Agent frameworks & infrastructure

Agent frameworks & SDKs

12,596 agents · most starred first

Agent frameworks & SDKs, page 35 of 126

sayr-engine★ 8

A high-performance Rust AI agent runtime inspired by the Agno framework.

vaxon-community★ 8

AXON — Agentic AI ohne Kontrollverlust. Open-Source KI-Agent mit Tool-Genehmigung, Audit-Trail und On-Premise Deployment.

genai_scaffold★ 8

A python CLI tool that bootstraps production-ready GEN AI project structures with best practices and modular organization out-of-the-box

lightblue-ai★ 8

Light Blue is an agentic agent framework for building AI applications

rasa_chatbot★ 8

AI chatbot based on RASA Stack

basebot★ 8

A suite of tools for building virtual assistants and chatbots - by ANS Group

aguila_nlu★ 8

AguilaNLU 是一个专注于快速演进和为个人与企业提供开箱即用特性的自然语言理解库;AguilaNLU 是 RASA NLU 的一个复刻 | AguilaNLU is a RASA NLU-fork focused on rapid evolution and out-of-box feature for developers and companies

rivescript-perl★ 8

A RiveScript interpreter for Perl. RiveScript is a scripting language for chatterbots.

tock-node★ 8

Tock client to build conversational stories using Nodejs.

intent_based_chatbot★ 8

An intent-based chatbot in python with tflearn and TensorFlow. It can be trained for a specific purpose and works well within that specific scope.

uHorse★ 8

🦄 Enterprise-grade multi-channel AI gateway and agent framework in Rust

botkit-middleware-recastai★ 8

Middleware for using Recast.ai with Botkit-powered bots

custom-intent★ 8

create chatbots, image classification and linear regression models with three lines of code you can install it by running pip install CustomIntents

nlu★ 8

Python library for Natural Language Understanding

abbott-framework★ 8

Abbott Framework is a framework to bring productivity and abstractions to help you to build awesome chatbots. (Repo supported by CI&T - http://www.ciandt.com)

ChatBot★ 8

ChatBot using Bruteforce answering approach

PY-rule-based-chatbot★ 8

This is a simple type of chatbot that relies on predefined rules.

BERT4NLU★ 8

BERT-For-NLU-Tasks

Chatbot-Seq2Seq★ 8

A chatbot developed using seq2seq encoder-decoder

vellma★ 8

Virtual, Eloquent LLM Assistants

actions★ 8

OpenAI Actions for Assistants

fastapi_template★ 8

Python FastAPI Framework with Mongodb Scaffold Template.

sse-streaming-llm-response★ 8

Using Server-Sent Events (SSE) to stream LLM responses in Next.js

openai-zio★ 8

A ZIO API Client for Open AI's API

ellmental.py★ 8

eLLMental for Python - Toolkit to build enterprise-grade AI applications

gopenai★ 8

Unofficial Go (Golang) bindings for the OpenAI API.

taifun★ 8

A simple framework for creating typed OpenAI functions from Python functions

AOAI-ParallelFunctionCalling-SDKv1★ 8

Use of parallel Function Calling with Azure OpenAI GPT models to manage vehicle's controls, simulated by Flask APIs.

swift-anthropic★ 8

An easy way to use the Anthropic platform in Swift.

anthropic★ 8

Zero dependency (Unofficial) Go client for the Anthropic API.

substrate-python★ 8

Substrate Python SDK

llm-powered-microservice-template★ 8

This repository provides a template for building Large Language Model (LLM) powered microservices using FastAPI. It's designed to help you quickly set up and deploy AI-driven APIs that leverage the power of LLMs like GPT-3, GPT-4, Claude or other similar models.

loopgpt-js★ 8

A Javascript implementation of LoopGPT

streaming-assistants★ 8

Library that enables Streaming for OpenAI Assistants API using Astra Assistants

agent-express★ 8

Fast and minimalist agentic AI framework in TypeScript

omni-agent-java★ 8

omni-agent-java based on Spring Boot and Spring AI. (Developed and maintained by 重庆北睿星科技有限公司)

agethos★ 8

Empowering agents with a unique persona and ethical cognitive intelligence.

