Category

Agent frameworks & infrastructure

46,465 agents

Every agent in Agent frameworks & infrastructure, page 272 of 465

@self-evolving-harness/kivo

KIVO — Agent 知识平台,覆盖知识提取、存储、检索、迭代、调研、图谱、工作台全生命周期

@langwatch/server

Run LangWatch locally with one command — `npx @langwatch/server`. Complete LangWatch stack: observability, evaluations, AI gateway, agent simulations.

@rozenite/agent-bridge

React hook API for registering agent tools in React Native

@hyperspaceng/neural-agent-core

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

llm-polyglot

A universal LLM client - provides adapters for various LLM providers to adhere to a universal interface - the openai sdk - allows you to use providers like anthropic using the same openai interface and transforms the responses in the same way - this allow

infinity-agent

Creates HTTP/HTTPS Agent with Infinity maxSockets

@typia/utils

Superfast runtime validators with only one line

@dudko.dev/agent

Tool-using planning agent over MCP servers, built on the Vercel AI SDK.

agent-hub-llm-sdk

Generic LLM provider SDK with local tool execution for OpenAI-compatible APIs

@mondaydotcomorg/atp-vercel-sdk

Vercel AI SDK integration for Agent Tool Protocol.

@goyamegh/agent-health

Agent Evaluation and Observability Framework

@cool-ai/beach-protocol

Envelope shape, canonical part-type registry, and Agent Card for Beach applications.

agent-inspect

Local evidence debugger and trajectory-test toolkit for TypeScript AI agents — execution trees, TraceContract checks, Evidence v2, and read-only MCP

dance-of-tal

Dance of Tal — Agent Manager for Agentic AI. CLI for managing AI agent personas, rules, and workflows.

recursive-llm-ts

TypeScript bridge for recursive-llm: Recursive Language Models for unbounded context processing with structured outputs

@toon-format/toon

Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts

@grafana/llm

A library for working with LLMs in Grafana plugins

@mondaydotcomorg/atp-runtime

Runtime SDK injected into sandbox for Agent Tool Protocol

llmz

LLMz - An LLM-native Typescript VM built on top of Zui

@amodalai/core

Amodal agent runtime core

@lmstudio/sdk

LM Studio SDK

@foxxytux/buddy-agent-core

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

aiyu-multi-agent

AI Agent Platform — 84 Agents, 46 Skills, 78 Workflows, 14 Tools, 5 LLM Providers (OpenAI/Claude/Groq/Ollama/Mock), Smart Init, Frontmatter Task Runner, Plugin System, Agent Testing, Publishing

@openrouter/sdk

The OpenRouter TypeScript SDK is a type-safe toolkit for building AI applications with access to 400+ language models through a unified API.

@kolisachint/hoocode-agent-core

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

deepagents

Deep Agents - a library for building controllable AI agents with LangGraph

@posthog/pi

PostHog LLM Analytics extension for pi coding agent

@newrelic/native-metrics

A module for generating metrics from V8.

@zhixuan92/multi-model-agent

Standalone HTTP server for multi-model-agent. Routes tool-invocation work to Claude, Codex, or OpenAI-compatible sub-agents with async-polling REST dispatch and installable skills for Claude Code, Gemini CLI, Codex CLI, and Cursor.

@nlux/core

nlux is JavaScript and React library for building conversational AI interfaces, with support for OpenAI, Hugging Face, and more.

@llm-ui/json

[llm-ui](https://llm-ui.com) JSON blocks for building custom components.

@fede0089/skill-eval

CLI to evaluate agent skills triggering and functionality

@octoryn/cli

Octoryn LLM official command-line interface

@aabadin/project-memory-context

Portable project memory context CLI — bootstraps semantic enrichment workflows for any AI coding agent.

byterover-cli

ByteRover's CLI

newrelic

New Relic agent

@dwmkerr/mock-llm

Simple OpenAI compatible Mock API server. Useful for deterministic testing of AI applications.

@ikunin/sprintpilot

Sprintpilot — autopilot and multi-agent addon for BMad Method v6: git workflow, parallel agents, autonomous story execution

promptfoo

LLM eval & testing toolkit

@mondaydotcomorg/atp-client

Client SDK for Agent Tool Protocol

promptmetrics

Lightweight, self-hosted prompt registry with versioning, metadata logging, evaluations, and multi-tenant observability

cacheable-lookup

A cacheable dns.lookup(…) that respects TTL

llm-info

Information on LLM models, context window token limit, output token limit, pricing and more

keep-alive-agent

a keep-alive agent for http and https

@anthropic-ai/claude-agent-sdk-linux-x64-musl

Native CLI binary for @anthropic-ai/claude-agent-sdk on linux-x64-musl

@google/genai

[![NPM Downloads](https://img.shields.io/npm/dw/%40google%2Fgenai)](https://www.npmjs.com/package/@google/genai) [![Node Current](https://img.shields.io/node/v/%40google%2Fgenai)](https://www.npmjs.com/package/@google/genai)

mem0ai

The Memory Layer For Your AI Apps

pocketflow-js

A minimalist LLM framework for building AI agents and workflows with JSON configuration

@cool-ai/beach-llm-mastra

Mastra adapter for Beach's LLMProvider — wraps a @mastra/core Agent so its model + tool runtime drives Beach actor turns.

