Ollama Python Packages

ollama

Ollama Python library

strands-agents

A model-driven approach to building AI agents in just a few lines of code.

strands-agents-tools

A set of tools that gives agents powerful capabilities.

agentops

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

npmai

🚀 npmai By Sonu Kumar (Viral Boy) npmai is a lightweight Python package designed to bridge the gap between users and open-source LLMs.Connect with Ollama and 10+ other powerful models instantly—no installation, no login, and no API keys required, and help in development of RAG Agents on cloud without signup and local installations in free of cost.

strands-agents-builder

An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder can help you to build your own agents and tools.

shell-gpt

A command-line productivity tool powered by AI large language models like GPT-5, will help you accomplish your tasks faster and more efficiently.

specsmith

Applied Epistemic Engineering toolkit · AEE agent sessions · execution profiles · FPGA/HDL governance · tool installer · 50+ CLI commands · Anthropic/OpenAI/Gemini/Ollama

cafitac-hermit-agent

Quiet MCP executor for Claude Code and Codex. Offload edits, tests, refactors, and commits to cheaper local or flat-rate models.

pygpt-net

Desktop AI Assistant powered by GPT-5, GPT-4, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, chat, vision, voice, RAG, image and video generation, agents, tools, MCP, plugins, speech synthesis and recognition, web search, memory, presets, assistants,and more. Linux, Windows, Mac

local-deep-research

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.

whichllm

Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.

soup-cli

Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.

agentmake

AgentMake AI: a kit for developing agentic AI applications that support 24 AI backends and and work with 7 agentic components, such as tools and agents. (Developer: Eliran Wong) Supported backends: anthropic, azure, azure_any, cohere, custom, deepseek, genai, github, github_any, googleai, groq, llamacpp, mistral, ollama, openai, vertexai, xai

strands-agents-mcp-server

This MCP server provides documentation about Strands Agents to your GenAI tools, so you can use your favorite AI coding assistant to vibe-code Strands Agents.

srclight

Deep code indexing MCP server for AI agents. 25 tools: hybrid FTS5 + embedding search, call graphs, git blame/hotspots, build system analysis. Multi-repo workspaces, GPU-accelerated semantic search, 10 languages via tree-sitter. Fully local, zero cloud dependencies.

claude-code-llm-router

DEPRECATED: Use 'llm-routing' instead. This package provides redirect to the new package.

arcllm-sdk

Fast, typed, dependency-light Python SDK for 25+ LLM providers (OpenAI, Anthropic, Bedrock, Vertex, xAI, Groq, Cohere, and more) with a single OpenAI-compatible API

npcpy

The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.

aipdf

A tool to OCR PDFs using gen-AI models

notebook-intelligence

A JupyterLab extension supporting Claude Code, Copilot, Ollama, and OpenAI-compatible LLMs, with MCP, skills, plugins, and notebook agents.

nvhive

Rootless NVIDIA GPU AI lab: local LLMs, ComfyUI, agents, creative/game/music packs, and a self-healing setup wizard.

komit

AI-powered git commit message generator using local LLMs

llm-autotune

Zero-config local LLM optimization for Ollama, LM Studio, and Apple Silicon MLX. Reduces TTFT by 40%, wall time for local agents by 46%, and RAM usage by 3x.