Agent frameworks & infrastructure
Local LLM runtimes
1,401 agents · most starred first
Local LLM runtimes, page 12 of 15
Interact with llama-server models
LLM plugin providing access to llama.cpp server models
Access llamafile localhost models via LLM
LLM plugin for models served by LMStudio (local LLM studio HTTP API)
Agentic interface to local LLMs with tree-based context management.
LLM plugin for running models using MLC
Support for MLX models in LLM
Plugin for LLM adding support for the MPT-30B language model
Advanced system information tool for local LLM usage
LLM plugin providing access to models running on an Ollama server
Unofficial python bindings for llm-rs. 🐍❤️🦀
Unofficial python bindings for llm-rs.
Unofficial python bindings for llm-rs. 🐍❤️🦀
Unofficial python bindings for llm-rs. 🐍❤️🦀
SmolLM2-135M-Instruct.Q4_1 for LLM
Run large language models.
Plugin for llm adding support for 🤗 Hugging Face Transformers
A Python client for interacting with llamafile local LLM instances
Hundreds of models & providers. One command to find what runs on your hardware.
A python package for developing AI applications with local LLMs.
Professional open source client for running large language models locally
LLM Package Manager — download, run, and share AI models from the command line
A CLI tool to check if your local hardware can run a Hugging Face LLM.
A fast, modern CLI that shows which local LLMs fit on your machine
One command. Full LLM stack. Zero config.
llmster
Tools using ollama and torch that are easy and nice to have for working with local LLMs
Explore the answer-space for any prompt and any MLX-supported model.
A lightweight Python toolkit for LLM text and image workflows with Ollama.
Local-first AI agent orchestrator — manages llama.cpp, local models, and cloud APIs
A flask server for a chrome extension that querys llm models
Local-LLM is a llama.cpp server in Docker with OpenAI Style Endpoints.
Find which local LLMs can run on your system
One Python API for offline LLMs and local servers: Ollama, AirLLM, SGLang, vLLM, LM Studio and llama.cpp
Local-first LLM wrapper (import local_llm_wrapper) with pluggable transports (Ollama, Apple, optional Claude Code CLI) and a stable text-in text-out API.
An api to query local language models using different backends
Local Collaborative LLMs -- Frontier AI on a Student Budget
Browser UI for Ollama • Local LLM Interface • Web Chat Client for Local AI Models
Tools for working with Ollama
A command-line interface for Ollama API
Merlin — a fast local LLM for agentic coding on Apple Silicon
An EXPERIMENTAL Ollama decorator for Metaflow
Lightweight GPT implementation designed for resource-constrained environments
('A library for augmenting large language models using MLX',)
Minimal OpenAI-compatible server for GPT-OSS models on Apple Silicon with MLX
Large Language Models (LLMs) applications and tools running on Apple Silicon in real-time with Apple MLX
A locally runnable LLM
llmcli 模型下载
Nano Llama
Ollama inference provider for the NucleusIQ AI agent framework (official ollama Python SDK).
HTTPS proxy with CORS support for Ollama
This module replaces AI from html_editor to use an Ollama server instead of OpenAI through Odoo IAP.
Opinionated, Ollama Client based Python Tools.
The official Python client for Ollama.
A beautiful, agentic CLI for Ollama — run local LLMs with auto tool-calling, memory, and more
Ollama model management, trends viewing, testing & external runner assistant
A Python client for the Ollama API
Macos status bar app that allows you to start/stop/view ollama from the menu bar.
Run text LLM prompts over a list of texts
A simple Python wrapper for Ollama API
Text classification with constrained output and confidence scoring across multiple LLM backends
Simple command line tool that reads a text from stdin and pipes it to Ollama. One can set all Ollama options on commandline as well as define termination criteria in terms of maximum number of lines, paragraphs, or repeated lines.
Lightweight CLI client for a remote Ollama server
Object-oriented library for interacting with Ollama Cloud
Tools for working with Ollama model data
A library and Hugging Face model downloader for Ollama.
A Python library for the Ollama API.
Ollama Inspect — minimal GGUF inspector web server
Install Ollama from a Python CLI.
Validate structured outputs from LLMs with Ollama and automatic retries.
Local LLM infrastructure with monitoring dashboard for distributed AI applications
Manage Ollama models from your commandline!
Python client for the ollama-models API — search and list Ollama model weights
CLI tools to export and import Ollama models (.tar.gz)
Expose OLLAMA models to the internet on a remote server via tunneling
Scan your hardware and find compatible Ollama LLMs
A Python package that ensures the Ollama server is running and ready with the models your project expects.
Provide interaction service to LLM with Ollama.
A package to manage Ollama service and models.
CLI tool for Ollama - backup, restore, update, and list models
A comprehensive Python client library for the Ollama API
A lightweight client for interacting with LLMs served via Ollama
A simple Python package for Ollama utilities with built-in AI vibe tests
Ollamate is a simple AI assistant for local LLMs hosted on your machine using Ollama. it will support some custom functions and a RAG system.
OllamaWebUI-A Simple Flask WebUI, You Can Chat With Ollama On Web|Flask聊天界面,可以自定义设置Ollama Api(python学霸公众号)
A package to manage Ollama service and models.
Bundle Ollama models into single portable archives for transfer between machines.
OnnxLLM: A collection of Onnx Large Language Models.
Ollama and llama.cpp providers for the OpenAI Agents SDK
One command launcher for running OpenCode with a local llama.cpp model.
Multi-tier local LLM stack: llama-swap + FastAPI auto-router + opencode wiring.
openllama
High-performance LLM runtime for Apple Silicon
python inference handler for agents
A question solver plugin for ovos
A question solver plugin for ovos
Python bindings for OxiLLaMa — Pure Rust LLM inference engine
Terminal UI for Ollama and other LLM providers
A patch to enable llama.cpp as acceleration backend on windows platform