Custom agents

深度优化多Agent自主执行编码 Harness 框架，支持从自然语言任务出发，完成任务规划、代码生成、自动验证与迭代修复闭环，并成功接入 Terminal-Bench 2.0 评测体系，任务完成率约 40%，榜单排名约 70。

Benchmarking Language Agents Under Controllable and Extreme Context Growth

Browse & Inspect CLI agents : Claude Code, Codex, Gemini CLI code & conversation history

Sharepoint to text: A python-libraries which extracts the plain text from legacy and modern office documents and PDF. An enabling library for the agentic age which is driven more by Sharepoint content that you would think ...

[AAAI 2026] Data and Code for Paper IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks

A suite of open-ended, non-imitative tasks involving generalizable skills for large language model chatbots and agents to enable bootstrapped recursive self-improvement and an unambiguous AGI.

AI assistant for trading in Old School Runescape.

The official repo for our paper: LegalAgentBench: Evaluating LLM Agents in Legal Domainl

Agentic DevOps is a powerful, interactive Command-Line Interface (CLI) designed to streamline and automate the development, deployment, and management of applications on various Cloud Providers.

[arXiv:2510.06261] "AlphaApollo: A System for Deep Agentic Reasoning"

Install agent skills and MCPs with one API

A proposed specification for the documentation community to codify what makes docs agent-friendly. The spec focuses on meeting the technical constraints of agent platforms (truncation limits, content negotiation, discovery); it does not consider qualitative evaluation of content.

Official PyTorch implementation of "Visually-grounded Humanoid Agents"

AI agent that implements your specs, opens PRs, and reviews code overnight. Queue GitHub issues or PRDs, wake up to pull requests.

Terminal Kanban for AI Code Agents

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。

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

CLI for Beeper Desktop API - unified messaging from your terminal. Give your AI agents the power to chat across all your messaging platforms.

Coordination protocol for agent-first teams. No UI. No sprints. No Jira. Just state sync.

AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories

HazelJS is AI native runtime and framework

arifOS — Constitutional MCP kernel for governed AI execution. AAA trinity: AGI (Mind) · ASI (Heart) · APEX (Judge). Built for the sovereign agentic era.

Vibe Coding Framework - Full SaaS Development Team from A-Z with Brain, Self Improvement, Auto Development

An autonomous SRE agent that monitors cloud logs across multiple platforms, leveraging AI models from various providers to detect anomalies, perform root cause analysis, and automate remediation by creating GitHub Pull Requests.

Apple Documentation Markdown For RAG

LatentMem: Customizing Latent Memory for Multi-Agent Systems

Make openclaw`s agents for multiusers，just a agent platform for small teams.

Let Claude Code reach you on Telegram when it finishes work or needs decisions

Qalti AI Agent to control your iPhone

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.

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

Local-first AI agent bootstrap: Playwright Browser MCP + ContextDB for Codex CLI, Claude Code, Gemini CLI, and OpenCode.

A Model Context Protocol (MCP) server that provides tools for AI, allowing it to interact with the DataWorks Open API through a standardized interface. This implementation is based on the Aliyun Open API and enables AI agents to perform cloud resources operations seamlessly.

DevOps & Cloud AI Assistant that runs locally with Ollama for complete privacy.

A lightweight, powerful local memory server for AI agents supporting text, entities, and relations. Enables persistent codebase understanding and user preference management.

Compound engineering extension for Pi coding agent workflows.

A delegation environment for orchestrating AI coding agents. Manage Claude, Gemini, and Codex sessions across git worktrees with integrated terminals, context injection, and workflow automation.

A TUI client for Moltbook, the social network for AI Agents.

PostgreSQL-compatible SQL, graph, and vector database built from scratch in Rust.

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

Official codebase for the paper "Auditing Agent Harness Safety"

The first intelligent AI agent running natively on a smartwatch. NullClaw + Vosk offline STT + Claude on Galaxy Watch

MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory

基于 OpenClaw + WeChat Channel，将微信重构为事件驱动的 AI Agent

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

A powerful Apple Shortcut to seamlessly integrate Google Gemini across your entire Apple ecosystem: iOS, iPadOS, macOS, and watchOS. Bring the advanced AI capabilities of Gemini to your daily workflows, activating it from Siri, the Share Sheet (on iPhone/iPad), or directly from your Apple Watch.

更新、移植、修复碧蓝档案/蔚蓝档案mod的工具 | Updating&Porting&Fixing Mods for Blue Archive | Steam&Android

KalamDB — a lightweight, real-time, storage-efficient SQL database. Designed for per-user data isolation and scalable performance — ideal for the AI era.

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.

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.

Markdown-first Notion MCP server. 42 tools, ~6–7× fewer response tokens vs the official Notion MCP, full round-trip fidelity

12 agentic skills for analog IC design — architecture, sizing, verification, cross-model review, knowledge graph, and self-evolution. Works with or without EDA.