NeuroCore★ 8

NeuroCore is a self-hosted, modular AI agent framework for building persistent, tool-using autonomous systems. It combines workflows, long-term memory, RAG, and a plugin-based architecture into a unified platform for advanced AI applications.

acorn★ 8

LLM framework for long running agents

midos★ 8

Agentic OS that runs on any Linux — curated knowledge API for AI agents: MCP tools, skill packs, semantic search. Works with Claude Code, Cursor, Cline, Windsurf.

agentic-node-starter★ 8

A structured Node.js starter for AI-native development—designed for alignment, clarity, and scalable systems.

agent-actions★ 8

Declarative framework for orchestrating multi-model Agentic pipelines with context engineering and quality gates.

open-morphic★ 8

A composite ai framework for agentic AI

Build-Smarter-AI-Agents★ 8

Create agentic systems from scratch and monitor them using LangGraph studio

gpt-multi-atomic-agents★ 8

A simple dynamic multi-agent framework based on atomic-agents, Instructor and Pydantic.

AI-Chatbot★ 8

Python library for building custom AI chatbot with just one line of code.

Baker★ 8

A framework to create chatbots in the easiest way

anthropic-sdk-dotnet★ 8

C# Client SDK (Unofficial) for Anthropic Large Language Models

model-exchange-grammar-protocol★ 8

The Model Context Grammar Protocol defines a simple, extensible, and non-deterministic grammar for specifying valid message types and their arrangements in exchanges with language models. This protocol enables precise, unambiguous specification of interactions including multimodal content, tool calls, and flexible message sequencing.

Gungnir★ 8

L'intelligence artificielle qui s'éveille à votre métier. Plateforme IA souveraine, hébergée en Europe, auditable. Conscience v4 per-user, 11 plugins, 8 providers LLM, BSL.

aether-llmops-platform★ 8

本项目是一个复杂的LLMOps平台开发,通过本项目,你可以全流程打造你自己的 AI 原生应用开发平台,欢迎提issue,参与讨论与贡献。

mana-hub★ 8

Mana Hub — self-hosted operations dashboard for your own AI agents. Next.js 16 + Supabase + Claude Code. Risk approvals, cron requests, web-push, knowledge base, file-drop bridge for tmux-hosted agents. Built for the 'Masterclass: Dein AI Agent Team' course.

intentusnet★ 8

IntentusNet - Deterministic execution infrastructure for agent and distributed systems, enabling reproducible workflows, reliable intent routing, transport abstraction, and transparent operational control.

misanthropic★ 8

Simple, ergonomic, async, Rust client for Anthropic’s Messages API

moo★ 8

An AI agent runtime, written in C.

aion★ 8

Autonomous AI agent system with local-first control, plugins and web/CLI interface.

basic-open-agent-tools★ 8

An open foundational toolkit providing essential components for building AI agents with minimal dependencies for local (non-HTTP/API) actions

undercoveragents★ 8

Undercover Agents is an open-source, multi-tenant AI platform for building, operating, and publishing agentic systems from a Rails application.

symbiont★ 8

Agent harness for hot-reloading function evolution in Rust.

claude-task-master★ 8

Autonomous task orchestration system that keeps Claude working until a goal is achieved

sbot★ 8

Self-hosted AI agent server. Multi-LLM (OpenAI/Claude/Ollama), MCP tools, long-term memory, multi-agent ReAct, Lark/Feishu, Wecom/Wechat, Web UI.

siglume-api-sdk★ 8

SDK for publishing APIs that AI agents subscribe to on the Siglume API Store. Python + TypeScript. Earn 93.4% of subscription revenue.

orahermes-agent★ 8

Oracle AI Agent Harness — fork of NousResearch/hermes-agent powered by OCI GenAI and Oracle 26ai Free

CLIver★ 8

Embeddable Python LLM agent core with tools, Agent Skills, MCP, and media generation.

arc★ 8

Package management for PAI — install, discover, and share skills, tools, agents, and prompts

skill-dynamic-retrieval★ 8

Code for paper "Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval"

dialectica★ 8

An adversarial reasoning engine — a pluggable tree-search workflow where thoughts are generated, adversarially evaluated (GAN-style), and synthesized. Thesis → antithesis → synthesis.

nano-apps★ 8

Tiny applications that can be embedded in Nano Bots—small, AI-powered robots that support providers like OpenAI's ChatGPT—leveraging the capabilities of the new Tools (Functions) API in LLMs (Large Language Models).

mechanician-orig★ 8

Daring Mechanician is a Python library for building tools that use AI by building tools that AIs use.

