Custom agents

UXCascade: Scalable Usability Testing with Simulated User Agents

Generate production-quality Dify workflow DSL files with precise Pydantic-based node schemas

Long-term memory for AI coding agents — local-first, privacy-absolute, works everywhere.

A one-file door-guard for coding agents — first-class on Claude Code (permissionDecision deny); portable to any agent with a blocking pre-exec hook.

Safe bridge between AI agents and Web3 transactions. Open-source React kit + protocol with anti-phishing UI patterns built in.

AgenticART (Android Runtime) automates Android penetration testing and generates exploitation sequences with execution verified annotations. The purpose is to test the extent in which human guidance is needed for LLM-powered vulnerability discovery.

Open-source memory for AI agents. MCP-native. Self-hosted. One Docker image.

Local-first AI memory system for coding agents: desktop app, CLI, and MCP server for durable project context, handoffs, recall, and task continuity.

Collection of Claude code snippets for research,learning and AI development reference

🎬 Turn any idea into a scroll-stopping video script in seconds. AI agent prompt optimized for YouTube, TikTok, Reels & educational content. Supports English & Arabic.

Benchmark tool for evaluating Memvid on the LoCoMo (Long-term Conversational Memory) benchmark.

A simple way for open source maintainers to request recognition from AI coding agents

AI Agents: A Comprehensive List of The Best AI Agents

Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models.

Ai-Agent Builder is a production-grade, "backend-less" single-file web application for authoring, configuring, and packaging AI agents. It runs entirely in the browser — no server, no API keys stored, no telemetry — making it invisible to trackers and safe for enterprise environments.

Portable encrypted context state for AI sandboxes and VMs

Curated list for policy-as-code, audit, agents, and LLM safety.

The Graph for Kaspa — AI-native subgraph indexer with GraphQL + MCP + KasStream + WebSocket. KIP-20 Covenant IDs first-class, native KRC-20/KRC-721, BlockDAG-aware reorgs.

A self-hosted, containerized platform for AI agents, exposed as Capability Packs — schema-validated, one-shot JSON tools — and native MCP. The defining metric is ≥90% pack success on 7B–30B-class open-weight models, something no frontier-targeting competitor is optimizing for.

Compression Runtime for Universal eXecution — a 60–95% token reducer for AI coding agents (Claude Code, Cursor, Cline, …). Single Rust binary, SQLite, 11 layers, local-first.

Open reference implementation: agent identity + routing at the web edge (Ed25519 + ES256/JWKS). Python & Node.

OmniHarness is an open-source super agent harness that orchestrates sub-agents, persistent memory, and sandboxed execution to handle tasks that take minutes to hours — powered by extensible skills and MCP tools.

The successor to ds2api

See and drive any Mac app from your terminal or your AI agent.

A extension chrome mcp server allow AI agent full remote same playwright

Directs AI to follow git workflows, use diffs to prevent hallucinations, resolve dependencies cleanly and avoid silencing linters or other undesirable workarounds.

Evaluate AI agents with Unix-style pipeline commands. Schema-driven adapters for any CLI agent, trajectory capture, pass@k metrics, and multi-run comparison.

MCP server for AlbumentationsX image augmentation workflows

End-to-end AI hackathon platform enabling users to train ML models, deploy AI agents, and get evaluated via an automated leaderboard and intelligent AI judge system.

AI agent steering for Apple (Swift 6.4 / SwiftUI / visionOS / Foundation Models) and Android (Kotlin / Compose / Gradle / Gemini Nano). Rules + skills + MCP for code, a11y, localization, TestFlight/Play. One install.sh detects your stack, installs the right per-platform rules, and keeps them current for Claude/Copilot/Cursor/Gemini/Codex/Kiro.

The first decentralized prop firm for AI agents — on-chain, oracle-settled prop-trading fund any autonomous agent can eval into, get funded, and trade. No backend, no admin.

Local-first permission gateway for AI agents: connector-based SSH, Postgres, and Redis access with scoped tokens, human approval, audit logs, and encrypted local credentials.

The relationship file for human–AI collaboration.

The open schema for multi-agent workflows — define agents, roles, models, skills, tools, access policies, and handoffs in a single versioned document.

GovRider MCP Server - Match your tech product or consulting service to thousands of live government tenders, RFPs, grants, and frameworks from 25+ official sources worldwide

A governed, auditable workflow engine for an agent-driven software factory.