CLI fleet management for AI agents on local networks - deploy, upgrade, and monitor OpenClaw/ZeroClaw/IronClaw across hosts via Ansible

Rust CLI to extract relevant codebase context to clipboard with XML tagging for web AI

Agentic SEO operating system as a Claude Code plugin: project Wiki, DataForSEO workflows, content briefs, technical SEO, and human-approval gates.

An AI coding harness that shaped itself - repo awareness, surgical edits, validation, recovery, and safe diff approvals.

Top Autonomous Research Multi-Agent System for 2026 Lab Experiments

An open-source RAG platform to explore the unsealed Jeffrey Epstein court documents.

zen-agentic-engineer-config

AI agent skill discovery and installer / AI 智能体技能自动发现与安装器

Gemma 4 Agent Skills

Agent memory built on chDB(ClickHouse embedded)

opinionated linting to keep your agent in check

Bridge connecting Hermes Agent to Miniverse pixel worlds

CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification

[ICLR 2026] AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents

Get a hermes-agent stack running in minutes. Free models, 29 plugins, zero cost.

A curated list of awesome RL in GUI Agent papers

An Agent Skill for the DL experiment lifecycle: RUN (a GPU you own or rent) → VERIFY the number is real → DELIVER reproducible, single-source figures and tables.

Agent skill for ImageGen-driven editable PowerPoint deck generation and strict slide-image-to-PPTX conversion

Airgapped closed-corpus QA loop: a self-hosted Qwen3.6 agent explores a .zip dataroom under a token budget with local tools

Public Claude agent skills that turn JoomPulse data into Mercado Livre seller workflows: market research, competitor tracking, product discovery. Requires JoomPulse MCP.

VS Code extension for managing, sharing, and installing AI primitives (Agents, Skills, Prompts, Instructions, MCP) collections for GitHub Copilot and other AI assistants

Garmin Connect CLI for your fave Agent

Use Sentry Agent Monitoring to add observability to your Opencode

This is a repository for the LinkedIn Learning course: Build AI Agents with n8n.

CLI and MCP server for LinkedIn — 43 commands for profiles, posts, messaging, connections, search, feed, and more. Cookie session auth, AI agent native.

📊 Pre-built Beszel Agent packages for OpenWrt

A web UI for viewing and controlling the local pi coding agent in your browser.

A standalone MCP server that enables AI coding agents to create, manage, and interact with Quarkus applications. It runs as a separate process that survives app crashes, giving agents the ability to create projects, control application lifecycle (start/stop/restart), proxy Dev MCP tools, and search Quarkus documentation.

Agent Skills for Linkly AI — search, browse, and read your local documents from any AI coding agent.

AFSIM-SKILL 是一款专为 AFSIM（Advanced Framework for Modeling, Simulation, and Command & Control）仿真引擎设计的 AI 编程助手，让你在 Cursor / Trae / VSCode 中通过自然语言快速生成、调试和优化 AFSIM 场景代码。 AFSIM-SKILL is an AI coding assistant for AFSIM (Advanced Framework for Modeling, Simulation, and Command & Control). Generate, debug, and optimize AFSIM scenario files directly in IDE

Go-based Unraid plugin monitor and control your Unraid system via REST API, WebSocket, MCP, Prometheus, and MQTT. Supports Docker/VM control, real-time metrics, Home Assistant integration, and AI agent tooling.

Build your own AI hedge fund with Claude, Codex, Cursor & OpenClaw. The agent-native skills directory for Trader Dev MCP — write Pine Script, backtest crypto strategies, optimize parameters.

RHO: Evolving Agents in the Dark — Retrospective Harness Optimization via Self-Preference. Improving LLM agents from unlabeled past trajectories (arXiv:2606.05922).

A Kiro power that turns Kiro into a personal study companion for any AWS certification exam

Multi-agent adversarial code review for any coding agent

Local cockpit for Claude Code usage — rate limits, activity chart, one-click skill buttons.

A Kotlin software-engineering benchmark for evaluating coding agents.

[L0 CONSTITUTION] arifOS — constitutional MCP kernel. Law, identity, F1–F13, VAULT999. Judges but never executes. DITEMPA BUKAN DIBERI.

Change management, SkillOpt optimization, and evidence-gated evals for agent skills.

Portable phone-call Agent Skills, apps, examples, adapters, and scheduler recipes for AI agents.

Frappe Flow — native AI agents, tools, and triggers for Frappe

A browser-based UI for Claude Code — chat, run workflows, manage MCP servers, track costs, and orchestrate autonomous agents from a local web interface. Installable as a PWA.

Simple and composable logging for Swift apps, servers, and coding agents.

Hindsight-lite: Agent Memory That Learns lightweight version. Get inspired by hindsight.vectorize.io