GitHub - Iito/parley: Run local AI models across every machine on your network. Zero config, zero cloud, zero data leaks. · GitHub
/" data-turbo-transient="true" />
Skip to content
Search or jump to...
Search code, repositories, users, issues, pull requests...
-->
Search
Clear
Search syntax tips
Provide feedback
--><br>We read every piece of feedback, and take your input very seriously.
Include my email address so I can be contacted
Cancel
Submit feedback
Saved searches
Use saved searches to filter your results more quickly
-->
Name
Query
To see all available qualifiers, see our documentation.
Cancel
Create saved search
Sign in
/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up
Appearance settings
Resetting focus
You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
Iito
parley
Public
Notifications<br>You must be signed in to change notification settings
Fork
Star
gh-pages
BranchesTags
Go to file
CodeOpen more actions menu
Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit
History<br>8 Commits<br>8 Commits
docs
docs
README.md
README.md
View all files
Repository files navigation
Parley
One binary that turns every machine on your network — Apple Silicon Macs, NVIDIA workstations, spare CPU boxes — into one shared, private LLM cluster. OpenAI- and Ollama-compatible, so the tools you already use just work.
→ Downloads & full docs: lmparley.com · Releases
How it works
Run parley serve on each machine. That's the whole setup — no config file.
Discovery is automatic. Nodes find each other on the LAN. New machines join the cluster the moment they start; they drop off cleanly when they stop.
Routing is automatic. A request goes to the node that already has the model warm; ties break toward the shortest queue. You don't pick the node.
Naming is by capability. Address the cluster as parley:code, parley:fast, parley:best, parley:reason, and Parley resolves to the best concrete model available across all nodes — or just use a model name from parley list.
Security is built in. Inter-node traffic is TLS-encrypted with per-machine certificates; peers are identity-pinned on first contact. No telemetry, no phone-home.
$ parley serve<br>parley serve<br>local: http://localhost<br>network: http://192.168.1.42
$ parley pull qwen3-coder:30b<br>$ parley status
APIs
Parley speaks three API families on every node, so existing code and tools point straight at it:
API<br>Endpoints<br>Connect by
OpenAI<br>POST /v1/chat/completions, GET /v1/models<br>OPENAI_BASE_URL=http:///v1
Ollama<br>/api/chat, /api/generate, /api/tags, /api/show, /api/ps<br>OLLAMA_HOST=http://
Anthropic<br>POST /v1/messages<br>base URL http://
/v1/chat/completions \<br>-H 'Content-Type: application/json' \<br>-d '{"model":"parley:code","messages":[{"role":"user","content":"hello"}]}'">curl http://node>/v1/chat/completions \<br>-H 'Content-Type: application/json' \<br>-d '{"model":"parley:code","messages":[{"role":"user","content":"hello"}]}'
Chat interfaces
Because Parley implements the OpenAI and Ollama APIs, the local-LLM ecosystem's chat front-ends work against it. In the app, set the OpenAI base URL to http:///v1 (or the Ollama host to http://) and pick a parley:* alias or any model from parley list.
The lists below are drawn from Ollama's community integrations and checked against Parley's API surface — only interfaces that actually work are listed.
Web
Open WebUI — extensible, self-hosted web UI
LibreChat — multi-provider ChatGPT-style UI
Lobe Chat — modern UI with a plugin ecosystem
NextChat — cross-platform ChatGPT UI
big-AGI — AI suite for professionals
Hollama — minimal web UI
Chatbox — desktop & web client
Chatbot UI — ChatGPT-style Ollama front-end
chat — chat web app for teams
ollama-gui — minimal Python/Tkinter client
Onyx † — connected AI workspace
Perplexica † — open-source Perplexity-style answer engine
ChatOllama † — chatbot with knowledge bases
Bionic GPT † — on-premise AI platform
Desktop
Dify — LLM app development platform
Maid — cross-platform desktop & mobile client
Witsy — AI desktop app for Mac, Windows, Linux
Cherry Studio — multi-provider desktop client
Ollama App — desktop & mobile client
PyGPT — desktop AI assistant for Linux, Windows, Mac
Alpaca — GTK4 client for Linux and macOS
SwiftChat — cross-platform (iOS, Android, macOS)
Enchanted — native macOS and iOS client
Ollama Grid Search — evaluate and compare models
macai — macOS client
AI Studio — multi-provider desktop IDE
Reins — Ollama client with parameter tuning
MindMac — AI chat client for Mac
Msty — multi-model desktop client
BoltAI — AI chat client for Mac
AnythingLLM † — all-in-one desktop AI app
† Chat works normally. These also offer built-in document-RAG / search, which needs an embeddings model — point...