Skip to main content
📖 The AI Tool Bible

Self-hosted AI tools

Editorial picks for "self hosted ai".

48 tools

FL

Flux

Featured
Image Generation · Flux.1 [schnell / dev / pro]
9.0

Black Forest Labs' open-weights image model — rivals Midjourney quality.

Freemium· FLUX.2 [max]: $0.07 · FLUX.2 [pro]: $0.03 · FLUX.2 [klein] 9B: $0.015 · FLUX.2 [klein] 4B: $0.014 · FLUX.2 [flex]: $0.05open sourceself-hosted
LA

LangGraph

Featured
Agents · BYO (Claude / GPT / open)
8.8

Agent Orchestration Framework for Reliable AI Agents

Freemium· Developer: $0 / seat per month then pay as you go; Plus: $39 / seat per month then pay as you go; Enterprise: Custom pricing then pay as you goLong-running, stateful agentsMulti-agent and hierarchical architectures
LL

LlamaIndex

Featured
RAG · BYO (Claude / GPT / open)
8.7

Data framework for connecting LLMs to your data.

Freemium· Free tier · from $500/moRAGdata ingestion
CR

CrewAI

Featured
Agents · BYO (Claude / GPT / open)
8.4

The Enterprise Agent Build & Runtime for the work your business runs on

Free· Basic: FreeAutomating long horizon workIdentifying automation opportunities in tickets, chats, apps, and workflows
SD

Stable Diffusion

Image Generation · SD 3.5 / SDXL
8.8

Enterprise-ready creative partner delivering professional-grade generative AI tools for content production at scale.

FreeMarketing asset creationGame and film sound design
CL

Cline

Coding · Model-agnostic: Claude (Anthropic), GPT (OpenAI), Gemini (Google), DeepSeek, Grok, Mistral, Cerebras, plus local Ollama/LM Studio
8.7

Open-source agentic coding assistant that plans, edits, and runs code inside your IDE

Freemium· Free tierMulti-file feature scaffoldingLarge-scale refactors
EV

Elasticsearch Vector Search

RAG · BYO embeddings (OpenAI, Cohere, Hugging Face, Mistral, Bedrock, Vertex, Azure) plus Elastic's built-in ELSER sparse model and E5 dense model
8.7

Hybrid vector + keyword search in the enterprise-grade Elasticsearch engine

Freemium· Resource based pricing: Pay as you go (monthly) or prepaid · Usage based pricing: Pay as you go (monthly) or prepaid · License based pricing: ?RAG chatbot over enterprise docsHybrid semantic + keyword product search
WH

Whisper

Audio · Whisper large-v3
8.6

Whisper is an automatic speech recognition system trained on 680,000 hours of multilingual and multitask supervised data.

FreeMultilingual speech transcriptionTo-English speech translation
QU

Quivr

RAG · Multi-model (OpenAI, Anthropic, Mistral, Gemma)
8.4

Quivr helps users build a second brain using Generative AI to act as a personal assistant.

Free
WE

Weaviate

RAG · Hosted vector DB (not an LLM)
8.4

Open-source AI-native vector database supporting hybrid search, multi-tenancy, and RAG.

FreemiumSearchMulti-tenancy
CL

ClearML

Agents · Model-agnostic
8.3

End-to-end platform for streamlining AI development and deployment.

Freemium· Community plan is $0; Pro plan is $15 per user/month plus usageExperiment trackingDataset versioning
FL

Flyte

Agents · Multi-model
8.3

Flyte 2 is a durable AI runtime for running training, serving, and agent workloads with automatic recovery from failures.

FreemiumAI trainingModel serving
HE

Helicone

Evaluation · Platform (any LLM)
8.3

AI Gateway and LLM Observability platform

Freemium· Hobby plan is Free; Pro plan is $79 per month; Team plan is $799 per monthCost tracking for LLM modelsMonitoring local and cloud LLM interactions
LA

LangChain

RAG · BYO (any major LLM)
8.3

The broad LLM application framework — chains, agents, retrievers.

Freemium· Free open-source; LangSmith paidgeneral LLM appsRAG
LL

Llama

Fine-tuning · Llama 4 (Maverick, Scout), Llama 3.3/3.2/3.1
8.3

Meta's open-weight LLM family covering 1B mobile models up to 405B frontier and natively multimodal 10M-context Llama 4 variants.

