Local LLM
Open Webui
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
★ 153.9k starsCustom (check repo)
View guide →// local-llm · Orkas-AI/Orkas
Orkas
Orkas is an open-source local llm project by Orkas-AI (Orkas-AI/Orkas on GitHub). It has 2,151 GitHub stars and 88 forks, is released under the MIT license, and was last updated on GitHub on 3 October 2026.
Local-first desktop where a commander LLM directs specialist coding agents.
💎 Hidden gem★ 2.2k stars⑂ 88 forksMITupdated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- Orkas-AI/Orkas
- GitHub stars
- 2,151
- Forks
- 88
- License
- MIT
- Last updated on GitHub
- 3 October 2026
- Category
- Local LLM
- Listing
- Hidden gem — a shorter page for a lesser-known project
- Official site
- Official site
// how it works
How it works
- Install Orkas
Get the desktop app for your OS.
- Add your keys
Bring your own API keys for models.
- Connect CLIs
Link your installed coding CLIs.
- Command the team
The commander LLM directs specialist agents.
// features
Why people love it
Commander model
One LLM orchestrates specialist sub-agents.
CLI integration
Runs Claude Code, Codex, OpenCode, and more.
Self-evolving
Agents improve via reflection.
Skill crystallization
Repeated successes become reusable skills.
Bring your own keys
No bundled model markup.
Cross-platform
macOS, Windows, and Linux.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/Orkas-AI/Orkas.git cd Orkas - Step 2 — Check the README
Every project documents its own setup; start with install requirements.
cat README.md | head -60 - Step 3 — Run it
Follow the project's launch command — Docker, pip, npm, or a binary release.
# see README for the exact launch command
// use cases
What you can build
- Orchestrate multiple coding CLIs.
- Run specialist agents on big tasks.
- Keep AI coding local-first.
- Build reusable skills from successes.
Advertisement
// faq
Questions, answered
Do I need API keys?
Yes, it is bring-your-own-keys for the models you use.
Is orkas free for commercial use?
MIT licensed — commercial use allowed.
Which coding CLIs work with it?
Claude Code, Codex, OpenCode, OpenClaw, and Hermes are named.
What is skill crystallization?
Repeated successful patterns get saved as reusable skills.
Is my code sent to the cloud?
It is local-first, but model calls go wherever your keys point.
// keep exploring
Similar tools
AI Chat
LibreChat
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI…
★ 45.3k starsMIT
View guide →AI Chat
chatbox
Powerful AI Client
★ 41.9k starsGPL-3.0
View guide →Local LLM
starnet
Pixel-art desktop where your local-first AI agents visibly do real work.
★ 1.0k starsMIT
View guide →Local LLM
Dark-Moon
Autonomous AI pentesting with 50 specialist agents on a local LLM.
★ 992 starsGPL-3.0
View guide →Local LLM
alethe-agents
Local-first desktop workspace designed for running.
★ 804 starsAGPL-3.0
View guide →// alternatives
Alternatives in Local LLM
The most-starred other Local LLM projects in the LibreAI catalogue — the realistic shortlist if Orkas is not the right fit.
- Ollama★ 182.1k
The simplest way to run open language models on your own machine.
- Open Webui★ 153.9k
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
- llama.cpp★ 130.2k
LLM inference in C/C++
- vLLM★ 93.1k
A high-throughput and memory-efficient inference and serving engine for LLMs
- lobehub★ 83.0k
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
// more in local-llm
More in Local LLM
Nearby Local LLM projects in the catalogue, closest in stars to Orkas — keep exploring the shelf either side of it.
- node-llama-cpp★ 2.2k
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
- agent-safehouse★ 2.1k
Sandbox for local AI agents so they only touch what they need.
- claude-real-video★ 2.2k
Let any LLM actually watch a video — frames plus transcript, run locally.
- meridian★ 2.1k
Local API bridge to run Claude and Antigravity inside other coding clients.
- kalosm★ 2.2k
Run controllable pre-trained AI models locally, written in Rust.
- Step-3.5-Flash★ 2.1k
StepFun's open 196B MoE model that activates 11B parameters per token, built for fast agentic reasoning.
Get Orkas
Free and open — grab the source, star the repo, and start creating.