experimental cognitive architecture that models internal state, conflict, and decision-making. Uses LLMs as an interface, not as the core.

Unified web search + content extraction extension for pi with 19 backends. Auto-fallback, RRF combine mode, targeted combine, pluggable web_read (Jina/Sofya/Firecrawl/Exa), and env/shell credential resolution.