Freemiumself-hosted-llmfine-tuning
L3

Llama 3

Writing · Llama 3 / 3.1 (8B, 70B, 405B)
8.3

Meta's open-weights LLM family that put serious frontier-adjacent models in everyone's hands.

Free· Weights free under Meta Llama Community License; inference cost via self-hosting or 3rd-party providerschatlong-context reasoning
LS

LM Studio

Agents · Multi-model (gpt-oss, Qwen3, Gemma, DeepSeek-R1, Llama, others)
8.3

LM Studio Bionic is a natively local agent for open models built for creativity, work, and code.

Freemium· Free plan at $0; Bionic+ plan at $20 USD / month; Pro plan at $100 USD / monthCoding tasks and automationsReal-time voice transcription
N8

n8n

Agents · Multi-model
8.3

Workflow automation platform combining AI capabilities with business process automation, offering code flexibility and no-code speed.

FreemiumBuilding AI agentsWorkflow automation
VA

Vanna.ai

RAG · Multi-model (Anthropic, OpenAI, Gemini, Ollama)
8.3

Vanna 2.0 is a user-aware AI agent framework that connects LLMs to your database.

Freemium· from $50/monatural language database interactionquerying company systems of record
VL

vLLM

Fine-tuning · Multi-model (open-weight LLMs: Llama, Qwen, DeepSeek, Mistral, Gemma, Phi, etc.)
8.3

Open-source high-throughput inference engine for serving LLMs with PagedAttention and continuous batching.

Free· Free and open-source (Apache 2.0); self-hosted infrastructure costs applyllm-servingself-hosted-inference
AU

AudioCraft

Audio · MusicGen, AudioGen, EnCodec
8.2

AudioCraft is a code base for generative audio needs including music, sound effects, and compression.

Free· Free and open source; self-hostedtext-to-sound generationtext-to-music generation
BE

BentoML

Agents · Multi-model
8.2

Open-source framework and managed platform for serving and scaling AI models in production.

Freemium· OSS free (Apache 2.0); managed Bento cloud has free tier + usage-based pricingmodel-servingllm-inference
BU

Browser Use

Agents · Multi-model (BYO LLM; Claude in hosted Box)
8.2

Cloud browser infrastructure and hosted agents for AI automation, with stealth browsers available at $0.02 per hour.

Freemium· Free tier
FE

Feast

RAG
8.2

Feast is an open source feature store that delivers structured data to AI and LLM applications at high scale during training and inference.

Free· Free, open source (Apache 2.0); self-hostedReal-time recommendationsFraud detection
GE

Great Expectations

Evaluation
8.2

Open source framework for testing, validating, and documenting data quality across modern data pipelines, workflows, and teams.

Freemiumdata quality testing and validationnotifying teams of critical failures
HA

Hermes Agent

Agents · Multi-model (300+ via Nous Portal)
8.2

Open-source, self-hosted AI agent with persistent memory, autonomous skill creation, and a messaging gateway for Telegram, Discord, Slack, WhatsApp, Signal, and email.

Freemium· Free plan costs $0personal-assistanttask-automation
JA

Jan

Writing · Multi-model (local open-weights + OpenAI/Claude/Gemini via API)
8.2

Open-source desktop ChatGPT alternative that runs local LLMs and connects to cloud models.

FreeRunning open-source AI models locallyConnecting to cloud models like GPT and Claude
LA

LanceDB

RAG
8.2

Open-source multimodal lakehouse and vector database built for AI training and retrieval at petabyte scale.

Freemium· Open-source free; LanceDB Cloud and Enterprise via contact salesvector-searchrag
LI

LibreChat

Writing · Multi-model (OpenAI, Anthropic, Google, AWS Bedrock, Azure, Ollama, and others)
8.2

LibreChat brings together all AI conversations in one unified, customizable interface.

Free· Free and open source; self-hosted (you pay model providers for API usage)unified AI conversationsAI agents and tools
LU

Ludwig

Fine-tuning · Multi-model (PyTorch + HuggingFace Transformers)
8.2

Open-source declarative deep learning framework for building, fine-tuning, and deploying custom models across tabular, text, image, and audio data without writing training loops.

Free· Free, Apache 2.0 open sourceLLM fine-tuningText classification
MS

Msty

Writing · Multi-model (Ollama, Claude, GPT, Gemini, others)
8.2

Freemium· Free: $0; Aurum: $149 USD per user / year; Aurum Lifetime: $349 USD per user (one-time purchase)
SG

SGLang

Fine-tuning · Multi-model (DeepSeek, Qwen, Llama, Mistral, GLM, GPT-OSS)
8.2

Open-source inference framework for large language, vision-language, and diffusion models optimized for agentic workloads and large-scale serving.

