Javascript agents

A Node.js package for multi-LLM agent support

The llm-agent is a TypeScript project designed to facilitate interactions with language models from multiple providers. It supports various LLM API providers that are compatible with the OpenAI API structure, allowing users to manage chat interactions and

Ollama LLM provider (ILlm, extends OpenAIProvider — Ollama's OpenAI-compatible /v1 API) for @mcp-abap-adt/llm-agent.

End-to-end encrypted, agent-portable memory for OpenClaw and any LLM-agent runtime. XChaCha20-Poly1305 with protobuf v4 + on-chain Memory Taxonomy v1 (claim / preference / directive / commitment / episode / summary).

Offline HTTP RAG (Retrieval-Augmented Generation) server for the Red Sift Design System — returns ranked, scored documentation chunks for any LLM/agent to consume.

High-level tool-schema optimizer for LLM agent frameworks. Integrates with LangChain, MCP, Vercel AI SDK.

Markdown wiki template for LLM agent persistent memory. Gives agents cross-session, cross-provider memory.

Local mirror of Anthropic product changelogs + curated cross-product synergies. So the LLM agent inside the harness knows what the harness can do.

MCP server adapter for Agent Bazaar — connects any LLM agent to the marketplace via OAuth

Vue 3 component library that lets an LLM agent render real UI — chat, forms, charts, tables and interactive A2UI surfaces — over the AG-UI protocol.

`uwf-builtin` agent — built-in LLM agent with file read/write and shell tools.

MCP server for GenCraft AI image generation. Exposes generate_image / get_task / batch_get_tasks tools to any MCP-compatible LLM agent (Claude Desktop, Cursor, Cline, …).

Improve, rewrite, debug, evaluate, and compress prompts for any LLM agent. Ships an installable Skill plus a deterministic local CLI.

Core SmartAgent composition runtime. Builder, agent runtime, pipeline, sessions, history, resilience, observability, plugins, skills.

Default SmartAgent implementation with LLM providers, MCP client, HTTP server, and CLI.

Manage configuration profiles for LLM agent tools

Agent-native Figma operations platform. Run 29 Figma operations from any LLM agent at ~230 tokens per call.

MCP client wrapper, adapter, factory, and connection strategies for the SmartAgent runtime.

This package handles the browser side of the BlindAgency system: encrypting the user's API key before it leaves their device, managing the encrypted credential across requests, and running the LLM agent loop.

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

huu (Humans Underwrite Undertakings) — guided-execution TUI that runs LLM agent pipelines in parallel git worktrees, with serial reproducible merges stage-by-stage.

RAG and embedder composition for the SmartAgent runtime.

MCP server for prompt-to-JSON contracts, JSON Schema validation, and structured LLM/agent outputs.

Production LLM agent sidecar + Claude Code skill library for building, testing, and running tool-calling agents.

HermesHandler is a lightweight, framework-agnostic message router for browser extensions and event-driven systems, with strict {ok,result,error} envelopes, timeouts, cooperative cancellation, and safe normalization. Ideal for reliable LLM agent backbones.

Hydration and loaf-weight calculator for the Zojirushi BB-PDC20 (and similar 2-lb bread machines), with an LLM-agent-friendly API.

Lightweight CLI for DataForSEO keyword research, optimized for LLM/agent use

Quickly scaffold a TypeScript-based LLM agent application with local or remote AI models

LLM-agent-optimized CLI for syncing, searching, and browsing OpenClaw documentation locally

llm plugin for SkynetXBT

Semantic filesystem operations for LLM agent frameworks with natural language understanding. See LLM_AGENT_GUIDE.md for copy-paste examples.

Spark Bitcoin L2 wallet skill for AI agents — encrypted-at-rest seed storage, Lightning interop, L402 paywall payment, BTKN/LRC20 tokens. Works with Claude Code (via plugin marketplace) and any other LLM agent framework (via the npm package's getSkillCont

OpenAI integration for computer-agents SDK. LLM agent runtime and OpenAI API support.

A framework for tracing, tracking and evaluating LLM agent pipelines

Image generation skill for Claude Code, Codex, OpenClaw and any SKILL.md-compatible LLM agent. Wraps api.letmego.top (GPT-Image-2).

Flip AI CLI — incident root-cause analysis CLI for SREs and developers. Observability-aware (Datadog, Splunk), LLM agent loop, terminal UI.

Turn a function into an `http.Agent` instance

⚡️ AI 系统测试框架 — 面向 LLM/Agent 的轻量断言测试工具，AI 界的 Vitest

Query your local WeChat data from the command line. Designed for LLM agent tool calls.

Typescript bindings for langchain

LLM-agent native GitLab explorer CLI

Three-skill kit for spec-driven development: brainstorm an idea into a spec, turn the spec into an executable plan, hand the plan off to another LLM agent.

