Open Source Alternatives LogoOpen Source Alternatives
AlternativesBlogAdvertise
Open Source Alternatives LogoOpen Source Alternatives

Stay Updated

Subscribe to our newsletter for the latest news and updates about Alternatives

Open Source Alternatives LogoOpen Source Alternatives

Handpicked Open Source Alternatives to Paid Softwares

Product
  • Search
  • Categories
  • Tag
  • Sign In
Resources
  • Blog
  • Collection
  • Submit
  • Advertise your tool
Company
  • Privacy Policy
  • Terms of Service
  • Refund Policy
  • Sitemap
Copyright © 2026 All Rights Reserved.
Home/Categories/AI & Machine Learning/OpenYak
icon of OpenYak

OpenYak

Open source alternative to Zapier Central, Glean Assistant and Lindy

OpenYak is a local AI agent that enhances productivity with multi-model support and local-first privacy.

781 starsPythonMITActive this month
Visit websiteGitHub repo
image of OpenYak
Contents
  1. 01Who OpenYak is for
  2. 02The problem it solves
  3. 03How it solves it
  4. 04Strengths and trade-offs
  5. 05Tech stack
  6. 06FAQ
  7. 07Similar open-source tools
TL;DR

OpenYak is a local-first desktop AI agent for working with files, tools, long threads, local models, and bring-your-own provider keys. It replaces hosted AI workspaces for users who want agent workflows on their own computer without an OpenYak account or telemetry. MIT licensed.MIT · Python · 781 stars · Active this month

who it's for

Who OpenYak is for#

Knowledge workers handling sensitive files

OpenYak fits users who want AI help with local documents while keeping workflow state on their own device.

Skip if:

Your organization requires all AI workflows to run through a centrally managed SaaS admin console.

Developers comparing local and cloud models

The local model and BYOK paths make it useful for testing which tasks can stay local and which need a hosted model.

Skip if:

You do not want to manage model runtimes, provider keys, or desktop agent permissions.

the problem

The problem it solves#

Hosted AI assistants are convenient, but they often pull files, conversations, memory, and workflow state into a vendor account. That creates privacy, billing, and portability concerns for users who want AI help on sensitive local work.

Desktop agent workflows need more than a chat box. Users want to attach documents, keep context across long tasks, choose local or cloud models, and produce reusable artifacts without turning every task into a cloud workspace.

how OpenYak solves it

How it solves it#

Local-first desktop runtime

OpenYak keeps files, conversations, memory, generated artifacts, tool permissions, and workflow state on the user's device.

Local or BYOK model choice

OpenYak supports local models through Rapid-MLX or Ollama and direct BYOK calls to providers such as OpenRouter, OpenAI, Anthropic, and Google.

File-centered agent workflows

OpenYak supports DOCX, XLSX, PPTX, PDFs, CSVs, and local project context, then can generate briefs, tables, plans, and reusable artifacts.

strengths · trade-offs

Strengths and trade-offs#

Strengths

  • No account or telemetry requirementOpenYak states that it requires no OpenYak account and includes no telemetry, which is a strong differentiator against hosted AI workspaces.
  • Model boundary controlOpenYak requires no OpenYak account and includes no telemetry, which is a strong differentiator against hosted AI workspaces.

Trade-offs

  • -Local setup shifts responsibility to the userLocal-first workflows improve control but require users to manage desktop app updates, local model performance, provider keys, and file permissions.
tech stack · detected from GitHub

What it's built on#

Languages
JavaScriptPythonRustTypeScript
Frameworks
Next.jsReact
Tooling
esbuild
frequently asked

FAQ#

Does OpenYak require an account?

No. OpenYak does not require an OpenYak account.

Can OpenYak use local models?

Yes. OpenYak supports local models through Rapid-MLX or Ollama, plus BYOK access to cloud providers.

What files can OpenYak work with?

OpenYak supports DOCX, XLSX, PPTX, PDFs, CSVs, and local project context as inputs for agent workflows.

also worth a look

Similar open-source tools#

Screenpipe

Screenpipe

Record your screen and audio 24/7 for local AI automation

18.7KRust
Atomic Bot

Atomic Bot

One-click OpenClaw installer and agent setup bot

307TypeScriptMIT
Jan

Jan

Run open source LLMs on your own hardware with no cloud required

42.5KTypeScript
AnythingLLM

AnythingLLM

Chat with your documents using any LLM, private and self-hosted

60KJavaScriptMIT
Khoj

Khoj

Self-hosted AI assistant that searches your notes and web

34.6KPythonAGPL-3.0
Scira

Scira

Open source AI search engine that retrieves cited sources

11.7KTypeScriptAGPL-3.0

Repository

Stars
781
Forks
53
License
MIT
Latest
v1.1.10
Last commit
15 days ago
Last verified
May 13, 2026
Repo
openyak/openyak ↗

Additional details

Language
Python
Open issues
19
Contributors
4
First release
2026

Categories

AI & Machine LearningLLMOps & AI ToolingBusiness & Productivity

Tags

AI AgentsLocal-firstLLMAI Coding AssistantPersonal AssistantSelf HostedWorkflow Automation