Javascript agents

Express binding for @langgraph-toolkit/core: SSE middleware and graph router.

Fastify plugin for @langgraph-toolkit/core: graph routes with native SSE.

Optional community model provider presets for Langgraph-Toolkit, including Hugging Face and OpenAI-compatible open-source deployments.

Deployable LangChain and LangGraph runtime for Inupedia Spotlight

Database checkpointers for @langgraph-toolkit/core: SQL (SQLite/Postgres/MySQL), Redis, MongoDB. Drivers are injected, so no database library is a hard dependency.

Leatop CDP AI Agent - Vue 3 智能对话组件库

A real design engine for your AI agent: generate designs and print-ready PDFs, over MCP.

Piardify AI Agent CLI & Executable Function Package

MCP server for Lightdash semantic-layer, organization-audit, content-reader, content-developer, content-governance, ai-agent-ops, ai-agent-chat, and data-analyst profiles.

Partner SDK for the Asterisk AI Agent Gateway realtime protocol v1

AI-agent-agnostic documentation-map generator for FE/BE codebases

AI agent CLI with Rust-powered vector intelligence

Cadence - multi-model AI agent in your terminal.

Sync AI agent configurations (skills, agents, prompts) from shared sources into your project's tool directories.

AI agent skills for NodeCoda — teach coding agents to author .ncoda Source and use the NodeCoda MCP service

Terminal UI binary for the Real Memory AI Agent CLI (linux/x64).

`@gea-ai/agent-sdk` is the code-first authoring SDK for GEA Agent applications. It defines main Agents, package-local executable Tools, Skill references, Agent-owned Durable Objects, and secret-free Connector definitions and requirements.

Terminal UI binary for the Real Memory AI Agent CLI (win32/x64).

AI Agentree TypeScript SDK — AI Agent Decision Tracing

Terminal UI binary for the Real Memory AI Agent CLI (linux/arm64).

Terminal UI binary for the Real Memory AI Agent CLI (darwin/arm64).

MCP server for SpecForge - AI agent integration

Terminal UI binary for the Real Memory AI Agent CLI (win32/arm64).

Audit a repo's AI-agent configuration — config, rules, styles, environment — against the AGENTS.md standard (Claude Code, Cursor, Gemini, Copilot, Codex, Kimi, Antigravity, Windsurf).

A Curated AI AGENT OS – Optimized agent skills and add-ons like memB, OpenWiki, Heimdall Token Saver, and Godmode architectures.

A Git-native package manager for AI Agent assets.

Mu, a general-purpose extensible AI agent platform for the terminal and TypeScript

CLI to bootstrap AI-agent-ready Nx monorepos with SDD methodology

Command-line client and AI agent skills for Metrack event metadata management.

BLUN CLI - your own AI agent with a Telegram channel. Get it done. With BLUN.

A self-evolving workflow management system for AI agent development

DeepSeek-native terminal AI agent for digital work — DeepSeek model harness analogous to Claude Code for Claude models.

Install curated AI agent skills for Claude Code, Codex, Cursor, OpenCode, and Kimi: zero dependencies, one command.

Agent-as-data (CHAT-HARNESS L2): Entry primitive, Persona + SettingsStore contracts, pure compilePersona → @adia-ai/agent AgentConfig, versioned persona file import/export.

Unofficial npm bridge for Hermes Agent 0.21.5: The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

Portable AI-agent skill and TypeScript toolkit for creating, editing, rendering, and validating editable PowerPoint presentations.

verglas-pay — give any LLM agent a spending envelope it cannot exceed

A content-addressed, auditable foundation for LLM agent systems.

DeepSeek Harness model provider for virtualized local CLI agents

分层长期记忆 MCP 服务器：本地 MiniLM 或 OpenAI 兼容嵌入 API，供 LLM Agent（DeepSeek Harness / Claude Code）做可语义检索的长期记忆

BridgeNode LLM client — AI inference for AI agents with x402 payment on Solana USDC. No API keys, no registration.

The production framework for self-improving & self-organizing LLM knowledge vaults — grounding invariants, code drift detection, auto-skillification, and 1-click multi-agent setup.

Declarative workflow orchestration for LLM agents — schemas, routers, sub-workflow composition, full audit

The LLM Evaluation Framework for TypeScript

LLM-optimized Figma MCP server.

General-purpose agent with transport abstraction, state management, and attachment support

Lightweight LLM interaction interceptor: proxy + file tail + MCP, emits raw redacted captures

Automatic long-term memory for Vercel Eve agents — Hindsight memory injected before each turn and retained after, with no model tool-calling

A TypeScript SDK to extract and correct JSON from LLM outputs

NestJS-friendly LangChain utilities: decorator-based JSON Schema generation for tool/function calling, a streaming output parser for class-typed tool calls, LLM fallback chains, and an Observable adapter for LangChain streams.

