Custom agents

Turn ideas into autonomous research with Git-like evidence histories—inspectable, reproducible, and reversible.

Проверяемая гигиена вставки из чата для русского текста

Chat with your favorite models, gather a team of Cupcake advisors, and turn questions into ideas, working code, and projects worth keeping.

Git-backed shared memory for AI agent fleets: searchable knowledge base, incident and task tracking, every write versioned and attributed. CLI, HTTP API and MCP server.

Small enough to run on your Mac. Smart enough to ask. An open-source computer use agent for macOS, with local models (MLX) that see, decide and act. 得心，应手。

从原理到实践，全面掌握大语言模型安全攻防之道 | Latest security techniques with LLM and AI Agent

给 AstrBot 的可落地 AI 记忆与生活层：五类记忆、混合检索、遗忘治理、情绪边界、自主生活循环。不覆盖人格。

A comprehensive resource designed to help developers effectively use AI tools to develop websites, apps, and other projects.

Make WhatsApp ChatBot and use WhatsApp API to send the WhatsApp messages in python .

[ACL 2026] OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces

(not yet very) Ultimate LLMs aggregator right in your Discord server

[USENIX Security 25] PatchAgent is a LLM-based practical program repair agent that mimics human expertise.

Code repo for "Agent Instructs Large Language Models to be General Zero-Shot Reasoners"

Native-like RTL support for VS Code AI Agents (i.e. GitHub Copilot) with proper LTR code block formatting. Optimized for Hebrew, Arabic, and Persian.

Official repository of the 2025 paper, LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra.

This is the repository for the LatteReview python package. LatteReview is a low-code Python package designed to automate systematic literature review processes through AI-powered agents.

An orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and governs them for production-grade operation.

Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.

Context engineering for coding agents - CLAUDE.md templates, mechanical enforcement, and a field guide to 20+ best practices. Bootstrap with one command.

Vibe Trading — agentic AI trading platform for Indian markets. 7 LLM analyst agents analyze stocks in parallel, debate bull vs bear, and deliver trade plans. Open-source agentic quantitative researcher for NSE/BSE/NFO.

Agentic-first Cursor Rules powered by MiniMax M3 - clarify-first prompting, interleaved thinking, and full tool orchestration for production-ready AI coding

Animated components, blocks, charts, and templates for React. Copy them in, install with a CLI, or hand them to your coding agent.

Field-tested Claude Code patterns & anti-patterns for personal agents — an AI workflow that compounds: knowledge base, memory consolidation, hooks, subagents. Enterprise agent trust: agentrust-io.com. Updated monthly.

Run a team of AI coding agents. On your machine. Local-first orchestration for Claude Code, Codex, OpenCode, Antigravity, and Copilot.

Local-first AI knowledge app and Agent Skill with evidence-backed Wiki, an interactive knowledge universe, Viki Q&A, and shareable knowledge galaxies.

Autonomous multi-agent pentest framework — plans, exploits, verifies (proof-required), CVSS-scores and writes client-ready reports. 104/104 (100%) on the XBOW validation benchmarks, powered by Kimi K3.

The spreadsheet framework built for agents — write the model as React, export a live .xlsx. The third medium, after open-slide and open-doc.

MVP of an idea using multiple local LLM models to simulate and play D&D

Local-first MCP password and credential manager for AI agents. Use passwords, API keys, SSH identities, and TOTP without exposing hidden plaintext to the model.

Self-Hosted LLM Code Review Agent for GitLab, Forgejo and GitHub. Local LLM support

Model-neutral AI workspace for macOS with multi-provider models, extensible tools, and inspectable deliverables.

Long-horizon benchmark where 18 LLM agents got ¥100,000 each and ran simulated online stores for 365 days on real market data: negotiating with suppliers, pricing, managing inventory, keeping cash flow alive.

Publisher is the open-source analytics engine for Malloy. It lets you define data models once — and use them everywhere.

Moved to NousResearch/hermes-official-plugins/claude-subscription-directsdk, the home of Nous Research's official Hermes Agent plugins.

100,000+ AI briefings in 41 categories: models, dev tools, agents, research, funding. New briefings are fact-checked against their source post and link to it. Plain Markdown, CC BY 4.0. MCP server + Agent Skill let Claude, Cursor or VS Code ask for the latest. Read at blogs.drix10.com

open sourced personal agent + dual-brain voice assistant. 开源个人助手 + 前后脑语音助手. restrained proactivity, wide context. 主动但不啰嗦，懂你所想，帮你所需

让 AI 编程助手（Cursor / Claude Code 等）能更好地编写 Minecraft 模组的完整工具包。

OpenAPI definitions, converters and LLM function calling schema composer.

An open-source Agent platform for intelligent operations scenarios, built on Spring AI and integrating knowledge retrieval, streaming conversation, web search, and tool calling to enable a complete closed-loop operations analysis workflow.

Tool calling using MLX Swift across iOS, macOS, and visionOS platforms

Memory that learns what works.

Portable Memory Harness for Agents. Grounding the Autonomous Era

[NeurIPS 2025] Official repository of RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

[ICLR 2025] Official repo of "Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs"

Hammer: Robust Function-Calling for On-Device Language Models via Function Masking

High-performance, code-first workflow automation engine. TypeScript-native with Rust core for enterprise-grade speed, efficiency, and developer experience.

Official typescript implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

(WIP) Open Knowledge Layer(OpenKL): The Advance Knowledge and Memory for Personal Agents.

