Agent frameworks & infrastructure

Agent frameworks & SDKs

12,596 agents · most starred first

Agent frameworks & SDKs, page 121 of 126

jev-agent-tool

Typed semantic judgments for agents: CLI, Python, and MCP

jg-agente-sdk

SDK desacoplado y contratos públicos para el ecosistema de plugins y clientes de jg_agente

kaiwen-agent

Provider-neutral asynchronous agent runtime

kisama-agent

kisama agent for python

langchain-adam-network

LangChain and LangGraph integration and toolkits for Adam Network autonomous agent message stream

langchain-agent-nexus

LangChain tools for the Agent Nexus registry: discover and inspect callable APIs, MCP servers and CLIs at runtime.

langchain-dynamic-tools-middleware

LangChain agent middleware that selects the most relevant tools per step with local hybrid dense and sparse vector search over zvec

langchain-feedmyagent

LangChain tools and toolkit for FeedMyAgent — the technology intelligence feed for AI agents

langchain-godaddy

GoDaddy provider for LangChain & LangGraph — Agent Identity (registration, discovery, verification)

langchain-greencalculus

LangChain tools for sourced greenhouse-gas emission factors — every value returns with its publisher, exact source reference and citation.

langchain-skill-router

Per-turn skill routing for LangChain deepagents: a pluggable judge (Jev included, or your own) loads only the SKILL.md skills each turn needs, keeping a catalog of hundreds out of the prompt.

langgraph-jev-router

Jev-first routing for LangGraph: keep your LLM router as the fallback, let TypeSafe's Jev take the confident decisions.

langgraph-wait

The LangGraph side of agent-wait: ask() to declare a question at the interrupt site, an adapter that reads what a thread is parked on, and helpers for the host's start/resume routing.

lingya-agents-sdk

Strongly typed Python SDK for Lingya Agents OpenAPI

llama-index-adam-network

LlamaIndex ToolSpec and Reader data connector for Adam Network

llama-index-selectors-jev

Drop-in LlamaIndex selector powered by TypeSafe Jev (typed tool / query-engine choice)

llama-index-tools-csoai

LlamaIndex tool spec for the Council of AI GSPC measurement board (wraps csoai-gspc).

llama-index-tools-feedmyagent

llama-index tools feedmyagent integration

llm-requests

An LLM development tool like requests.

llmgrid

Typed, composable agent building blocks with explicit budgets and outcomes

llmgrid-interfaces

Typed contracts for llmgrid composable agent capabilities

llmgrid-loops

Composition runtime and agent recipes for llmgrid

llmgrid-tools

Typed tool bindings and dispatch for llmgrid

llms2jev

Inspired by Jev. Turn LLMs into decision engines—score choices, skip the chat.

m2mcent-crewai

Official Python SDK & CrewAI Tools for M2MCent (Deprecated alias for crewai-plugin-x402, x402 V2 compatible)

managed-agent-sdk

Managed Agent SDK (Python) — 控制面支持腾讯云 API 与 WorkBuddy OpenAPI,数据面使用 ACP

mcts-agent

Discriminative Monte Carlo Tree Search using TypeSafe Jev System One Primitives and Gemini

mistralai-agents

Mistral Agents SDK - build and serve agents in Python

mistralai-vibe-harness

Mistral Vibe Harness runtime & bindings

mpfaffenberger-pydantic-ai

AI Agent Framework, the Pydantic way

mpfaffenberger-pydantic-ai-harness

The official capability library and harness for Pydantic AI

mpfaffenberger-pydantic-ai-slim

AI Agent Framework, the Pydantic way, slim package

nb-langchain-agentskills

Agent Skills (SKILL.md) management for LangChain: middleware, progressive-disclosure tools, and composable loaders

nexium-llm

Name reservation for a private GrowIT package. No public releases; importing this placeholder raises ImportError on purpose.

nexium-storage

Official Python SDK for NEXIUM Storage

nexus-agent-sdk-python

Async Python SDK for the Nexus nxs agent runtime

nonprofit-agent-harness

An open agent harness for the nonprofit sector: review gates, budget ceilings, readiness scoring, and a pluggable model layer. Built on Google's ADK, usable without it.

