Open-source tools

Open-source and local-first AI tools.

This page separates open-source, open-core, and source-available tools from commercial workflow listings so builders can focus on local AI, RAG, inference, coding agents, evaluation, and infrastructure.

Reviewed June 2026

How to use this page

Treat this as the open-source lane of the tools directory. Review each tool profile for licensing, deployment notes, maintenance requirements, alternatives, and links to official documentation.

42 open-source and open-core tools

Coding agent

Cline

Open VS Code coding agent for reviewable file edits, configurable model providers, and agentic coding workflows.

Best for: Developers who want a more controllable AI coding agent workflow.

Open source · VS Code extension

Tool details →

Local runner

Ollama

Run open models locally with a simple CLI, model library, desktop app, and local API.

Best for: Developers who want repeatable local model workflows and simple app integrations.

Open source · Local CLI, desktop app, and API server

Tool details →

Local runner

Jan

Open-source desktop app for running local AI models with a friendly ChatGPT-like interface.

Best for: Users who want a local-first desktop AI workspace with open-source software.

Open source · Desktop app

Tool details →

Local runner

GPT4All

Local AI desktop and SDK project for running open models on consumer machines.

Best for: Beginners and teams testing local private chat on desktops.

Open source · Desktop app and SDK

Tool details →

Local runner

llamafile

Mozilla-backed project for packaging LLMs into portable executable files.

Best for: Portable demos, simple local distribution, and experiments where one-file packaging matters.

Open source · Portable local executable

Tool details →

Local runner

llama.cpp

Core C/C++ inference project behind many local GGUF model workflows.

Best for: Low-level local inference, quantized models, CPU/GPU experimentation, and embedded deployments.

Open source · Local runtime/library

Tool details →

Chat workspace

Open WebUI

Self-hosted AI platform and chat interface for Ollama and other model backends.

Best for: Private ChatGPT-style workspaces over local or self-hosted models.

Open source · Self-hosted web app

Tool details →

Chat workspace

AnythingLLM

Open-source AI workspace for document chat, agents, and local or hosted models across desktop, self-hosted, and cloud setups.

Best for: Teams and individuals who want private document chat and multi-user AI workspaces without locking into one model provider.

Open source · Desktop app, self-hosted workspace, or hosted service

Tool details →

Chat workspace

LibreChat

Open-source multi-provider chat platform with a familiar assistant interface.

Best for: Teams wanting a self-hosted chat UI across multiple model providers.

Open source · Self-hosted web app

Tool details →

Chat workspace

LobeChat

Open-source modern chat UI for multiple model providers and assistant workflows.

Best for: Builders who want a polished self-hostable chat interface with provider flexibility.

Open source · Web app

Tool details →

Coding assistant

Continue

Open-source AI coding assistant for VS Code and JetBrains with configurable models and context.

Best for: Developers who want a local or provider-flexible coding assistant inside their existing IDE.

Open source · IDE extension

Tool details →

Coding agent

Aider

Terminal-based AI pair programmer that edits files in your local git repo.

Best for: Developers who like command-line workflows and want AI edits tied to git diffs.

Open source · CLI coding agent

Tool details →

Coding agent

Cline

Open-source VS Code coding agent for planning, editing files, and using tools.

Best for: Developers who want an agentic coding workflow inside VS Code.

Open source · VS Code extension

Tool details →

Coding agent

Roo Code

VS Code AI coding agent forked from the Cline ecosystem with multi-mode workflows.

Best for: Developers testing agentic coding modes, custom roles, and local/provider model setups.

Open source · VS Code extension

Tool details →

Coding agent

Kilo Code

Open-source VS Code coding agent focused on agentic development workflows.

Best for: Developers comparing modern Cline-style open coding agents.

Open source · VS Code extension

Tool details →

Coding agent

OpenCode

Terminal-based coding agent for working with models and repositories from the command line.

Best for: Developers who want a CLI-native coding agent experience.

Open source · CLI coding agent

Tool details →

Coding assistant

Tabby

Self-hosted AI coding assistant for code completion and team-controlled coding workflows.

Best for: Teams that want more control over code completion infrastructure.

Open source · Self-hosted coding assistant

Tool details →

RAG and workflow

Flowise

Open-source visual builder for AI agents, chat assistants, RAG flows, and multi-agent systems.

Best for: Builders who want to prototype or deploy agentic workflows visually before stitching everything together in custom code.

Open source · Open-source visual agent builder

Tool details →

RAG and workflow

LangChain

Framework ecosystem for LLM apps, agents, tools, retrieval, and observability workflows.

Best for: Developers building custom LLM apps that need integrations and agent patterns.

Open source · Python/JS framework

Tool details →

RAG and workflow

LlamaIndex

Data framework for connecting LLMs to documents, databases, retrieval, and agents.

Best for: RAG applications where data ingestion, indexing, and retrieval are central.

