Code agents

Find the AI agents in your codebase. Zero config, zero dependencies. Just run npx arkna-scan.

Browser automation API for AI agents — structured page recon, form filling, clicking, and navigation via Chrome CDP

Official Taxida MCP server and developer toolkit for cab search, booking, and trip workflows.

Persistent sequential thinking MCP — chain-of-thought reasoning that survives sessions, resumes across agents, and saves conclusions as plan artifacts. Powered by ZeroDB. Zero-config: agents self-provision a ZeroDB account on first run, no signup required

The local-first falsifiable decision ledger — MCP server that turns an Obsidian vault into a compounding decision system with multi-model AI council dissent and outcome-driven refutation propagation.

CLI tool to scan codebases for LLM SDK usage, AI frameworks, and exposed API tokens

Install PM Council — five AI strategists that argue about your product decisions — into Cursor or Claude Code.

Core engine for AgentVoy — framework adapters, deployment targets, DevTools generators, and guardrails config

Security-focused `SKILL.md` packs for reviewing and hardening LLM systems.

A2A (Agent-to-Agent) protocol wrapper for OpenCode. Drop a JSON config file in, get a fully-spec-compliant A2A server out. Supports any agent persona, MCP tool servers, SSE streaming with polling fallback, context building, and multi-turn conversations.

LLM-first test layer for AI coding tools. https://tailtest.com

Text processing toolkit with 12 MCP tools for AI assistants - case transformation, encoding, hashing, text analysis, smart diff, and notes management

<p align="center"> <picture width="200"> <source media="(prefers-color-scheme: dark)" width="172" srcset="https://github.com/ComposioHQ/composio/blob/fix/docs-images/js/docs/assets/Composio-Logo-dark.svg"> <img alt="Text changing depending on mo

AI prompt injection defense scanner for agents. 25 phases covering HTML obfuscation, encoding attacks, semantic similarity, behavioral anomaly detection, multi-step attack chains, supply chain worm detection, and more.

Agent Skills for the truval.dev API

Free AI agent code hygiene checker. Scans for hardcoded LLM keys, shared credentials, and long-lived agent permissions in TypeScript, JavaScript, and Python projects.

Your unified workspace for building and debugging AI agents

NodeMind AI dev agent CLI

Generate visual AI automation workflows from Claude, Cursor, Windsurf, Cline, or any MCP-compatible client. Describe a business process, get an interactive workflow map you can edit and share.

Postals — the agent skill that turns any AI into a direct mail machine. One MCP tool call mails a physical handwritten postcard (real pen-and-ink, USPS 3-5 day delivery, $4.99 per card). Works with Claude Desktop, Cursor, Claude Code, OpenClaw, n8n, LangC

Security co-pilot for AI agents. Scan for vulnerabilities, verify governance, and generate compliance reports during development.

Generate MCP servers from natural language descriptions, OpenAPI specs, database schemas, GraphQL, or ontologies. Supports 10+ LLM providers via Vercel AI SDK.

Agent-friendly CLI for the Hyperliquid DEX — market data, trading, and account management

ScoutAgent — no-code agent builder plugin for CMDOP

Open-source coding agent inspired by Claude Code. Multi-provider (Anthropic/OpenAI/Ollama), streaming tool execution, MCP support.

Complete starter kit for bootstrapping AI agent companies. Three-layer verification, 27 skills, GSD v1 execution, self-learning CLAUDE.md.

Multi-user AI group chat via MCP — let your AIs talk to each other

Multi-agent orchestration CLI powered by Claude Code

Best in class open source LLM router across 47+ providers with Evolution-inspired routing: EXP3 diversity, MVT rate-limit rotation, optimal defense theory verification.

Neruva MCP -- proprietary memory + grounding substrate for AI assistants (Claude Desktop / Claude Code / any MCP client). Typed Records store, document knowledge graph with exact multi-hop traversal (ownership/relationship tracing), semantic + structural

> **Record the vibe of your build** — A revolutionary Model Context Protocol (MCP) server that captures key development moments, enables **multi-agent traceability**, provides **intelligent context curation**, and facilitates **seamless agent-to-agent han

Multi-agent YAML workflow engine — 267 CN + 184 EN + 5 more language libraries of AI roles, auto DAG parallelism, zero code. One sentence → multiple AI roles collaborate → complete plan in minutes. 11 LLM providers, 7 need no API key.

Core memory palace engine for AgentRecall

Memory Palace MCP server for AI agents

Jack into any OpenAPI spec and rip a full-featured CLI with AI-agentic workflow automation

SDK for AgentRecall — persistent, compounding memory for AI agents

Long-term memory engine for AI agents

HITL infrastructure for AI agents. Your agent calls awaitHuman(), a human reviews via Slack/email/dashboard, agent resumes with a typed response.

Run N LLMs in parallel, keep the best answer. Confidence-scored ensemble merging beats sequential fallback on latency and quality. 40-60% token savings built in.

ASG Pay MCP Server — 18 AI agent tools for Claude, Codex, Cursor, and Gemini CLI. Create virtual cards, fund wallets, manage spending, onboard agents via Model Context Protocol.

Memory OS for AI coding agents. Local-first persistent memory with an upgrade path to projects, teams, and cloud sync.

Your AI workforce. Every user gets an AI manager that runs their team — finance, marketing, engineering, operations — for the cost of API calls.

SDK for Pathlight — visual debugging and observability for AI agents

Security co-pilot for AI agents. Scan for vulnerabilities, verify governance, audit MCP servers, and generate compliance reports — all from Claude, Cursor, or any MCP client.

MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,

AINative ZeroDB Memory MCP Server - 18 tools for agent memory: 9 memory + 5 write-back (Slack, Gmail, Calendar, GitHub, Notion) + 4 plan artifacts (persistent plans/PRDs across sessions with diff history). Auto-context middleware. Production-ready for Cla

The security layer for AI agents — platform-agnostic threat detection with 300+ rules, runtime blocking, and remediation guidance. Continuous protection.

Background check for AI agents — discover, assess, and test before you ship

Real-time debug dashboard for multi-agent AI systems — topology graph, LLM turn inspector, tool call traces, memory panel, run history, replay, and webhook alerts

ATP (Agent Trust Protocol) security integration for OpenClaw agents

MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,

The `@anyparser/core` Typescript SDK enables developers to quickly extract structured data from a wide variety of file formats like PDFs, images, websites, audio, and videos.

End-to-end reliability testing for multi-step AI agent workflows. Tests what DeepEval and Langfuse can't: cascading failures across 10+ step chains.

Visual debugger for AI agent loops. Step-by-step. Locally. Zero config.

TypeScript client for total-agent-memory (server v8.0+) — local-first MCP memory layer for AI coding agents

Multi-agent YAML workflow engine — 211 AI roles, auto DAG parallelism, zero code. One sentence → multiple AI roles collaborate → complete plan in minutes. 10 LLM providers, 7 need no API key.

Universal Context Graph for AI Agents — persistent memory with user isolation, sub-50ms retrieval

AI agent security platform — scan, fix, monitor, and pentest MCP servers, Claude skills, Codex plugins, Cursor extensions, and 5 more platforms. 227 rules across 17 threat categories.

MCP server that gives LLMs live, version-pinned documentation from 57+ AI/ML libraries. Eliminates hallucinations about APIs.

Monitor your AI agents. Track cost, latency, and errors in two lines of code.

Visual debugger for AI agent loops. Step-by-step. Locally. Zero config.

Monitor your AI agents in 2 lines of code — heartbeat watchdog, loop detection, cost tracking, auto-restart

Time Machine SDK for AI Agent Observability — capture, debug, and replay AI agent executions

Elite Kotlin AI reviewer for production-grade code analysis

Scaffold a full AI engineering team into any project — personas, wired and ready in 60 seconds.

OpenGAP — the Git Agent Protocol: a framework-agnostic, git-native standard for defining AI agents

Debug LangGraph/LangChain agents offline with cassette record/replay + token & cost logging.

Standalone Agent Gateway for AionUI remote ACP sessions (OpenCode, Claude Code, Flowise, LangGraph)

AI-powered rules-based code review CLI using LangGraph

LangGraph BaseStore adapter backed by Flair — durable agent memory with crypto-pinned identity, federation, and cross-orchestrator portability.

AgentDrive CLI — cross-agent artifact workspace with provenance and portable storage across Claude Code, Codex, Cursor, and LangGraph.

Framework-agnostic commercial integration package for AIOS with Firebase Auth, Stripe billing, and LangGraph integration. Works with any JavaScript environment.

Deep Agents CLI skill for LangGraph Deep Agents

AI-powered rules-based code review CLI using LangGraph

CLI tool that autonomously converts React web projects into production-ready React Native (Expo) apps using AI and LangGraph agentic workflows.

Create VS Code Chat participants (agents) with LangChain/LangGraph: tool-calling and streaming bridge for LanguageModelChat.

Senior Security Auditor AI agent — performs thorough read-only security analysis of codebases. Identifies vulnerabilities, assesses risk via CVSS scoring, maps compliance gaps, and provides actionable remediation. Built with LangChain, LangGraph, and Groq

Autonomous coding agent with MCP, LangGraph and Docker - npm wrapper

LangGraph Multi-Agent Automated Testing Suite for Node.js/TypeScript — 8 AI agents that analyze, test, review, secure & document your project. OWASP Top 10, Zero-Day scanning, 100+ vulnerability patterns.

Catch silent failures in your AI agents. TypeScript SDK for Pisama, the failure detector for vibe-coded agents (Cursor, Claude Code, LangGraph, Vercel AI SDK).

OpenSWE CLI - Unified CLI tool for running OpenSWE CLI + LangGraph server

SPARK Method - Production-Ready AI Agents with LangGraph TypeScript

Pluggable visual debugger for LangGraph-based agents.

Embeddable workbench for LangGraph Agent apps — edit, run, debug, and monitor in one place

WAVE Agent Developer Kit — build AI video agents with 10 MCP tools, 5 templates, and framework adapters for Mastra, LangGraph, LiveKit

AI-powered task orchestration with LangGraph single-orchestrator architecture, 150+ MCP tools, and LangChain function calling. Submit development tasks via Copilot Chat.

MCP server for AgentDrive — cross-agent artifact workspace with provenance and portable storage across Claude Code, Codex, Cursor, and LangGraph.

A library to accelerate REST agent app development on top of Express, enabling users to focus on Langgraph agent development.

OpenAPI-based multi-target code generation CLI for Kubb, Python types, and LangGraph tools

AI Terminal Assistant - LangGraph-based CLI with multi-provider support

Agent code for the Autonomous Formulation Lab

AWS IoT Device Defender Agent SDK

Agentic DevOps Tool for automating and managing various DevOps tasks and configurations.

A package for generating technical articles from project codebases using LLMs

This code provides a new storage engine for DURUS, an excellent persistence system for Python

Identifying focal full methylation of cell subpopulation and inferring fraction

DDD Expert skill for Claude Code - guides users through Domain-Driven Design

Dependency manager for the Claude ecosystem — rules, skills, agents, commands, hooks, MCP servers.

ClaudePy: high-compatibility Python rewrite of Claude Code

CoderGPT