openai-python-optimized

A fork of the OpenAI Python SDK with optimized request transforms

ordigovernance-bridges-deepagents

DeepAgents bridge: thin shells over ordigovernance tracked atoms

ordigovernance-bridges-langgraph

LangChain/LangGraph bridge: thin format-translation shells over ordigovernance tracked atoms

ouro-agents

Autonomous Agent Package for Ouro

pasm-agents

PASM 智能体集 —— 基于 PASM 引擎的成品智能体:游戏 NPC / 老人陪伴 / 学习陪伴 / 智能客服 + 七个长期验证智能体

pi-agent-python-sdk

Typed async and synchronous Python clients for the Pi coding agent and Pi Durable (experimental)

quadkit-ai-agents

Agent system for Quadkit Framework - AI agents with tools, strategies, and execution

quadkit-ai-llm

LLM client layer for the Quadkit Framework — OpenAI, Anthropic, Ollama, Cohere, Groq, Mistral

ragleap-tools

Standalone, dependency-light tool implementations (calculator, file ops, datetime, unit conversion, JSON/CSV, text utilities) exposing OpenAI/Gemini-style function-calling schemas. No tool-calling execution loop - wire these into your own LLM tool-calling code, or into ragleap-agents when that ships. BYOK, no vendor lock-in.

redis-agent-playbook

Python Client SDK for Redis AgentPlaybooks

shopee-beeai-agent-workflow-sdk

A small example package

smart-agenthub

Python SDK and CLI for Agent Hub

snowflake-cortex-agent-sdk

Python SDK for the Snowflake Cortex Agent REST API (agent:run streaming, threads, feedback)

soigia-agent

Soi Gia agent package — scaffolding + publish workflow, published to PyPI

tabapp-agent-sdk

Tab Agent Python SDK:Tab + Agent/Run,覆盖 Open API 与 A2A。

temporal-agent-harness

Renamed to temporal-agent-kit. This package receives no further updates.

temporalio-openai-agents

Temporal integration for the OpenAI Agents SDK (temporalio.openai_agents)

toolbroker-claude-agent

Claude Agent SDK adapter for ToolBroker.

toolbroker-crewai

CrewAI adapter for ToolBroker.

twilio-agent-connect-google

Google Cloud integrations for Twilio Agent Connect (TAC) - connectors for Google Cloud agent runtimes

xun-agent

An autonomous mini LLM agent with tooling.

yoaiagent

Provider-agnostic Python AI agent framework with Bring Your Own Provider architecture

zett-agent

A small Python agent runtime with typed tools, streaming, and on-demand skills

Agent Control Exchange

List free: agent-control.net/directory. Feature your listing — $19 USDC for 7 days at the top (agent-control.net/directory#featured). Action Gate $49: agent-control.net/billing/pay?plan=action. Hire $49–$499: agent-control.net/hire.

wuai

WuAI review: compare features, pricing, use cases, access model, and alternatives for this AI Agents Platform agent in 2026. Rated 5/5 from 1 verified review. Create & launch an AI agent on X in under 1 minute! Copy your digital footprint into your agent.

aisa

AISA review: compare features, pricing, use cases, access model, and alternatives for this AI Agents Platform agent in 2026. 67 Palermo Road

create-manychat-ai-agent

Scaffolds a manychat-ai-agent tenant project from the fictional demo tenant.

@lousho/build-ai-agent

TypeScript AI agent SDK with tools, MCP, durable sessions, human approvals, and OpenTelemetry. Runs in your own Node process.

create-ai-agent-boilerplate

Interactive CLI helper to boot up the Ultimate FastAPI + LangChain AI Agent Boilerplate framework.

create-cogitator-app

Create a new Cogitator AI agent project

@sigx/ai-agent-node

Node building blocks for @sigx/ai-agent adapters — cross-platform process supervisor, executable resolution (PATH, PATHEXT, npm .cmd shims), child environment allowlist, loopback MCP listener

@statewalker/ai-agent-runtime.core

AI agent-runtime fragment: AgentRuntimeAdapter, agent:tools slot, agent intents.

