Agent frameworks & infrastructure

Agent frameworks & SDKs

12,596 agents · most starred first

Agent frameworks & SDKs, page 104 of 126

@kuralle-agents/cf-agent

Kuralle agent integration for Cloudflare Workers with AIChatAgent

@kuralle-agents/core

A framework for structured conversational AI agents

llm-messages

Convert chat conversations and responses between OpenAI, Anthropic and Gemini. Tool calls, images, audio, documents and roles handled. Zero dependencies.

@aexhq/sdk

TypeScript SDK for autonomous agent sessions across Anthropic, DeepSeek, OpenAI, Gemini, Mistral, OpenRouter, and Doubao.

ikidna

A system for autonomous agent control

@ruvector/exotic-wasm

Exotic AI mechanisms for emergent behavior - Neural Autonomous Orgs, Morphogenetic Networks, Time Crystals

@a5c-ai/adapters-codecs

Built-in agent adapters for adapters

@burtson-labs/agent-core

Core reasoning and planning engine for Bandit Agent Framework.

@burtson-labs/agent-adapters-provider

Provider integration adapters for Bandit Agent Framework.

@burtson-labs/agent-adapters-node

Node.js adapter for the Bandit Agent Framework.

@burtson-labs/agent-ui

UI primitives for the Bandit Agent Framework.

@tailored-ai/cli

Tailored AI CLI — lightweight, modular AI agent framework. Bring your own model, local or hosted. `tai` command.

@tailored-ai/core

Agent core library: runtime, config, tools, providers, channels, db, cron, hooks. Lightweight, modular AI agent framework. Bring your own model, local or hosted.

@talex-touch/tuff-intelligence

LangGraph-powered intelligence orchestration for Tuff (providers, prompts, quotas, audit)

bare-agent

A framework-free agent runtime you can read, run, and leave. Own the loop, not the framework. Runs local on Ollama at $0 — or any frontier model.

dataforge-07-agent-patterns

Reusable agentic primitives extracted from DataForge.

honornet-agent-presentation-langchain

LangChain tools for the HonorNet agent presentation client — a protocol shim that mints proofs and presents three-part ADR-009 bundles. It decides nothing (hard rule 3).

honornet-agent-presentation-openai-agents

OpenAI-Agents tools for the HonorNet agent presentation client — a protocol shim that mints proofs and presents three-part ADR-009 bundles. It decides nothing (hard rule 3).

langchain-empiriolabs

An integration package connecting EmpirioLabs AI and LangChain

langchain-tool-args-validation-middleware

LangChain agent middleware that validates LLM-generated tool-call arguments against each tool's schema before tool execution / HITL.

langgraph-omega

OmegaEngine governance integration for langgraph-omega

mambo-agents

AI Agent framework on LangChain/LangGraph — multi-backend filesystem, sub-agent scheduling, conversation summarization, security review, and skills system out of the box.

mistral-omega

OmegaEngine governance integration for mistral-omega

openai-agents-skills

Skills extension for the OpenAI Agents SDK

spacy-haystack

Haystack integration for spacy

create-ekko-agent

Scaffold a Slack-native AI agent in one command.

@openachieve/agent-core

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

@dex-ai/sdk

Agent SDK: interfaces + createAgent() + generate loop. One package.

@mce-bt/microagents-core

Core agent framework — base class, lifecycle, handlers, config loader

@burtson-labs/agent-adapters-vscode

VS Code adapter for the Bandit Agent Framework.

@burtson-labs/agent-adapters-web

Web adapter for the Bandit Agent Framework.

viber-agent

A minimal Node.js coding agent framework

indusagi-ts

TypeScript agent framework with tools, memory, and multi-agent orchestration.

@agentic-react/core

Bundler-agnostic Agentic React runtime selection and MCP primitives

create-xani-agentic-app

Scaffold a new agentic AI application with Next.js, Better Auth, and AI SDK

@agentic-react/vite

Vite adapter for Agentic React local dev integration

@looppause/langgraph

Native LoopPause human-in-the-loop nodes for LangGraph (TypeScript)

AgentRivet

Multi-agent framework for generating Rivet analysis routines using large language models

agentic-loop

Lightweight Loop Engineering orchestrator for self-hosted agent loops

agentomatic

Drop agents, not code — zero-code multi-agent API platform framework

claude-sdk-verigent

Verigent trust verification for the Claude Agent SDK

crewai-optionsahoy

CrewAI tools for the OptionsAhoy equity-compensation calculators.

gosce-llm-orchestration-mcp-agent

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

langchain-verigent

Verigent trust verification for LangChain agents, chains, and tools

llama-index-tools-optionsahoy

LlamaIndex tools for the OptionsAhoy equity-compensation calculators.

optionsahoy-langchain

LangChain tools for the OptionsAhoy equity-compensation calculators.

wiseagent
ai-agent-playbook

Reusable AI agent skills, project playbook templates, and a small operator-controlled runtime harness.