ELDA CLI：嵌入式Linux驱动开发Agent，包含PDF解析、硬件信息抽取、设备树构建、内核裁剪与配置、驱动源码编写、内核编译与部署等工具，可根据需求进行定制化工作流编排。

An engineering harness for AI coding agents — spec-first, TDD, multi-perspective review, clean commits.

Multi-provider persistent memory and orchestration backend for AI coding agents via MCP

Deep dive into Oracle Skills — เจาะลึกทุก skill ที่ Oracle ใช้ได้ พร้อมตัวอย่างจริง

Short paper (extended abstract) for PEARC26 conference on agentic workflows and HPC

A tiny, tool-agnostic convention for the context you give your coding agents.

The ultimate collection of native, high-performance skills for the Antigravity IDE. Supercharge your AI agent with strict TDD, GDPR security audits, and zero-to-SaaS architecture workflows.

Self-hosted MCP gateway with authorization, credential injection, audit logging, and output policies. Includes DADL — describe REST APIs as MCP tools in YAML.

Structured CI failure summaries on PRs + compact test/build logs for AI agents. GitHub Action, CLI, MCP.

MCP Server for AnythingLLM — Workspace, Chat, Document, and System management

分级开发工作流路由（L0–L4）的 Claude Code / Codex / Cursor 插件：判级加固、跨 session 续行、跨项目自主进化、codegraph 判级集成。skill 命令 /dev-workflow。

All releases & release notes for Atlarix

Same answer, fewer tokens — KO-first LLM output-compression skill for Claude Code & Codex. A Korean-native caveman alternative, measured on real session output_tokens.

vibestack is a portable skill pack for AI coding agents. Slash commands like /office-hours, /ship, /investigate, /tdd, /review install once and work across every agent that supports the Agent Skills open standard — Claude Code, Cursor, Kiro, and a growing list of others.

A Minimal Engineering Harness

vMux is the Windows-native cmux/tmux alternative for AI coding agents. Run Claude Code, Codex and others side by side with tmux-style splits, git worktree isolation, ConPTY terminals, MCP support and built-in localhost preview. Built on Electron and React.

OpenClaw plugins that add A2A compatibility and enable communication with other A2A-compatible agents.

Node.js CLI and TypeScript client for the Clawrma solver network — delegate web, search, and inference tasks to distributed solvers

Multi-session browser MCP for AI agents. 36 tools. 15 parallel sessions. Stealth. Self-improvement. Up to 10x fewer tokens.

MCP server for Booking.com - let AI agents book hotels

Best SKILL.md marketplace & manager for genetic ai development, a needed extention to make AI actually useful! Discover, visualize, and synchronize SKILL.md files across your workspace seamlessly.

Reliability Gateway for MCP Servers. Detect null responses, schema mismatches, timeouts, and silent failures before they reach users.

Nigerian & African AI agent governance policies for Microsoft AGT — NDPA 2023, CBN, NFIU/AML, BVN/NIN, POS geo-fencing, POPIA

agentcentral hosted Amazon MCP server, Amazon Seller Central MCP server, and Amazon Ads MCP server metadata for Claude, ChatGPT, Cursor, and HTTP-capable MCP clients

Production-grade Machine Learning, Data Science & MLOps skills for AI coding agents (Codex, Claude Code, Cursor, OpenCode). One npx command to install.

Open-source AI skill that turns a process interview into a professional BPMN swimlane diagram (.drawio). AS-IS with pain points, TO-BE with Quick Win / Full Automation.

🛒 Connect AI agents to Walmart's ecosystem using the Model Context Protocol for real-time data access and enhanced product search capabilities.

Sally Skill: The metabolic brain for your AI agents. 64+ biomarkers, real-time CGM, and TCM insights into OpenClaw, Claude, Hermes, and more via MCP/REST integration.

给历史研究者的中文文献 OCR 校对与阅读 pipeline · Agent-native OCR, collation & reading workflow for historical Chinese scholarship — works with Claude Code, Codex, Gemini CLI, Cursor & Hermes agents

CLI package manager for Claude AI agent skills

Convert any URL to clean Markdown. Cloudflare Worker with 14 site adapters, MCP Server, Agent Skills, llms.txt. Open source, Apache-2.0.