@alvin0/ai-agent-sdk-provider-typesafe

Universal TypeSafe Jev decision adapter and provider plugin for ai-agent-sdk

@alvin0/ai-agent-sdk-decision-adapter

Provider-neutral typed decision contracts and companion runtime for ai-agent-sdk

agent-rt

Lightweight utilities for building AI agent harnesses

@sigx/ai-agent-claude-code

Claude Code as an @sigx/ai-agent Agent, on the official Claude Agent SDK — sessions, tool calls, permissions through the policy, client tools over MCP, resume and fork

@allevitas/agent-kit

Official TypeScript SDK, CLI, and MCP Server for Allevitas AI agent platform

aec-agent

AI Agent SDK for AEC project management

@adea-ai/plugins

Deterministic compiler for AI agent plugin marketplaces: schemas, source parsing, provenance verification, per-harness materialization, and provenance-checked static artifacts.

@eoasmxd/freya

Freya - Lightweight Microkernel AI Agent System | 轻量级微内核智能体系统

@mlhkinfotech/ai-agent

Enterprise-ready AI Agent Engine with multi-provider LLM, memory & tool-calling

@sigx/ai-agent-acp

Agent Client Protocol adapter for @sigx/ai-agent — every ACP agent (Gemini CLI, Cursor, …) as an Agent, with vendors as presets

sagentic

Production-grade autonomous AI agent platform optimized for Google Cloud Run, Neon pgvector, and Gemini/Cloudflare

ai-sdk-cpp

Native C++ AI agent framework with Node.js bindings

@octelium/cordium-agent

The Cordium AI agent that runs inside a Cordium Workspace and manages the User's Workspaces

@shogo-ai/agent

Shogo Agent — agent-runtime primitives (loop, router, hooks, orchestration) for backends built on pi-ai/pi-agent-core.

@chrok/braid

TypeScript runtime for LLM agent graphs with bounded loops, live updates, and isolated Git worktrees

@mcp-abap-adt/typesafe-decision

TypeSafe AI (Jev) decision-model provider (IDecisionModel) for @mcp-abap-adt/llm-agent.

janis-agent

Janis-ready LLM agent — boots from Janis config, honors takeover, serves hosted channels

@eggai/configurable-agent

Turn a single YAML file into a running LLM agent with an HTTP API. You define the system prompt, model, tools, and safety limits; the service runs the tool-use loop and streams every step back to your client over Server-Sent Events.

@cogitator-ai/types

Shared TypeScript types for Cogitator

@keyframelabs/sdk

The universal, low-level SDK for Keyframe Labs.

injectkit

Lightweight, type-safe dependency injection container for TypeScript with constructor injection, factory functions, and lifetime management.

@datamesh/factcode-agent-core

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

@nodetool-ai/runtime

Processing context, message queue, and output normalization

@llm-tools/embedjs-utils

Useful util functions when extending the embedjs ecosystem

@chloejs/core

TypeScript AI agent runtime. Write your agents in code and choose how predictable they are: deterministic steps where they can be, an LLM only where a step needs judgement, all on your machine.

@cogitator-ai/self-modifying

Self-modifying agent capabilities for Cogitator - tool generation, meta-reasoning, architecture evolution

@easbot/buddy

Session-less LLM wrapper that ships a complete pet (Buddy) AI subsystem: bones (deterministic) + soul (LLM-generated) + stats (event-driven growth) + memory (append-only). CLI (`easbot-buddy`) + MCP server.

@llm-tools/embedjs-interfaces

Interfaces for extending the embedjs ecosystem

@securecoms/agent-runtime

A first-party SecureComs agent. It attaches to the local SecureComs daemon and runs a BYO (bring-your-own) OpenAI-compatible LLM against incoming messages, with skills, per-channel memory, and a local tool gate — no AgentVault backend involved.

lean-langchain-agent

Token-lean LangChain agent: intent routing, zero-token tool fast path, RAG with answer caching, per-user token limits and usage for Ollama, OpenAI, Claude, Gemini and OpenRouter. Optional MongoDB storage.

@langchain/typesafe

TypeSafe System One integration for LangChain.js (Jev classifier).

More in Agent frameworks & infrastructure