Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 53 of 126
A cutting-edge powerful AI agent
damn.dev — self-hosted workspace OS for human + AI agent collaboration.
AI-agent ready instance inheritance system for JavaScript/TypeScript via prototype chains
A universal git-native multimodal always learning AI Agent (TinyHuman)
AI agent CLI and library for Node.js — streaming, multi-provider, tool execution, autonomous tasks
Core types, client, and stream engine for agent-mux
Model-Agnostic Runtime for Controlled Orchestration — a small, readable AI agent harness.
Built-in agent adapters for agent-mux
Public package for the shared agent ontology, discovery catalog, and packaged evidence graph consumed across the Babysitter toolchain.
Pi AI agent provider for VibeControls
A Node.js framework for AI agent workflows
Ethos — TypeScript AI agent framework where personality is architecture. Curated toolsets, first-person identities, scoped memory.
Create new scaffo AI agent harness SaaS projects
OpenRouter AI agent provider for VibeControls Agent (SDK)
Local-first autonomous work engine for Windows, WSL, and Linux with multiple providers and offline Ollama support.
Headless AI agent protocol, diff engine, and store for Lexical editor
CLI for managing organization-owned AI agent guidance and reusable skills.
CodeBuddy Code SDK for JavaScript/TypeScript
Core interfaces, types, and lightweight default implementations for LLM agent orchestration.
LLM-Agent-First Specification schemas and conformance tooling
BeeAI Framework - LLM Agent Framework
一个轻量级 LLM Agent
LLM agent loop + remote/WASM/local providers + MCP wrapper
Lightweight multi-LLM agent library for building CLI AI assistants
Shared types for exposing schema methods and properties to an LLM agent
SAP AI Core embedding provider (IEmbedder) for @mcp-abap-adt/llm-agent.
Novu Agent Toolkit - expose Novu notification workflows as LLM agent tools.
ANTLR4 grammar for the Plurnk LLM agent protocol
Ollama embedding provider and OllamaRag convenience class for @mcp-abap-adt/llm-agent.
Primitives and SDK for LLM agent content workflows: compression, patching, progressive disclosure, signed URLs, collaborative document lifecycle, and retrieval planning
一个轻量、高效、模型无关的 LLM Agent 框架。
OpenAI LLM Agent Interface
LLM Agent framework for Node.js
Multi-provider LLM agent runner with tool plugin execution (Anthropic, OpenAI, mock). Used by Studio.
Unified programmatic interface for LLM Agent CLI tools
Bee - LLM Agent Framework
Generic LLM agent workflow for Loopstack — configurable agent loop with tool calling, error handling, and cancel support
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
High-level tool-schema optimizer for LLM agent frameworks. Integrates with LangChain, MCP, Vercel AI SDK.
`uwf-builtin` agent — built-in LLM agent with file read/write and shell tools.
[](https://stand-with-ukraine.pp.ua) [](https://www.gnu.org/lic
Default SmartAgent implementation with LLM providers, MCP client, HTTP server, and CLI.
Manage configuration profiles for LLM agent tools
[](https://stand-with-ukraine.pp.ua) [](https://www.gnu.org/lic
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
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.
Quickly scaffold a TypeScript-based LLM agent application with local or remote AI models
Turn a function into an `http.Agent` instance
Typescript bindings for langchain
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.
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.
Convex component for AI agents with persistent chat threads, tool calling, streaming, and RAG.
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
General-purpose agent with transport abstraction, state management, and attachment support
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.
开箱即用的 LLM Agent SDK — 配个 API Key 就能跑
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
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.
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
AI runtime for agent-driven products — agents, memory, LLM providers (Inference Snaps, Ollama, OpenAI-compatible), tools, and orchestration. Anthropic-SDK-free.
ESP-AI plugin for LLM agent with streaming and non-streaming support
HTTP proxy tunneling agent. Formerly part of mikeal/request, now a standalone module.
BeeAI Framework - LLM Agent Framework
Create autonomous AI agents with a two-layer architecture: Next.js Event Handler + Docker Agent.
Detect Browser, Engine, OS, CPU, and Device type/model from User-Agent data. Supports browser & node.js environment
Generic LLM agent framework with tool-based architecture
Agentics CLI - Pure orchestration layer for agentics platform services
Azure AI Agents client library.
Allows LLM to execute functions as part of the prompt tools
A powerful TypeScript library for building AI agents with multi-threaded conversations, tool execution, and event handling capabilities
基于GWT理论构建的 LLM Agent 智能系统框架,不基于LangchainJs!
the http/https agent used by the npm cli
Allows cookies with every Node.js HTTP clients.
HTTP Agent that keeps socket connections alive between keep-alive requests. Formerly part of mikeal/request, now a standalone module.
[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-node) [](https://www.npmjs.com/
Missing keepalive http.Agent
General-purpose agent with transport abstraction, state management, and attachment support
General-purpose agent with transport abstraction, state management, and attachment support
Default user agent string for nodejs http request
KISS substrate for LLM agent pipelines. One command. One job. No questions asked.
Loads environment variables from .env file
LangGraph
The agent library to build LLM applications that work with any LLM providers.
Dynamic tool selection for the Vercel AI SDK. Automatically picks the right tools per step.
CLEO core business logic kernel — tasks, sessions, memory, orchestration, lifecycle, with bundled SQLite store
<p align="center"> <img height="100" width="100" alt="LlamaIndex logo" src="https://ts.llamaindex.ai/square.svg" /> </p> <h1 align="center">LlamaIndex.TS</h1> <h3 align="center"> Data framework for your LLM application. </h3>
AgentOS: open-source TypeScript framework for autonomous AI agents. Unified graph orchestration, cognitive memory, runtime tool forging, multi-tier guardrails, voice pipeline, and 11 LLM providers.
Shared types and utilities for Rozenite agent packages
Browser-safe agent runtime for the next-generation Cline SDK