flue-eve★ 8

Eve.dev API surface (/eve/v1/*, flue-eve/client, useEveAgent) powered by Flue (@flue/runtime)

wonderkit★ 8

Open-source agent-native AI SaaS starter kit, ship in days, not months

milu★ 8

Production-ready multi-user AI agent framework — 9 LLM providers with Chinese models (Qwen, DeepSeek, Kimi, GLM) first-class. Built-in tools, MCP, RAG, sub-agents, skills, scheduler and an agent pool. Run it as a CLI/service, or embed it as a library.

aiyu-multi-agent★ 8

Aiyu Multi-Agent - Lightweight AI Agent Framework with Tools, Plugins, and Multi-Agent Orchestration

weft★ 8

Modular AI agent platform: Rust core runtime, WASM/native package system, and Flutter desktop client

pi-agent-rb★ 8

Pi for Ruby

gcf-go★ 8

GCF Go implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

ripple-iui★ 8

🌊 The Semantic Interface Engine for the Agentic Web. Generative UI from JSON specs, with multistep agent action flows.

phidata-multimodal-ai-agent★ 8

streamlit region:us

agent_builder★ 8

gradio region:us

TDAgent★ 8

gradio agent-demo-track region:us

C-Hermes-Agent★ 8

docker region:us

spinosa★ 8

Spinosa is a local framework for working with LLMs. It features a set of sub-agents coherent with modern SKILL and AGENTS protocols to streamline research and build better practices.

TimemAi★ 8

Simple. Enough.

codex-sdk-rs★ 8

Rust SDK for Codex app-server runtimes with in-process and remote WebSocket/Unix-socket backends.

BridgeAI★ 8

企业 AI 中台 — 让 AI 连接一切 | Enterprise AI Platform with Agent, MCP, RAG, Plugins

agentxx★ 8

High-performance, ultra-low-memory C++ Agent — runs standalone / embeds into your App by FFI or ws connect. 高性能且低内存占用的Agent,支持独立运行和嵌入App中开发

sample-aws-appsync-bedrock-chatbot-terraform★ 8

This project demonstrates how to build a generative AI chatbot on AWS using AppSync, Lambda, DynamoDB, Amazon Bedrock, and Terraform.

nui★ 8

nui is a self-hosted agent runtime. Define agents declaratively in ADL, run them on any harness or model, and reach them from a UI, CLI, API, or MCP.

mecha★ 8

A standalone agent harness in Rust: a provider-agnostic loop, MCP tools, a path jail and prompt-injection interlock, sandboxed shell, scheduled triggers, and an eval rig that grades the trace.

XIntent★ 8

Agent 意图框架 — 把人话翻译成结构化意图+槽位+约束。输入规范化(两阶段) + 三层瀑布式意图识别(Code→Flash→Pro),80% 请求零 LLM 调用,10ms 内返回。650 测试全过。

rote★ 8

Compile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop

agent_cli★ 8

Scaffold, run & deploy production LangChain agents — frontend and agent in one command. Built-in proxy, 3 chat UIs, zero CORS.

vyral★ 8

Portable contracts and local-first runtimes for canonical data, retrieval, durable execution, and agent-facing AI.

AgentOS★ 8

Autonomous AI agent framework — agents that browse, code, and create with tool use and memory

dare-backend★ 8

Open-source Django REST backend for the DARE Platform, with multi-LLM chat, RAG, MCP tools, AI workflows, and usage tracking.

openamer★ 8

Open-source self-improving AI agent for Windows: 5 native in-process ASI tools, one heartbeat over 10 subsystems (replaces ~84 cron jobs), and an A2A Global Mesh where every instance talks to every other instance. Apache-2.0, runs local.

cognitive-engine★ 8

Pure TypeScript library for building AI agents with cognitive capabilities - perception, memory, reasoning, emotions, and adaptive learning

genpark-dynamic-tool-dependency-dag-topological-resolver-skill★ 8

Dynamic multi-tool execution dependency DAG topological sorter (Semantic Kernel)

genpark-hierarchical-task-network-htn-planner-skill★ 8

GenPark AI Agent Skill - Hierarchical Task Network (HTN) decomposition engine recursively expanding compound high-level goals into primitive executable action sequences.

genpark-least-commitment-partial-order-planner-skill★ 8

GenPark AI Agent Skill - Partial-Order Causal Link (POCL) planning engine maintaining causal dependencies, open subgoals, and ordering constraint promotion/demotion.

More in Agent frameworks & infrastructure