@agent-context-kit/cli

CLI for agent-context-kit

gm-antigravity

Spool-dispatch orchestration engine with unified state machine, skills, and automated git enforcement

@agentmemory/agentmemory

Persistent memory for AI coding agents, powered by iii-engine's three primitives

@ruvector/rvagent-wasm

rvAgent WASM bindings — browser and Node.js agent execution

@agentesting/agentest

Embedded agent simulation & evaluation framework for Node.js/TypeScript

@havasik/agent-core

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

@viswa-test/test-citation

## Table of Contents

@clinebot/agents

Browser-safe agent runtime for the next-generation Cline SDK

@nlux/react

nlux React is a library for building conversational AI interfaces, with support for OpenAI, HuggingFace, and more.

psadk

ps adk adapter

feather-agent

Tiny, fast, provider-agnostic LLM agent framework (orchestrator, fallback, race, rate limits, retries, streaming, cost, middleware).

@elastic/apm-rum

Elastic APM JavaScript agent

@aictx/memory

Local-first project memory for AI coding agents.

@sammorrowdrums/mcpi-agent

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

@httptoolkit/proxy-agent

Maps proxy protocols to `http.Agent` implementations

@anthropic-ai/claude-agent-sdk-linux-x64

Native CLI binary for @anthropic-ai/claude-agent-sdk on linux-x64

agentkits

Agent Model Layer — One-line LLM access with built-in memory. 29 providers, 18 embeddings, zero lock-in.

synapse-orch-ai

Synapse - A Multi Agent Orchestrator

maestro-agent-sdk

Embeddable TypeScript agent SDK for DeepSeek — built-in tools, skills, memory, and MCP.

deepthink-js

SOTA NPM module for agentic processes using local or cloud LLMs.

@empiricalrun/llm

Package to connect and trace LLM calls.

veil-ai

A transparent, lightweight LLM agent framework

@raindrop-ai/pi-agent

Raindrop observability for Pi Agent — automatic tracing via subscriber or pi-coding-agent extension

@ax-llm/ax

The best library to work with LLMs

@tanstack/ai-code-mode

Secure TypeScript Code Mode for TanStack AI agents to execute sandboxed tool orchestration programs.

ai-sdk-provider-claude-code

AI SDK v7 provider for Claude via Claude Agent SDK (use Pro/Max subscription)

botinabox

Bot in a Box — framework for building multi-agent bots

@kb-labs/llm-router

Adaptive LLM router with tier-based model selection and fallback support.

@forwardimpact/libeval

Agent evaluation framework — prove whether agent changes improved outcomes with reproducible evidence.

@flink-app/fake-llm-adapter

Fake LLM adapter for Flink AI framework - perfect for demos and testing

@newrelic/browser-agent

New Relic Browser Agent

@reportportal/client-javascript

ReportPortal client for Node.js

@napse/phronergo-agent-core

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

@diabolicallabs/llm-client

Unified LLM API for Anthropic, OpenAI, Google, and DeepSeek. Streaming, retry/backoff, structured output, token normalization. © Diabolical Labs

@uncaged/workflow-agent-llm

`AgentFn` adapter that calls an OpenAI-compatible `POST /chat/completions` endpoint using `LlmProvider` from `@uncaged/workflow-runtime`.

minimal-agent

Bun-first 的本地 Agent 内核,支持工具、插件、工作流、上下文压缩、长期记忆与 OpenAI 兼容接口;Tauri 桌面宿主和 Node.js npm 发布可复用同一内核

@relayplane/proxy

Open source cost intelligence proxy for AI agents. Cut LLM costs ~80% with smart model routing. Dashboard, policy engine, 11 providers. MIT licensed.

@elg/coerce-llm-output

[![CircleCI](https://dl.circleci.com/status-badge/img/gh/taneliang/coerce-llm-output/tree/main.svg?style=svg)](https://dl.circleci.com/status-badge/redirect/gh/taneliang/coerce-llm-output/tree/main) [![codecov](https://codecov.io/github/taneliang/coerce-l

@nebulaos/llm-gateway

NebulaOS LLM Gateway provider - OpenAI-compatible chat completions

@mupt-ai/pi-agent-core

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

@pyxmate/memory

SDK for pyx-memory — Memory as a Service for AI agents

llm-checker

Intelligent CLI tool with AI-powered model selection that analyzes your hardware and recommends optimal LLM models for your system

@enfav/agent-engine

Wiring-engine-driven adaptive reasoning engine with declarative, versioned, hot-reloadable artifact configuration

openevals

Much like tests in traditional software, evals are an important part of bringing LLM applications to production. The goal of this package is to help provide a starting point for you to write evals for your LLM applications, from which you can write more c

agents

A home for your AI agents

cursor-api-proxy

OpenAI-compatible proxy for Cursor CLI — use Cursor models from any LLM client on localhost

@agent-relay/credential-proxy

JWT-authenticated credential proxy for upstream LLM providers

@ipads-skvm/skvm

SkVM — compile and run LLM agent skills across heterogeneous models and harnesses

@indexnetwork/protocol

The agent orchestration layer for Index Network. Implements LangGraph-based workflows for intent processing, opportunity discovery, and chat — decoupled from any specific infrastructure via adapter injection.

@swarmclawai/swarmclaw

Build and run autonomous AI agents with OpenClaw, Hermes, multiple model providers, orchestration, delegation, memory, skills, schedules, and chat connectors.

@inference/tracing

First-party OpenInference-shaped tracing for TypeScript LLM and agent applications on Catalyst by Inference.net.

Other categories