New: Manta reads a hundred million tokens in one prompt.Join the waitlist
New: Manta

Everything you give it, it keeps.

Manta is our long-context model. It reads a hundred million tokens in one prompt, and from today a small group can use it before its public release.

Manta

A hundred million tokens in one prompt

We gave Manta every S&P 500 filing, 88 million tokens, hid 20 codes inside and asked for them back. It found 18.

18/20hidden codes found in 88 million tokens
17/20hidden codes found in 10 million tokens
43/50of 50 look-alike codes found in 10 million tokens

We are opening Manta to a small group first. Tell us what you would do with it.

New: Quark

128K context and reinforcement learning at 165M parameters

Quark is a small hybrid language model we trained from scratch for about $4,200 of compute. It reads 128K tokens, and one version learned simple agentic tasks from reinforcement learning alone, with no supervised fine-tuning stage. Four checkpoints are out under Apache-2.0, with a technical report. Compute for this work was partly sponsored by lium.io.

What we work on

Our research is about efficiency: reaching the same loss in fewer training steps, reading fewer bytes per token, and fitting more capability into the memory people already have. Every report ships with the code and the results of each run.

Products

Software you can use today

Kojo runs in the browser and PiVo Studio speaks on your own CPU. Abacus, Brewery and autocode are open source and work with the model of your choice.

Free AI chatSince October 2026

Kojo

Kojo searches the web, reads images and builds pages, games and art for you. Sign in with an Empero account to create keys for its OpenAI-compatible API.

# OpenAI-compatible base_url = "https://api.kojo.sh/v1" model = "kojo"
Kojo: free AI chat that searches, sees and builds.
Text to speechNovember 2026

PiVo Studio

Our PiVo voices, running locally. One Rust binary gives you a command line, an OpenAI-compatible speech API and a web studio, with no Python or ONNX Runtime to install. Audio starts playing after about 30 to 50 ms, and a single CPU thread generates it faster than real time.

# in a clone of github.com/empero-org/PiVo-studio cargo build --release git clone https://huggingface.co/empero-ai/PiVo-1.4M models/PiVo-1.4M ./target/release/pivo-studio studio
PiVo-1.4M16 kHz, 1,401,562 parameters
Pi
Vo

Both voices read “NASA is ready for the next mission.” These are the samples from the model card.

Coding agentOpen source

Abacus

A coding agent that works in your repository. It reads code, edits files and runs tests, and has a second model check anything risky before it runs. One Rust binary for macOS, Linux and Windows, with a desktop app that drives the same agent in a window.

curl -fsSL https://abacus.empero.org/install.sh | sh
Abacus Desktop with a conversation on the left and the changes it made on the right.

Brewery

A guided agent for fine-tuning language and image models. It helps choose a base model, prepare data and safe hyperparameters, then trains, tests and publishes the result with a model card.

GitHub

autocode

A coding agent in one file, with one tool and the standard library. It writes its own tools and may rewrite its own source.

pip install empero-autocode GitHub

More open source

All 17 repositories
How we work

We publish what we make. Weights, code and results go out with each release, most of them under Apache-2.0, and a model you download is a file on your disk that keeps working without us.

Before we say that something works, we test it against a baseline with the same data order and several seeds, and we report the results that did not hold up next to the ones that did.

And we size our models for the hardware people actually own: a single GPU, a workstation or a laptop. The main releases come with GGUF builds on the day they ship.

Updates

Releases and writing

All updates
15 Nov 2026ModelQuarkA 165M model that reads 128K tokens and learned simple agentic tasks from reinforcement learning alone. Four checkpoints, Apache-2.0, with a technical report. Compute for this work was partly sponsored by lium.io.15 Nov 2026WritingQuark: our whole training stack, end to end, for $4,200Before we scale up, we wanted proof that every part of our stack works. Quark is that proof: a 165M-parameter model with 128K context that we took from raw data through pretraining, long-context training, reinforcement learning, evaluation and release for about $4,200 of compute. One version learned simple agentic tasks from reinforcement learning alone, and all four checkpoints are out today under Apache-2.0.6 Nov 2026ModelMantaEarly access to our long-context model, which reads a hundred million tokens in one prompt. Join the waitlist.6 Nov 2026WritingManta: everything you give it, it keepsManta is our long-context model. It reads a hundred million tokens in one prompt, and when we hid 20 codes in 88 million tokens of company filings, it found 18 of them. Early access is open now.5 Nov 2026WritingPiVo Studio: local speech from one Rust binaryPiVo Studio runs our 1.4M-parameter voices without Python or ONNX Runtime: a command line, an OpenAI-compatible speech API and a web studio in one Rust binary, with first audio after about 30 to 50 ms on a single CPU thread.2 Nov 2026SoftwarePiVo StudioOne Rust binary for PiVo: a command line, an OpenAI-compatible speech API and a web studio that starts playing in about 30 to 50 ms.
Work with us

Scale this work with us

Compute partners

Long-term compute partners

We are looking for long-term compute partners to grow our research and models step by step, with a particular interest in AMD Instinct, NPUs and other cost-efficient accelerators. Paid, discounted or sponsored: we are open to whatever works for both sides.

Contribute

Build open models with us

Contributors work with the people who train our models on research, data, systems, community and the business around them, remotely and on their own schedule.