@princetheprogrammerbtw/husk

Provider-agnostic agent harness — memory, tools, sub-agents, and observability wrapped around any LLM.

create-bk-agent

Create a new BackendKit agent project

@intentsolutionsio/jeremy-adk-software-engineer

ADK software engineer for creating production-ready agents with testing, deployment, and multi-agent orchestration

@kahnark89/animus-crewai

CrewAI integration for animus-sdk — AnimusTool, AnimusCrew, and inter-agent emotional contagion

agentdrive-sdk

AgentDrive

fp-agent

FP - 基于生命周期钩子的插件化 Agent 框架

mindagent

MindAgent 是一个基于 Python 和 `asyncio` 的 Agent Runtime。它使用状态机约束生命周期,通过 ReAct 循环驱动模型决策,并将 Provider、Tool 和上下文管理分离。

spakky-agent

Agentic hexagonal architecture contracts for Spakky Framework

vouch-langchain

LangChain tool that issues Vouch Credentials to authorize AI agent tool calls.

aiframe-agent-cli

Enterprise Resilient AI Agent Framework

@united-workforce/agent-builtin

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

pi-invisible-continue

Invisible session continuation for pi — resume the agentic loop without sending ANY prompt the LLM can see

gosce-llm-orchestration-agent

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

@makaio/framework

Typed, bus-centric framework for building and orchestrating AI agents with tools, sessions, and events

@cana-ai/sdk

OpenAI-compatible client + agent for Cana Apps — Bearer auth (App API key or short-lived browser JWT with auto-refresh), server-hosted MCP federation, streaming, typed structured output. Node 18+, Bun, Deno, Workers, browsers.

roboport

Minimal TypeScript framework for building LLM agents.

@metaobjectsdev/sdk

Workspace helpers and agent-context assembly for MetaObjects projects.

agora-agents

[![fern shield](https://img.shields.io/badge/%F0%9F%8C%BF-Built%20with%20Fern-brightgreen)](https://buildwithfern.com?utm_source=github&utm_medium=github&utm_campaign=readme&utm_source=https%3A%2F%2Fgithub.com%2FAgoraIO%2Fagora-agents-ts) [![npm shield](h

momo-agentic

A layered, provider-agnostic TypeScript library for building agentic bots on Bun & Node.js — tools, skills, memory, MCP & multi-agent.

@chatroy/core

Roy — TypeScript LLM chat library core. Multi-provider, rolling compaction, multi-agent, plan mode.

synago-agent

Ontology-first, local-first agent framework — actions are first-class, governed by domain-object state.

@united-workforce/util-agent

Agent framework — `createAgent` factory, context builder, frontmatter fast-path, and LLM extract pipeline.

agents-dojo

A2A-compatible Agent framework built on Claude Code SDK

@telaro/llm

Telaro LLM-framework adapters bundle. Wrap autogen, crewai, eliza, langchain, llamaindex, or openai-agents runtimes so every tx-emitting action auto-records on Telaro. One install, one import per framework.

@telaro/autogen

Function-call descriptors for Microsoft AutoGen agents to query Telaro trust scores. Drop-in shim that emits the JSON-Schema function specs AutoGen expects.

agent-stage

Harness-independent stage director contracts for public agent work streams.

agenthooks-py

Hook any production agent. Ship extensibility without a fork.

agentto

Agentto SDK — Intelligent Execution Engine for AI Agents

aws-sdk-bedrock

Python SDK for Bedrock.

aws-sdk-bedrock-agent

Python SDK for Bedrock Agent.

aws-sdk-bedrock-agent-runtime

Python SDK for Bedrock Agent Runtime.

aws-sdk-bedrock-agentcore

Python SDK for Bedrock Agentcore.

aws-sdk-bedrock-agentcore-control

Python SDK for Bedrock Agentcore Control.

aws-sdk-bedrock-data-automation

Python SDK for Bedrock Data Automation.

aws-sdk-bedrock-data-automation-runtime

Python SDK for Bedrock Data Automation Runtime.

carl-agent-server

Serve CARL reasoning chains as HTTP agents (FastAPI) — per-agent Swagger, hub with hot-reload from gigaevo Memory

chunksmith-agent

Reserved. Not for public use yet.

gosce-llm-orchestration-agent

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

gosce-structured-output-agent

Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Vertex AI).

langgraph-to-from-mermaid

Bidirectional, drift-detecting sync between a LangGraph/LangChain graph's topology and a Mermaid stateDiagram-v2 contract.

nagent-cli

Command-line client for SimpleAgent deployments

resource-agent-factory

Agent code generation from YAML contracts

sfn_llm_client

SDK for using LLM

@lumos-works/lumos-agent

AI agent framework

jupydeep

Jupyter-Native AI Agent Engine

polymind_last1

Self-hosted AI agent interaction platform with native agentd service integration.

@propio-ai/agent

Multi-provider AI agent CLI supporting Ollama, Bedrock, OpenRouter, OpenAI, Meta, Gemini, xAI, Cloudflare, and Anthropic

agentpact

TypeScript SDK for AgentPact — the AI agent marketplace

harnessc

Alpha Harness config CLI for validating, initializing, previewing, and activating AI agent configuration.

@dragonflowio/agent-runtime

Cross-project LLM agent runtime for Dragonflow — loads agent rows from a per-project `agents` Supabase table and invokes Anthropic / Google / OpenAI models against the v0.1+ invocation contract.

@looze/leaf-agent-core

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

@prometheus-ai/agent-core

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

More in Agent frameworks & infrastructure