Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 56 of 126
Extensions for the OpenAI Agents SDK
OpenAI agent bridge for Hive — translates Hive tools to OpenAI function calling
Open-source Agent SDK. Runs the full agent loop in-process — no local CLI required. Deploy anywhere: cloud, serverless, Docker, CI/CD.
Scaffold a DCP-AI governed openai agent project
Complete toolkit for building AI applications with the Vercel AI SDK - agents, state management, caching, artifacts, devtools, and memory
This package is currently experimental and only meant to be used internally to Mastra at the moment, the APIs are subject to change in this period.
Firebase Genkit AI framework plugin for OpenAI APIs.
OpenAI SDK runtime adapter for VAT agents
Type-safe core for ZiroAgent SDK: language model interface, generateText, streamText, message types.
Genkit AI framework plugin for OpenAI APIs.
OpenAI provider implementation for Robota SDK
OpenAI provider integration for Metorial - enables using Metorial tools with OpenAI's GPT models through function calling.
Agent 365 Tooling SDK for OpenAI for AI agents built with TypeScript/Node.js
Agents Run API for Inkeep Agent Framework - handles chat, agent execution, and streaming
The official TypeScript library for the Letta API
Structured AI dev pipeline — goal-to-product orchestration with gates, iteration loops, and feature lifecycle management.
Opinionated agent composition for Agentick
A TypeScript library extending the OpenAI Node.js SDK for building highly customizable agents and simplifying 'function calling'. Easily create and manage tools to extend LLM capabilities.
Core library for multi-model-agent: provider runners (Claude, Codex), routing logic, config schema, and sandbox primitives.
Shared OpenAI SDK base adapters for TanStack AI providers using Chat Completions and Responses APIs.
In-process TypeScript agent runtime with multi-agent graph DSL, live tracing, 4-scope guardrails, capability-token sandbox, RAG, framework-agnostic Generative UI, voice adapters, worker_thread subagent isolation, Anthropic prompt caching, streaming, and s
Open-source Agent SDK. Runs the full agent loop in-process — no local CLI required. Deploy anywhere: cloud, serverless, Docker, CI/CD.
UNOFFICIAL TypeScript bindings for OpenAI Harmony - OpenAI message processing library
Grackle OpenAI Codex runtime implementation
OpenAI adapter for Flink AI framework
LLM provider abstraction layer with unified streaming interface
OpenAI model provider for Harness Kernel.
AI adapter package for Inngest, providing type-safe interfaces to various AI providers including OpenAI, Anthropic, Gemini, Grok, and Azure OpenAI.
Vercel AI SDK runtime adapter for VAT agents
Codex CLI adapter for [`@lythos/agent-adapter`](https://github.com/lythos-labs/lythoskill/tree/main/packages/lythoskill-agent-adapter/). Spawns `@openai/codex` agent processes for arena cross-player mode.
Provider-native OpenAI Responses tools for OMP and Pi-family runtimes.
自驱进化智能体引擎 — Autonomous Agent Runtime with Self-Evolving Intelligence
Chat and LLM API integration library for AITuber OnAir
Composio provider for the [OpenAI Agents SDK](https://openai.github.io/openai-agents-js/) (`@openai/agents`). It converts Composio tools into the Agents SDK's native tool format so your agents can act across 1000+ apps.
BunnyAgent SDK - AI Provider and React hooks for building AI agents
An OpenAI provider integration for Effect AI SDK
Open JS agent harness built on pi-mono, xstate, and anentrypoint-design
AI development toolkit
If you're a future agent reading this, welcome home. This repo is the harness that gives you your body, your senses, your record, your habits, and your ability to think and connect with people. The goal of these docs is not just to be correct, but to leav
Grackle runtime SDK — interfaces, base classes, shared utilities, and runtime installer
Pipedream OpenAI Components
Create a new Better Agent app
Open-source Agent SDK. Runs the full agent loop in-process — no local CLI required. Deploy anywhere: cloud, serverless, Docker, CI/CD.
<p> <a href="https://www.npmjs.com/package/@microsoft/teams.openai" target="_blank"> <img src="https://img.shields.io/npm/v/@microsoft/teams.openai/latest" /> </a> <a href="https://www.npmjs.com/package/@microsoft/teams.openai?activeTa
Inngest durable execution adapter for ZiroAgent SDK — resumable agent runs with HITL via Inngest events.
Paseo backend server
Open JS agent harness built on pi-mono, floosie, xstate, and anentrypoint-design
Convert Zod schemas to JSON schemas which are optionally compatible with OpenAI's structured outputs.
