// open-weights coding agent

Your coding agent.
Your inference.
Your machine.

A Claude-Code-class agent that runs on open-weights models you control — private by default, no vendor lock-in, no wallet. The whole stack is open: your agent, your inference, your machine. One command.

curl -fsSL https://raw.githubusercontent.com/Libertai/libertai-cli/main/packaging/install.sh | sh curl -fsSL https://apt.libertai.io/install.sh | sudo bash brew install Libertai/tap/libertai cargo install libertai-cli

Read the docs See the Claude Code parity

Private by default
Open weights
No lock-in
<60s first run

~/code/payments — libertai private · open weights

$ libertai login

✓ Signed in · no wallet needed · free trial credits active

$ libertai code "add retry + backoff to the Stripe client"

∿ engine: pi_agent_rust model: qwen3.6-35b-a3b mode: plan

● read src/payments/stripe.ts

● read src/lib/http.ts

I'll wrap the client in an exponential-backoff retry (3 attempts, jittered) and surface a typed RetryError. Here's the diff:

+ for (let attempt = 0; attempt < MAX_RETRIES; attempt++) {

+ try { return await this.request(req); }

+ catch (e) { await sleep(backoff(attempt)); }

Apply changes to stripe.ts? ❯ yesnoplan

// the wedge

The only end-to-end private, open coding agent.

Cline and Aider make you bring your own key to someone else's cloud. Claude Code is proprietary and centralized. LibertAI Code is the one stack where the agent and the inference are both open, private by default, and lock-in-free — running on your machine, one command away.

Private by default

Prompts, code and context run against inference you control — not harvested to train someone else's model. Privacy isn't a setting you opt into; it's the default path.

no telemetry on your code

Open weights

Qwen, Gemma and other open-weights models — inspectable, reproducible, swappable. No black box, no silent model swaps under you mid-project.

inspect · pin · swap

No lock-in

Point the same agent at LibertAI, OpenAI, Anthropic, OpenRouter, or your own endpoint. OpenAI-compatible all the way down. Leave whenever you want — your workflow comes with you.

bring any endpoint

One command

A single static binary. Install, log in, and you're in an agent session in under a minute — no Node runtime, no Docker, no wallet, no crypto.

<60s to first run

// migration

Already know Claude Code?
You already know this.

Same muscle memory — the slash commands, the plan mode, the permission tiers, the hooks and skills. Powered by the open-source pi_agent_rust engine instead of a proprietary cloud. It's your Claude Code workflow, open, private, and lock-in-free, in one binary.

Plan / Accept-Edits / Auto permission tiers
UserPromptSubmit & tool hooks
Bundled skills (image gen, search…)
Inline approvals + slide-in diff editor

/ type a command… ⌘K

/plan plan-first mode, Shift+Tab to cycle
/review review the working diff
/pr open a PR from the session
/memory persistent project memory
/init generate project guide
/security-review audit pending changes
/model swap the active model
/compact compress the context
/resume reattach a saved session

+ 20 more · full Claude-Code-parity command set

// two ways in

No wrong door.

Use the integrated LibertAI agent, or keep the agent you already love and just swap the backend. Either way it's one login and an OpenAI-compatible endpoint — no rewiring your setup.

native

The LibertAI agent

One binary. Your agent, your inference, your machine.

$ libertai code the native LibertAI coding agent
$ libertai chat streaming REPL with history
$ libertai ask one-shot completion
$ libertai image generate & save images
$ libertai search web search, news & images

bring your own

Launch any agent on LibertAI

Pre-wired presets inject LibertAI credentials and launch the tool you already use.

Claude Code libertai claude
OpenCode libertai opencode
Aider libertai aider
Claw Code libertai claw
Hermes libertai hermes

…or point any OpenAI-compatible tool — Cline, Continue, Roo — at api.libertai.io.

// open weights

Models you can read, pin, and replace.

Every model is open-weights and OpenAI-compatible. Pin a version so it never changes under you — or set default_code_model to anything you like, including your own endpoint.

Code

Fast, tool-fluent models tuned for agentic editing.

qwen3.6-35b-a3b
qwen3.6-coder

Reason & chat

Large open-weights models for planning and deep reasoning.

qwen3.5-122b-a10b
gemma-4-31b-it

Image

Generate assets right from the CLI or an agent skill.

z-image-turbo

Your own

Already paying for a frontier API, or self-hosting?

OpenAI
Anthropic
OpenRouter
localhost:*

// coming soon

The same engine, hand-it-to-anyone GUI.

LibertAI Desktop wraps the very same agent loop in a polished three-pillar workspace — built on Tauri, private by default. The CLI for your terminal; the Desktop for everyone else on your team.

LibertAI Desktop

Code

Multi-pane agent sessions with a slide-in diff editor and inline approvals.

Agent

Long-running, plan-driven agents working across your repos and tasks.

Chat

Quick, project-aware conversations on private open-weights models.

Get the Desktop beta first.

One email when it lands. No spam, no token, unsubscribe anytime.

Under the hood, inference runs on Aleph's decentralized network — that's how we keep it private and unstoppable. But you never touch a wallet or a token to use it: sign in with email, get free trial credits, top up with a card. The decentralization is ours to operate, not your homework.

// ready in under a minute

Liberate your coding agent.

Install the binary, log in, and you're in a private agent session. One command.

View on GitHub free trial credits · no wallet · no crypto

Your coding agent. Your inference. Your machine.