Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 85 of 126
A toolkit for quickly implementing llm powered functionalities.
LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths and weaknesses of multiple open-source large language models (LLMs). LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
Simple interface for creating and managing LLM chains
Python library for developing LLM bots
Developer-first kit for LLM chatbots with streaming, memory, and personas (Discord-first)
common functions, utilities using multiple DB and LLM options.
Structured LLM based classification, clustering and extraction framework that works with all major API providers
Framework to build production-grade LLM-based classifiers
LLM plugin for content classification using various language models
A robust JSON repair and extraction tool for LLM outputs.
SDK for using LLM
A reusable library for LLM clients with LangChain framework
A library of ready-to-use LLM components
A tool for LLM agent conversations
A processor for LLM tasks
A dataclass interface for llms
A light-weight Python library 🐍 for deploying DAG chains of customizable Large Language Model operations. Leveraging the asyncio framework, LLM-Director allows developers to create, manage, and orchestrate actions and processes in an efficient and scalable manner. With its unique structure and integration with FastAPI, LLM-Director offes a robust solution for building applications, API endpoints, and workflow automation systems.
A modular, block-by-block LLM building library
A prompt graph definition and execution library for LLM app development.
Minimal llm_formats package exposing a single public function
LLM Foundation Tools
Finite State Machines for Large Language Models
Llm function is a decorator that uses llm to assemble reusable workflows from available tools to match input and output models.
Minimal metadata and discovery helpers for typed Python tools used by llm_function runtimes.
A lightweight Python library for creating reliable, contract-driven LLM functions whose core logic is implemented by an LLM.
Build semantic functions.
Agent framework with learning capabilities
LLM ベースのエージェントのワークフローをグラフ形式で記述・実行する軽量ライブラリ
Lightweight AI agent infrastructure — harness orchestrates, backends execute
LLM utilities and tools
A helper package to work with LLMs
Async multi-provider LLM client with typed tool calling, lazy output parsing, and Azure/Databricks/OpenRouter/LiteLLM/DeepSeek/local backends
A pythonic way to call llms & implement llm algorithms.
An LLM tool plugin for using Latchkey to make authenticated HTTP API requests.
A utility package for querying language models with pattern matching and retry logic
LLM Magics for Ipython created by kmkolasinski
Turn Python functions into typed LLM calls using docstrings as prompts
llm_matrix
An experimental project using Monte Carlo Tree Search (MCTS) to refine LLM responses for better accuracy and decision-making.
A framework to glue all your AI tools together
An open-source chatgpt tool ecosystem where you can combine tools with chatgpt and use natural language to do anything.
LLM Patch Driver is a framework for patching data objects using LLMs. It can generate and apply a single patch, or start the patching loop to fix complex validation issues.
A modular, async, composable AI pipeline library for building conversational agents and content processing pipelines
Pydantic data models and adapters for the LLM Protocol Suite.
A Redis-based queue task manager for LLM processing with intelligent token budget management
A library for advanced reasoning methods with large language models
A Python framework for building intelligent, recursive task decomposition systems powered by Large Language Models
This system utilizes a large language model (LLM) and reflection
LLM tools for repeated generation
A minimum Python package built on top of the LangChain framework to interact with LLM.
A Python package for LLM RPC operations
Recursive self aggregation
Framework-agnostic verb vocabulary for LLM agents
Salvage structured data from LLM responses that didn't follow instructions.
Microlib for sampling from an LLM
A library for advanced LLM sampling techniques
LLM-ify your JSON schemas
Fix broken JSON from Ollama, llama.cpp, vLLM. Auto-repair and offline validation.
A collection of LLM utils
This is a python sdk for llm
Provider-agnostic SDK for LLMs with async support and plugin providers.
Small, clean Python SDK for OpenAI-compatible LLM APIs.
Generate Data from LLM easily using LLMKit
Agent framework with tool calling for OpenAI, Anthropic, and Google
Real-time parser for LLM streaming responses with tag-based content extraction
A brief description of my package
lightweight library for building Trigger-Action programs with llm
LLM Task Handler
A lightweight Python library for creating tasks and workflows with Large Language Models (LLMs) using prompt templates.
Biblioteca Python que simplifica e unifica a definição e chamada de ferramentas para grandes modelos de linguagem (LLMs). Compatível com Ollama, LangChain, OpenAI e outros frameworks.
A library to easily build LLM agents with tool-using capabilities.
Implements a tool registry to make tool calling easier when using LLMs
Tool calling runtime for text-only LLMs with LangChain support
Library for interacting with the LLM Tool Store API
llm-toolbox is now LMtoolbox
A unified tool calling interface for LLM providers
The foundational shared event schema for the LLM Developer Toolkit
ToolPy is a Python module made to facilitate the creation of tools using LLMs.
Instant integration of external tools into LLM applications via automatic function calling.
JavaScript execution as a tool for LLM
Reusable Flask server for LLM backends (Ollama, LM Studio) with tool calling
Make simple_eval available as an LLM tool
LLM access to Topology
Orchestrate LLM tasks. Define workflows, run and track progress.
Utilities for our LLM projects (CWhy, ChatDBG, ...).
Moteur de workflow LLM basé sur des graphes d'agents
Core library for experimenting with LLMs - provides configuration, workers, tools, and LLM integrations
LLM utilities and tools
LLM utilities for handling inputs and outputs.
An interface that allows you to use LLMs in an ultra-simple way
Create a Python package.
Create a Python package.
A simplified function decorator for OpenAI and LiteLLM API calls.
A simplified function wrapper for OpenAI and LiteLLM API calls.
A Python package that enables batch submission of prompts to LLM APIs, with simplified interface and built-in async capabilities handled implicitly.
Directly Connecting Python to LLMs - Dataclasses & Interfaces <-> LLMs