Not another chatbot

What makes Chalie different.

Memory

Chatbots reset every session.
Chalie remembers everything.

Every conversation with other AI starts from zero. Chalie builds a persistent picture of who you are — your preferences, history, and important details — across every session.

Freedom

Assistants lock you in.
Chalie lets you choose.

Other assistants tie you to a single AI company. Chalie works with any provider — local or cloud. Switch models without losing your history.

Privacy

Cloud AI owns your data.
Chalie runs on your machine.

Your conversations, memories, and personal context never leave your device. No cloud database. No training on your data. Full sovereignty.

Reasoning

Automation is brittle.
Chalie reasons.

Automation tools move data between apps. Chalie understands what you want, loads relevant context, reasons about the best approach, and takes action — with your approval.

Why it matters

AI today is stateless. Chalie isn't.

Every conversation you have with cloud AI starts from scratch.

Cloud AI

×

Resets every session

No memory between conversations

×

Stored on their servers

Your data trains their models

×

Locked to one vendor

Switch and lose everything

×

Only when you ask

No proactive assistance

×

Monthly subscription

$20/month per service

×

Closed source

Trust their black box

Chalie

✓

Remembers everything

Six memory layers across timescales

✓

Stays on your machine

One SQLite file, full encryption

✓

Any model you choose

Ollama, OpenAI, Anthropic, Gemini

✓

Runs tasks autonomously

Background goals with human gating

✓

Free & open-source

Pay only for AI provider usage

✓

Apache 2.0

Read every line of code

Core Capabilities

Remember

Memory that
compounds.

Six layers of memory on different timescales — from your last message to patterns observed over months. Every session builds on the last. Important things persist. Noise fades naturally.

episodes knowledge decay consolidation

Reason

Reads your intent and picks the best approach — focused on being genuinely helpful, not just generating text.

Execute

Tools run safely on your machine. You review and approve anything consequential before Chalie acts.

See it in action

One interface. Memory that lasts.

Chalie now

Talk to Chalie...

Every model. Every conversation. One persistent memory.

Who it's for

People who refuse to start from scratch.

I have 6 projects across 3 languages. Chalie remembers the architecture decisions, the bugs I've fixed, and what I was doing last Tuesday. I just pick up where I left off.

The Developer

project context background tasks local models

I feed Chalie papers, notes, and ideas across months of work. It connects threads I'd forgotten about and surfaces relevant context — without me asking.

The Researcher

long-term memory document search goal tracking

I wanted AI without sending my life to someone else's server. Chalie runs on my machine, my data stays in one SQLite file. My memories never leave.

The Privacy-Conscious

local-first zero telemetry data sovereignty

Architecture

Six commitments, built in.

Human-gated execution

All consequential operations require explicit approval. Autonomy is graduated, not granted.

Local-first by default

Memory, configuration, and execution state live on your machine. Your data never leaves.

Your choice of AI

Swap between local and cloud providers without losing memory or context.

Zero telemetry

No analytics. No usage reporting. No external calls except to your AI provider.

Memory-native

Six memory layers on different timescales. Memory is what makes Chalie improve over time.

Composable

Extend Chalie with tool modules in any language. No SDK required.

Common Questions

Things people ask before trying Chalie.

Is my data sent anywhere?

No. Chalie runs entirely on your machine. All conversations, memories, and personal data are stored locally in a single SQLite file. The only outbound calls are to whichever AI provider you configure.

Which AI models work with Chalie?

Chalie works with Ollama (local), OpenAI, Anthropic, and Google Gemini. You can switch between them at any time without losing your history. The core reasoning loop needs frontier-class models (GPT-4o, Claude Sonnet, or equivalent), but lighter tasks can run on smaller local models.

How much does it cost?

Chalie is free and open-source (Apache 2.0). You only pay for the AI provider you choose. No subscriptions, no usage limits, no hidden fees. Run local models and your ongoing cost is zero.

Can I use it offline?

Yes — run capable local models via Ollama and Chalie works fully offline. Memory, search, voice, and all skills run on your hardware. The only feature requiring internet is web browsing.

What does Chalie actually remember?

Everything you tell it — and things it notices. Your name, preferences, past conversations, decisions, goals, and patterns. Memory works in layers: short-term fades naturally, important facts persist long-term. Designed to work like human memory, not a search engine.

What hardware do I need?

Any machine that runs Python 3.9+. macOS, Linux, or Docker. Chalie itself is lightweight — a single Python process with SQLite. You can use cloud APIs or run local models if you have the GPU hardware.

Early Alpha

You're early. Help shape what this becomes.

Chalie is in active development. The architecture is proven and everything works. Your feedback shapes what gets built next.

Shape the product

Every feature request from early users gets read. You influence the roadmap directly.

Fast-moving

We ship fast and fix fast. Expect breaking changes — that's the pace of early development.

Built in the open

Follow every decision in the build log.

Get Started Open an issue

Free forever. Apache 2.0. No account required.

AI that actually remembers you.