FreeAgentic workloadsLarge-scale serving
SI

Sim

Agents · Multi-model (Claude, OpenAI, Google)
8.2

Open-source AI workspace for building, deploying, and managing AI agents.

Freemium· Free: $0; Pro: $25 per user/month; Max: $100 per user/monthStoring structured data for agentsManaging team uploads and agent outputs
UN

Unsloth

Fine-tuning · Llama, Mistral, Gemma, Qwen, GLM (multi-model)
8.2

Open-source LLM fine-tuning toolkit with custom kernels that train 2-30x faster and use up to 90% less VRAM.

Freemium· Free open-source; Pro and Enterprise contact saleslora-finetuningqlora
VE

Vespa

RAG · Hosted search engine (not an LLM)
8.2

Yahoo's open-source search engine with vector + sparse retrieval.

Freemium· Free open-source; Vespa Cloud paidlarge-scale searchranking
CH

Chroma

RAG · Hosted vector DB (not an LLM)
8.1

Open-source search infrastructure for AI

Freemium· Starter: $0 /month + usage; Team: $250 /month + usageVector, full-text, regex, and metadata searchDataset versioning, A/B testing, and roll-outs
CU

Cube

RAG · Multi-model
8.1

Cube is an agentic analytics platform built on a semantic layer for AI-native business intelligence and embedded analytics.

Freemium· Free plan is free forever; Starter plan is $40 per developer per month; Premium plan is $80 per developer per monthinternal business intelligenceembedded analytics
LA

Langflow

Agents · Multi-model
8.1

Low-code AI builder for agentic and retrieval-augmented generation (RAG) applications.

Free· Free open-source version with full featuresBuilding AI-powered agentsRetrieval-augmented generation (RAG) applications
LO

LocalAI

Writing · Multi-model (llama.cpp, diffusers, whisper, etc.)
8.1

LocalAI runs open models on the user's own hardware.

FreeChatting with open models on local hardwareRunning Python scripts on data files
MA

Mastra

Agents · Multi-model (90+ providers)
8.1

Open-source TypeScript framework for building AI-powered applications and agents.

Freemium· Free tier · from $25/moConversational agentsDomain-specific copilots
ML

MLflow

Evaluation · Multi-model
8.1

Open-source platform for tracking, evaluating, and deploying ML models and LLM applications.

Free· Free and open source (Apache 2.0); managed offering via Databricksllm-evaluationexperiment-tracking
OP

Optuna

Fine-tuning
8.1

An automatic hyperparameter optimization software framework designed for machine learning.

FreeHyperparameter optimizationScikit-Learn model tuning
PY

PyGPT

Writing · Multi-model (GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Ollama)
8.1

Open-source desktop AI assistant for Windows, Linux and macOS with agents, RAG, Python tools, MCP, vision, image/video generation and Ollama.

Free· Free and open-source (MIT); bring your own provider API keysdesktop-ai-assistantchat-with-files
RA

RAGFlow

RAG · Multi-model
8.1

Open-source RAG engine combining retrieval and agent capabilities to create a context layer for LLMs.

Freemium· Free plan at $0/month; Starter plan at $29/month or $59/month; Pro plan at $129/month or $259/monthEquity investment researchLegal precedent analysis
RT

Ray Tune

Fine-tuning
8.1

Python library for experiment execution and hyperparameter tuning at any scale.

Free· Open-source (Apache 2.0); managed via Anyscale offers a $100 starting credithyperparameter-tuningearly-stopping
RE

Repomix

Coding · ChatGPT, Claude, Gemini, Grok
8.1

Repomix packages an entire codebase into a single AI-friendly file.

FreeCode reviewsRefactoring
GE

Genmo

Video · Mochi 1
8.0

Open-source text-to-video model (Mochi 1) with a hosted playground for turning prompts into short clips.

Freemium· Free tiertext-to-videogenerative-video
OP

OpenHands

Agents · Multi-model (Claude, Gemini, GPT/Codex)
8.0

OpenHands is an AI agent platform for software development that executes real engineering work.

Freemium· Free tier · from $500/moIssue triage and draft PR creationDocumentation and codebase map updates