Models & local runtimes AI agent tools

pooled

Newmodels & local runtimesOpen source

Peer-to-peer LLM inference in the browser: pool your laptops, phones and other devices into a room to run large open models for chat and coding agents, with no GPU server.

Added Oct 20, 2026

GLM-5

Newmodels & local runtimesOpen weights

Z.ai's open-weights GLM-5 model family built for coding and long-horizon agentic tasks, also offered through the Z.ai API.

Added Oct 18, 2026

Sidekick

Newmodels & local runtimesOpen source

Native macOS app for chatting offline with a local LLM that can draw on your files, folders and websites.

Added Oct 18, 2026

Ollama

Newmodels & local runtimesOpen source

Runs open models such as Qwen, Gemma, DeepSeek and gpt-oss locally or in Ollama's cloud, and connects them to agents like Claude Code, OpenClaw and Codex.

Added Oct 18, 2026

Jan

Newmodels & local runtimesOpen source

Open-source ChatGPT alternative that downloads and runs LLMs fully offline on your computer, with optional connections to cloud models.

Added Oct 18, 2026

LM Studio

Newmodels & local runtimesFreemium

Desktop app for running local and open models, with Bionic, its agent for work and code that creates documents, slides, PDFs and software.

Added Oct 18, 2026

Meta Muse Wonder

models & local runtimesPaid

Meta's new models for personal and professional agent tasks, available via Meta Model API and Muse Code.

Added Oct 14, 2026

ASI:One

models & local runtimesFreemium

Agentic LLM and chat app from Fetch.ai built to reason, plan and call other agents on the ASI Alliance network.

Added Oct 16, 2026

LocalAI

models & local runtimesOpen source

Self-hosted engine with an OpenAI-compatible API for running LLM, vision, voice and image models on your own hardware, including agents.

Added Oct 16, 2026

Oumi

models & local runtimesOpen source

Open platform for fine-tuning, evaluating and deploying open agentic LLMs and VLMs.

Added Oct 16, 2026

MiroThinker

models & local runtimesOpen weights

Deep research agent and open models tuned for complex research and forecasting tasks.

Added Oct 16, 2026

Lemonade

models & local runtimesOpen source

Local server that runs optimized LLMs on your GPU or NPU for local AI apps and agents.

Added Oct 16, 2026