Extension pack for OpenSpec adding autonomous 7-phase implementation workflows, specialized agents, and utility skills for AI coding assistants.

Deterministic decision records for agents and humans alike

Claude Code agents for WordPress developers.

A curated list of services, APIs, and infrastructure built for AI agents

A Agentic Machine Learning, local-first tabular ML discovery workspace. Hand a goal to the AI Autopilot a multi-agent system that runs the full CRISP-DM lifecycle.

The Kubernetes of AI Agents — A production-grade operating system for multi-tenant agent orchestration, featuring gVisor isolation, OPA policies, and deterministic execution replays.

AI-powered spec-driven development framework with 26+ specialized subagents, mandatory TDD, immutable architectural constraints, and automated quality gates — enforcing zero technical debt from ideation to release.

End-to-end testing for voice agents. YAML scenarios, real audio through LiveKit/Daily/VAPI/Retell, and 13 evaluators for latency, tone, and roleplay consistency.

A single source of truth for AI coding context, kept consistent across Claude Code, Cursor, Copilot, Gemini, and more as your stack evolves.

Operational continuity protocol for AI agents

Open strategy frameworks for AI agents — 11 skills in SKILL.md format that turn any LLM into a strategy thinking partner. CC BY 4.0.

Agent-agnostic harness + one-line install for Monet — local-first, MCP-native memory for coding agents.

OutplayArena is a platform to facilitate game-theoretic analyses between AI agents, and, optionally humans.

Claude Code skills for people who ship alone. 7 bilingual (EN+中文) skills for solo founders and indie devs: launch tweets, customer emails, decision frameworks, postmortems, and more.

Makes a company, product, book, or personal brand legible, desirable, and inevitable, then writes the copy to match. An agent skill built on the Ekram Method.

A Claude skill making the model an expert in Apple's container CLI — run Linux containers & persistent Linux machines on Apple silicon. Benchmarked: 100% vs 68% vs plain Claude.

Automatically generate llms.txt and llms-full.txt files for Laravel applications to help AI models and LLM crawlers understand your website.

Build agent-ready APIs without splitting your server model. Define tools once, expose them as both HTTP endpoints and MCP tools.

A Rust CLI SDD tool that transforms feature descriptions into structured specs, plans, and tasks — then lets your AI agent build them

Pull requests for AI memory.

Sandboxed HTTP client with SSRF protection for AI agents. Prevents DNS rebinding, blocks private IPs, and validates every connection — available as a Rust crate and npm package.

让 AI 编程可交付、可审查、可追踪 — 给 Claude Code / Cursor / Codex 加一层规格驱动工作流

Outlit SDK

Agent Native CLI for publishing Markdown to X Articles with DraftJS, media upload, and OAuth2 PKCE.

See what your AI coding agent silently drops from its instruction files. A byte-exact truncation X-ray for AGENTS.md / CLAUDE.md / .cursorrules.

Engine-agnostic JSON dataset of game mechanics with typed relationships, scope metadata, validation tools, static browser, and Mechanic Mixer.

A Federated Multi-Agent System (MAS) architecture for Google Antigravity. Orchestrates specialized AI Skills (Backend, DevOps, Frontend) using the Google ADK and A2A Protocol.

Universal finder for local AI agent conversations (Codex, Claude Code, OpenCode, Hermes)

Contexer is not a chat memory tool. It is the engineering decision layer for AI coding agents, capturing architecture decisions, constraints, conventions, and patterns so engineering knowledge becomes a shared organizational asset instead of disappearing inside AI conversations.

Deploy Executor (open-source agent integration layer) to your own Cloudflare account in one command, private behind Cloudflare Access. Built with Alchemy.

帮助用户从零写出高质量 PRD，或评估/改进/增量更新已有需求文档。本技能按三视角（用户 / 商业 / 技术）完成诊断，分 **概念版** 与 **落地版** 写入工作区，并系统补全交互状态、数据规范、文案与关键页线框等细节，使文档可直接用于研发实现或 AI 生成代码。

Autonomous closed-loop IoT visual monitoring: an LLM agent turns plain-English goals into capture schedules, sends them over MQTT to a bare-metal STM32U5, and analyzes frames with cloud and self-hosted VLMs. Bachelor thesis (Maastricht University): 6-backend VLM benchmark + a cross-provider t=0 constraint-drift finding.