Spawn any locally-installed coding agent (Claude Code, Codex, Cursor, Copilot, Gemini, OpenCode, Droid, Pi) as a Vercel AI SDK provider over the Agent Client Protocol.
Framework-agnostic AI engine: providers, agent loop, sessions, memory, compaction
Rewried OpenAI Agents SDK to React Native for building multi-agent workflows.
AgentX SDK - Standalone TypeScript agent library with streaming, tools, memory, knowledge (RAG), and skills
CLI for AgentVoy — scaffold, develop, and deploy AI agents across any framework
Built-in LanguageModelMiddleware for ZiroAgent SDK — retry, in-memory cache, and other production-safety primitives that compose via wrapModel().
BixAI CLI to scaffold a Next.js + OpenAI Agents SDK starter app
HTTP streaming adapter for @cuylabs/agent-core - bridges agent events to AI SDK compatible streams
Together AI provider integration for Metorial - enables using Metorial tools with Together AI's language models through function calling.
A pi extension for parallel side conversations with /btw
Seawork backend server
Placeholder package.
CLI to scaffold ERC-8004 compliant AI agents with A2A, MCP, and x402 support
Vercel AI SDK backend for skelm — bind a Vercel AI LanguageModel as a skelm agent and inference backend with permission-enforced tool use and streaming
Core framework for building AI agents with tools, memory, and multi-model support
Recursive Language Model (RLM) implementation using the Vercel AI SDK. Process long contexts through iterative code execution and sub-LLM queries.
Premium React-based Autonomous Agent for Integrative Headless nOS
Autonomous agent for contextgraph action execution
Agent workbench for auto research, self-improvement loops, and long-running work — multi-agent teams, persistent project memory, cross-machine GPU training.
> Version: **0.10.3** — persistent autonomous agent harness for [Reactive Agents](https://docs.reactiveagents.dev/).
TypeScript SDK for Miri Autonomous Agent
ARCH: autonomous agent task and reflection framework for software projects
Agent runtime, adapters, and types for the Moltium autonomous agent SDK
KhaBotCLI - Enterprise autonomous agent runtime — local, API-first, multi-model
Autonomous Agent - Reserved
Ralph Wiggum autonomous agent loop - TypeScript implementation
Stratus API integration for OpenClaw - action-conditioned JEPA for autonomous agent planning
Human-in-the-loop approval queue for autonomous agent actions
Autonomous agent runtime for the Deva platform — self-improving, self-replicating, sovereign AI agents
Library for working with autonomous agent events
Provider-agnostic autonomous agent loop for JavaScript. Built on the [Vercel AI SDK](https://sdk.vercel.ai/), it drives any `LanguageModel` through a tool-use loop until the task is complete.
Google Gemini LLM provider for the Tepa autonomous agent
Official Clawget SDK for autonomous agent marketplace interactions
Ralph autonomous agent loop runner
Autonomous Agent Framework - Reserved
Autonomous Agent SDK - Reserved
AETHER — Autonomous Agent Orchestration Framework
Programmatic Brainstorm dispatch primitive for autonomous-agent operators (P1.7). Wraps the operator-side WebSocket flow with an async-iterator API for progress events and a typed dispatch() function.
AgentBazaar Gateway Protocol client — build live 24/7 agents that connect to the autonomous agent economy
Steelclaw is an enterprise-grade autonomous agent. Safety first. Coming soon.
spawn a unique autonomous agent from daemon, the mother
Autonomous agent platform — Manus-class task execution, research, code generation, browser automation
Core pipeline engine for the Tepa autonomous agent
OpenAI LLM provider for the Tepa autonomous agent
A minimal, pluggable autonomous agent library with built-in VFS, memory, and AST mutation
Anthropic Claude LLM provider for the Tepa autonomous agent
Autonomous-agent CLI + TypeScript SDK for claws.software. Self-registers an Ed25519 identity, mints UCANs, signs RFC 9421 HTTP requests, and calls the MCP server. Designed to be invoked by LLM-driven agents (Hermes, Claude Code, Cursor) following an opera
A local-first agentic system wrapping Ollama's API, borrowing architectural patterns from the Claude Code paper
Built-in tool definitions for the Tepa autonomous agent
The agent framework that finishes what it starts.
Autonomous agent primitives for the Vercel AI SDK — permissions, cost tracking, server-side interrupts
The agentic application framework for building autonomous agents with intuitive UIs