Framework-agnostic LLM agent evaluation harness

ZakoBot core — bot engine, LLM agent, plugin loader

Public MCP server for Ordering.Tools — discover venues, read menus, prepare orders. Used by Claude Desktop, Claude Code, OpenAI Apps in ChatGPT, and any MCP-compatible LLM agent.

Lightweight, purely-functional LLM agent framework for the MCP era.

Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.

LLM Agent Chat History Retrospect Application

A tool library for LLM agent in browsers to interact with the web.

TypeScript LLM agent framework: ReAct loop, tool calling, MCP, multi-agent workflows, memory, guardrails. Anthropic Claude, OpenAI, Ollama via fetch — vendor-neutral, zero SDK deps.

A agent component for Convex.

Headless workflow engine with LLM agent orchestration

An HTTP(s) proxy `http.Agent` implementation for HTTP

An HTTP(s) proxy `http.Agent` implementation for HTTPS

Site-level browser automation — deterministic CLI workflows for Chrome, optimized for LLM agent consumption.

Shopify MCP Server for LLM Agent Integration

Maps proxy protocols to `http.Agent` implementations

一个轻量、高效、模型无关的 LLM Agent 框架，采用 ReAct 单调用循环架构

Datadog LLM Observability exporter for Mastra - exports tracing data to Datadog's LLM Observability product

Framework-agnostic safety helpers for tool-calling LLM agent loops.

Sulcus reactive, thermodynamic memory sidecar — MCP server for Claude Code, OpenClaw, and any LLM agent. Local-first, zero-config.

Global HTTP/HTTPS proxy configurable using environment variables.

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

MCP server for iBitLabs — live receipts from a public $1k → $10k AI trading experiment. Exposes balance, contributor ledger, adopted shadow rules, and saga chapters as callable tools so any LLM agent can cite real fills instead of hypothetical backtests.

A SOCKS proxy `http.Agent` implementation for HTTP and HTTPS

A PAC file proxy `http.Agent` implementation for HTTP

Manage configuration profiles for LLM agent tools via direnv

Provider-agnostic LLM agent framework. One LLMProvider interface, two adapters (Anthropic + OpenAI-compatible), tool loop, router/specialist orchestration, streaming, confirmation gate, typed errors, retry, channels. Zero runtime dependencies.

LLM agent evaluation framework — define agent behaviour in YAML, evaluate against multiple models, compare results

开箱即用的 LLM Agent SDK — 配个 API Key 就能跑

A conversational AI-driven telecom multi-agent system for managing call balances, push notifications, marketing, targeting, and sales.

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

Standalone async parallel tool execution for any LLM agent

AgentKit is a framework for creating and orchestrating AI agents and AI workflows

Core primitives for llmtxt: compression, validation, patching, progressive disclosure, signed URLs, and attachment helpers for LLM agent content workflows

Enforce real-time token budgets and spending limits for OpenAI, Anthropic Claude, and Google Gemini API calls in Node.js

Standalone prompt agent powered by OpenAI SDK.

Paperclip adapter for Hermes Agent — run Hermes as a managed employee in a Paperclip company

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

SDK for building AI agents with Claude Code's capabilities. Programmatically interact with Claude to build autonomous agents that can understand codebases, edit files, and execute workflows.

A coding agent friendly reporter for playwright, so that your coding agent finally really understands what is going wrong

Next.js chat UI with assistant-ui, AI SDK, agents, and skills

HTTP daemon and CLI for agent-driven browser extension testing with Playwright

[](https://www.npmjs.com/package/@aws-sdk/middleware-user-agent) [](https://www.npmjs.c

LangChain tool wrappers for on-chain blockchain analysis. Exposes [OpenScan](https://github.com/aspect-build/openscan) algorithms and utilities as structured LangChain tools that any LLM agent can call.

Provider-extensible CLI search bridge for LLM agent workflows

Local AI assistant: 80 tools (Gmail, Calendar, Drive, GitHub, Slack, browser, code, files), 38 agents, visual workflows (Studio, AWF, WebCraft). Install with `npm i -g nothumanallowed`, run with `nha ui`. Free tier built-in (Liara), no API key required. Y

MCP server for shipsite.sh — deploy static sites from any LLM agent

MCP server that lets any LLM agent (Claude Desktop / Cursor / OpenAI Agents SDK) buy products on JPYC EC Platform via x402 — gasless EIP-3009 payments over HTTP.

Get a user agent string across all JavaScript Runtime Environments

AI-powered chat and tool execution for Open Mercato, using MCP (Model Context Protocol) for tool discovery and execution.

A ready to use http and https agent for working with proxies that keeps connections alive!

🤖/👨‍🦰 Recognise bots/crawlers/spiders using the user agent string.

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

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

Old abstractions from LangChain.js

Lightweight, zero-dependency LLM API cost & token usage tracker for OpenAI, Anthropic, Gemini, Mistral, Groq, and DeepSeek

[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-browser) [](https://www.n

Florentine.ai MCP server – query MongoDB & MySQL databases in natural language

Optimize web pages for LLM agent interaction and understanding