Open source · Python/TS framework

Tool details →

RAG and workflow

Haystack

Open-source framework for production-style search, RAG, and NLP pipelines.

Best for: Teams building retrieval pipelines with a more engineering-oriented architecture.

Open source · Python framework

Tool details →

Agent framework

CrewAI

Framework for orchestrating role-based AI agents and multi-agent workflows.

Best for: Experiments where multiple specialized agents coordinate around tasks.

Open source · Python framework

Tool details →

Agent framework

AutoGen

Open-source programming framework from Microsoft for building agentic and multi-agent AI systems.

Best for: Developers exploring multi-agent workflows, tool use, and code-first orchestration patterns.

Open source · Programming framework

Tool details →

Automation

n8n

Workflow automation platform for connecting AI tools, APIs, databases, and business systems.

Best for: Builders who want AI workflows connected to real business processes and integrations.

Source-available / fair-code · Automation platform

Tool details →

Vector database

Qdrant

Open-source vector database with strong filtering and production-oriented retrieval features.

Best for: RAG apps that need vector search, metadata filtering, and self-hosted or managed options.

Open source · Vector database

Tool details →

Vector database

Chroma

Open-source embedding database commonly used for quick RAG prototypes.

Best for: Small teams and prototypes that need fast local retrieval setup.

Open source · Vector database

Tool details →

Vector database

Weaviate

Open-source vector database and AI-native search platform with hybrid search features.

Best for: Teams that want vector search, hybrid search, and managed/self-hosted deployment choices.

Open source · Vector database

Tool details →

Vector database

Milvus

Open-source vector database designed for large-scale similarity search.

Best for: Teams planning larger vector search systems and scalable retrieval infrastructure.

Open source · Vector database

Tool details →

Vector database

LanceDB

Developer-friendly vector database built around Lance columnar data format workflows.

Best for: AI apps that need local-first or data-lake-friendly vector storage.

Open source · Vector database

Tool details →

Vector database

pgvector

PostgreSQL extension for storing embeddings and running vector similarity search.

Best for: Teams that already use Postgres and want a simple RAG database path.

Open source · Database extension

Tool details →

Inference serving

vLLM

High-throughput open-source LLM serving engine for production and research workloads.

Best for: Serving open models at higher throughput with batching and OpenAI-compatible APIs.

Open source · Inference server

Tool details →

Inference serving

SGLang

Fast serving framework and programming interface for language model applications.

Best for: Serving modern open models with efficient inference and structured generation workflows.

Open source · Inference server/framework

Tool details →

Inference serving

Text Generation Inference

Hugging Face server for deploying and serving text generation models.

Best for: Teams already using Hugging Face model workflows and deployment patterns.

Open source · Inference server

Tool details →

Inference serving

LiteLLM

Proxy and SDK for routing requests across many LLM providers with OpenAI-compatible interfaces.

Best for: Teams managing multiple model providers, budgets, keys, and routing rules.

Open source · LLM gateway/proxy

Tool details →

Inference serving

LocalAI

Open-source OpenAI-compatible local inference server for multiple model types.

Best for: Builders who want a self-hosted local API that mimics OpenAI-style endpoints.

Open source · Local inference server

Tool details →

Inference serving

BentoML

Model serving platform for packaging, deploying, and operating AI services.

Best for: Teams turning model code into deployable services with repeatable infrastructure.

Open source · AI service platform

Tool details →

Evaluation and observability

Langfuse

Open-source observability, tracing, prompt management, and evaluation platform for LLM apps.

Best for: Teams shipping LLM apps that need traces, evaluations, prompts, and production visibility.

Open source · Observability platform

Tool details →

Evaluation and observability

Phoenix

Arize Phoenix is an open-source observability and evaluation tool for LLM and ML systems.

Best for: Teams debugging RAG, tracing LLM calls, and evaluating application behavior.

Open source · Observability and eval platform

Tool details →

Evaluation and observability

OpenTelemetry

Open standard and ecosystem for traces, metrics, and logs increasingly used in LLM app observability.

Best for: Engineering teams that want AI telemetry to fit existing observability systems.

Open source · Observability standard/tooling

Tool details →

Evaluation and observability

Ragas

Open-source framework for evaluating RAG pipelines and LLM application quality.

Best for: RAG builders who need repeatable retrieval and answer-quality checks.

Open source · Evaluation framework

Tool details →

Evaluation and observability

DeepEval

Open-source LLM evaluation framework for unit-testing model outputs and app behavior.

Best for: Developers who want tests around LLM responses, agents, and RAG systems.

Open source · Evaluation framework

Tool details →

Image workflows

ComfyUI

Node-based interface for building advanced local image generation workflows.

Best for: Creators and builders who need precise, reusable image generation pipelines.

Open source · Local node-based workflow app

Tool details →