🐤🐧 A declarative and highly modular Blackboard Multi Agent System 🐓 🦆

🦞 ClawMark: A Living-World Benchmark for Multi-Day, Multimodal Coworker Agents

MCP server for computer use & browser automation - screenshot, OCR, click, type, find_text, Chrome/Electron CDP, template matching. macOS, Windows & Android. Works with Claude, Cursor, and any MCP client.

AgentSmithy provides a series of tools and templates that simplify the process of building and deploying custom AI agents on Google Cloud.

QuantConnect Algorithmic Trading Platform Orchestration MCP - Agentic LLM Driven Trading Strategy Design, Research & Implementation

An open-source, headless CRM built for agents. No UI. No dashboard. Just a CLI and a FUSE-mounted filesystem.

一款轻量级、可扩展的、跨平台的、专为医疗信息化设计的电子病历编辑器内核，为EMR（电子病历系统）提供专业的结构化病历编辑与AI接入解决方案。

Bot 100% editavel, gratuita e descriptografada

🚀 Advanced Data & AI Engineering Portfolio: Real-world projects and production-ready patterns to level up your AI skills—from building clean data pipelines to deploying RAG systems, AI agents, and intelligent dashboards.

AIRS-Bench: an AI Research Science benchmark for quantifying the end-to-end AI research abilities of LLM agents

MCP server for AI assistants to read and manage Coros fitness data: sleep, HRV, daily metrics, activities, and structured workouts via the unofficial Coros API

Install Oracle skills to Claude Code, OpenCode, Cursor, and 12+ AI coding agents

Agent skills for SwiftUI, built from Apple's Xcode AI documentation.

The first comprehensive open-source AI-native framework for CRE acquisitions, turning diligence, underwriting, financing, legal, and closing into executable agent workflows.

一个全新重构的 AI 聊天机器人框架，它的目标不仅仅是回答问题，而是创造一个真正的数字生命体。

17 triggers × 44 algorithms × 3 AI experts — live crypto trading signals with reasoning for Claude Code, Codex, Cursor & 30+ agents. Free key; Pro adds entry, SL and TP.

A library of Claude Code skills for teaching coding agents how to use various CAD tools

Token Efficiency For AI Agents

AI algorithmic trading toolkit with backtest, simulation modes. ai algo trading agent

Operation-bound protection for autonomous AI agents: contain and verify operations before committing changes, understand intent and risk across long-running work, and detect threats across agent and system activity.

Local-first Canvas LMS AI agent that learns each course's recurring assignment workflow and reuses it through scan -> approval -> execute with student review.

禁漫天堂 Agent Skills MCP | JMComic integration via Skills and MCP for AI Agents.

Data Science Skills for AI agents like Claude Code

Stealth headless browser engine in Rust — native BoringSSL TLS/JA4 fingerprint, real JS via deno_core, no Chromium, no CDP. Python + MCP bindings. A camoufox alternative.

ASL · 本地可日更的 A 股研究湖 · 42 数据集 · MCP 供数 AI agent · 零 token 零注册 | Local A-share research lake — history for humans & agents

AI agent skills for Upwork freelancers, from a real Top Rated Plus playbook. Free, open, community-written. Not affiliated with Upwork.

Vendor-neutral OpenTelemetry skills for AI coding agents like Claude Code, Cursor, and Codex, grounded in upstream sources

Fluent is a self-improving software factory. It autonomously turns your team's vision, ideas, bug reports, user feedback, production logs, and agent traces into working software.

Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.

止まった場面を責めずに振り返り、見えていなかった前提と次の一歩を見つけるClaude Code / Codex向け対話型Agent Skill

Epistemological database for agent and human efforts, beliefs, and findings.

Local-first AI math visualization desktop app: draw, analyze, and explain geometry with GeoGebra, Tauri, React, Bun, and native tool calling.

Self-hosted project management for devs and their clients: tickets, time tracking, docs and meetings, with an AI assistant that cites its sources. AGPL-3.0.

麦当劳配餐决策 Skill｜1881 种搭配里算出三档最优解，并告诉你为什么不是另外那些。控卡、忌口、拼单 max-min 公平分配；LLM 不参与算钱，每个数字可追溯。

ADLC Harness — AI SDLC 루프(의도→설계→계획→구현→검증→리뷰→출시→학습)를 Claude Code·Codex·Copilot CLI에서 돌리는 플러그인

Self-hosted API execution layer that sits between your agent and the outside world. Your agent says what it wants to do. Jentic Mini handles the how — finding the right API, injecting credentials at runtime, and brokering the request

Turn your documentation into an AI assistant that answers questions instantly

Benchmarks for Multi-Objective Multi-Agent Decision Making

Code for paper 'Learning transferable cooperative behaviors in multi-agent teams' (ICML 2019)

ICRA 2024 | Decentralized Multi-Agent Trajectory Planning in Dynamic Environments with Spatiotemporal Occupancy Grid Maps

A self-evolving subagent system for Claude Code

📖 A step-by-step guide for beginners to running Claude-generated React code locally.

ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning

AGENTS.md/CLAUDE.md generator and ExecPlan harness for Codex, Claude Code, Cursor, Antigravity, OpenCode, Pi and other coding agents. Use api keys or authenticate with Codex or Claude Code

MCP Armor continuously secures and monitors Model Context Protocol operations through static and dynamic scans, revealing hidden risks in agent-to-tool communications.

Collection of Claude Code Subagents designed to be used for Magento (2) development.

[RAG训练营] u.geekbang.org/subject/airag/1009927 这是我用Cursor自行制作的RAG Framework，好处是可以掌控RAG每一个环节的教学细节。

An interactive visualization tool for understanding Retrieval-Augmented Generation (RAG) pipelines.