Integrations

Open-source automation with AI-powered workflows

Use fine-tuned models with Aider's AI pair programming CLI

All-in-one AI desktop app for private knowledge bases

Microsoft's multi-agent conversation framework

Deploy custom AI behind Bolt-scaffolded apps

Open-source browser automation agent for any LLM

Visual workflow engine for AI generation pipelines

Connect fine-tuned models to Continue's open-source AI coding assistant

Multi-agent orchestration with role-based AI crews

Fine-tune coding models on your codebase patterns

Open-source platform for LLM app development

Serve fine-tuned models with ExLlamaV2's fast quantized inference

Visual LLM workflows with drag-and-drop simplicity

Enhance Copilot with fine-tuned models trained on your codebase

Privacy-first local AI by Nomic AI

Production NLP pipelines with fine-tuned precision

Self-improving open-source agent framework with persistent skills

Access thousands of open-source models

Your open-source local AI assistant

Lightweight GGUF inference for creative AI workflows

Build context-aware AI applications with fine-tuned models

Graph-based agent orchestration for production workflows

Stateful agents with persistent memory and infinite context

Blazing-fast inference on any hardware

Connect fine-tuned models to your private data

Run AI models locally with a polished desktop UI

Local model server with OpenAI-compatible API

Drop-in OpenAI API replacement powered by your fine-tuned models

AI app builder with fine-tuned model backends

Trigger fine-tuned model inference from Make.com scenarios

TypeScript agent framework on the Vercel AI SDK

Run fine-tuned models natively on Apple Silicon with MLX

Beautiful local AI chat with model management

Connect n8n AI agent nodes to Ertas-trained local models

Run models locally with one command

Self-hosted ChatGPT-like interface for local models

Power your AI agent with fine-tuned local models

Unified API gateway for any LLM

Optimize fine-tuned models for Intel hardware with OpenVINO

Cloud IDE with instant AI model deployment

Hugging Face's minimal code-action agent framework

Build production AI agents with fine-tuned reasoning

Complement Tabnine completions with fine-tuned domain models

Deploy fine-tuned models with NVIDIA's optimized inference engine

Feature-rich web interface for local LLM inference

Compare Unsloth CLI workflow vs Ertas Studio visual pipeline

Unified TypeScript interface to 3,300+ models from 94 providers

High-throughput production inference engine

Train domain-specific coding models for Windsurf's AI features

No-code AI automation for any business workflow