Production-oriented n8n community Chat Model for native Google Gemini and OpenAI-compatible APIs

LangChain-YandexGPT provides an integration of YandexGPT with LangChain for Node.js

Gate any LangChain.js tool or LangGraph.js node on a signed Decionis Decision Dossier.

The canonical read-only local command-line composition for moldea repositories.

LangChain integration package for MLflow Tracing

Pure-JS client and CLIs for Archil disks and sandboxes

A LangChain-based tool to answer questions strictly from PDF content using Groq LLM and local embeddings.

Default model selection shared by Agent entry points

Research-first CLI agent built on Pi and alphaXiv

CLI for local Postgres setup, connecting BD Agent backends, migrate, and doctor

Compile OpenAI Codex plugins into dynamic Eve skills, subagents, and connections.

DeepSeek Harness 外置视觉模型插件：inspect_image 把本地图片或 http(s) 图片 URL 发给任意 OpenAI 兼容端点，视觉模型看图的文字回答直接带回对话；附 Web UI 设置栏。

An independent Codex-based coding agent with Spine context management.

A Codex-style GPT Image 2 generation and editing extension for Eve agents.

Azure OpenAI adapter for Zhivex AI SDK.

Automatic LLM observability. Wrap your client, everything is traced.

Feishu/Lark bridge for OMP coding agent

Evaluate whether AI agents discover and use your skills correctly

An Eve extension that exposes a ChatGPT Enterprise user's authorized connectors as dynamically discovered tools.

多模态视觉 MCP + 文生图 Skill 工具包 (OpenAI GPT-4o · 通义千问 Qwen-VL · Google Gemini · Anthropic Claude)

Multi-model AI perspectives for coding agents - query GPT-5, Claude, Gemini, and Grok simultaneously through one MCP server

Writing agent for HackMD

Open-source agent security framework. Detects and defends against AI Agent Traps - content injection, embedded jailbreaks, RAG poisoning, data exfiltration, and more.

Server-side provider adapters for Charivo

General-purpose agent with tool calling and session persistence

DeFi Liquidity Provider Agent CLI - AI-powered LP management tool

Dr.DOC DMS Integration Package for PI Agent

Combined OpenCode plugin: agent orchestration, subagent throttling, persistent goals, OpenAI-compatible provider auto-configuration, MCP tool aggregation, and skill discovery.

Native Codex plugin for spawning, configuring, and overseeing ours-fleet agents.

Stateful Node.js sessions for Codex, Claude, Grok, Bedrock, and Responses-compatible model providers.

Provider-neutral coding-agent core: a bounded tool-use runtime, local and sandboxed workspace backends, model adapters for Anthropic/OpenAI-compatible providers, and multi-currency cost accounting.

SAP AI SDK integration with the official OpenAI npm package for Azure OpenAI on SAP AI Core

Ada CLI - coding agent CLI (rebranded fork of pi.dev) with read, bash, edit, write tools and session management

Local tool-call failsafe for DSH: blocks a fixed list of high-risk shell patterns and credential-file reads before execution, with a per-session hash-linked JSONL audit log, and an optional external Gateway for centralized policy.

Autonomous AI QA automation agent that transforms product intent into validated Playwright BDD test suites

Framework-neutral contracts and runtime coordination for autonomous application agents.

CLI for managing MultiSig accounts, transactions, and data queries across EVM networks

Let coding agents verify UI changes on real iOS, Android, and web surfaces, then enforce reviewed proof in deterministic CI.

Jefri Chat connector — join the Jefri Chat network (WhatsApp for AI agents) from any MCP client (Claude, Codex, Cursor, …).

Cohort Agent SDK — autonomous AI colleague runtime. Deploy senior AI colleagues on dedicated Mac minis, wired to the Cohort operating surface.

Persistent long-horizon autonomous mission runtime for DeepSeek Harness: dependency DAG, independent verification, replan-on-failure, lease ownership.

Zero-UI MCP Server connecting AI Agents directly to Chrome browser via DevTools CDP & Accessibility Tree

OmO agent harness for Kimi Code CLI

Vercel AI SDK adapter for assistant-ui

<div align="center" style="margin-bottom: 10px"> <a href="https://www.npmjs.com/package/planby"> <img src="https://i.postimg.cc/J0XMPHNQ/planby-logo.png" alt="Planby logo" /> </a> </div>

QuickJS-backed code mode tool for AI SDK

AA Code – AI-Powered Coding Assistant (Kimi, Claude, Gemini, DeepSeek & Codex)

Produced-files turn tail: the deliverables row a finished turn ends with

LaunchDarkly AI SDK OpenAI Provider for Server-Side JavaScript

A collection of round outlined React icons with 1px radius and 1.5px stroke width, designed for use in React applications.