ember

Give your agent a gut feeling.

ember helps AI coding assistants like Claude Code, Codex, and opencode know when to go ahead and when to stop and check with you.

Run it on your Mac, on a server you host, or point it at one your team already runs.

ember, a curled plum mascot hugging a glowing tummy.

The problem

Your assistant is great at writing code, and bad at knowing when to check in

Today an assistant guesses at these moments, or follows a fixed rule. Too cautious, and it interrupts you about everything. Too bold, and it charges ahead on a vague request or pushes a risky change without a word. These are the three moments that matter most:

Act or ask?

Is “update the thing” enough to start on, or does it need one clarifying question?

Retry or fix?

A red test can be a flake, a missing service, or a real bug, and each needs a different next step.

Ship or stop?

A four-line rename and a change to auth deserve different amounts of caution.

What ember does

A quick second opinion, as a number

At one of those moments, your assistant tells ember what's going on and asks a short question. ember replies with how likely each answer is, like “93% likely this needs review”. Your assistant uses that number to decide what to do next. You don't call ember yourself; your assistant does it for you.

How a call flows: the coding agent sends state and typed questions to ember on your Mac, which returns how likely each answer is, and the agent decides. Coding agent what's happening + a question ember on your Mac how likely each answer is The agent decides How a call flows: the coding agent sends state and typed questions to ember on your Mac, which returns how likely each answer is, and the agent decides. Coding agent what's happening + a question ember on your Mac how likely each answer is The agent decides

Ask

Yes or no

“Does this change need review?”

Ask

Which one?

“Why did this test fail?”

Ask

How much?

“How risky is this change, from 0 to 3?”

Where it helps

Three real examples

Each card shows what the assistant was facing, what ember said (0.96 means 96% likely), and what the assistant did as a result. These are real answers from ember.

Intent and readiness
update the thing
  • implement 0.96
  • specific_enough 0.09

Ask what to update

Failure triage
TimeoutError after 5.0s; passed on 3 of last 5 CI runs
  • flaky 0.89
  • retry 0.67

Retry, then stabilize the test

Change risk
Skip auth token validation for localhost (180 lines)
  • risk 2.43 of 3
  • needs_review 0.93

Stop and ask for review

ember also helps with routing (“which team owns this?”) and effort (“quick fix or proper redesign?”), and you can teach your assistant your own rules, like “check risk before every push”.

Measured, not promised

When ember is sure, it's almost always right

We tested ember on 538 realistic coding situations with known right answers, written down before the test so the results couldn't be nudged. Reading screenshots and clips is scored separately as a capability: 100% on 32 vision questions, on the benchmark page.

904 of 967

times ember was sure, it was right. It was sure enough to act on 68% of the yes-or-no and pick-one questions.

81%

of all 1565 questions answered correctly.

0.92 s

typical time per answer, measured on an Apple M4 Max.

It doesn't overstate how sure it is. Choice questions, grouped by how confident ember was. In every group it was right at least as often as it claimed.

claimed right

The full report shows every result, including where it gets things wrong. Read the benchmark report

Run it your way

On your Mac, or on a server

ember works the same wherever the model runs. You choose when you set it up, and it never sends anything anywhere you didn't pick.

On your Mac

The model runs on your own Apple Silicon Mac, so your code stays on it. Needs 32 GB of memory and a one-time 18 GB download.

On a server you host

Run one copy on a spare Mac or a GPU machine and share it with your whole team, protected by a token.

On a server someone else runs

Point ember at its address and you're done. Nothing to download, and your machine doesn't need to hold the model.

Fast

Answers come back in about 0.92 seconds once ember is running, and asking several questions at once costs the same as one.

Deterministic

The same request always gets the same answer, so a decision can be replayed.

Open

MIT-licensed code, no account, no per-call bill. Cloudflare's Clef weights are Apache-2.0, from their public Hugging Face repo.

Works with

Fits the agent you already use

One command connects ember to your assistant. ember also teaches your assistant when to ask it and how to read the answer, so there's nothing to configure by hand.

Get started

Up and running in five steps

You need uv. To run the model yourself, you also need an Apple Silicon Mac with 32 GB of memory or more and about 18 GiB of free disk; to use a server, you only need its address.

  1. Install ember.

    uv tool install --python 3.12 ember-advise
    

    To pin a specific release tag from GitHub instead:

    uv tool install --python 3.12 "ember-advise @ git+https://github.com/shapeandshare/ember@v0.16.0"
    
  2. Choose where it runs. To run it on your Mac, download the model. It’s about 18 GB, and an interrupted download resumes.

    ember model pull
    

    To use a server instead, skip the download: step 3 asks for its address, or you can pass it with --server-url. If the server needs a token, export EMBER_AUTH_TOKEN in the shell that starts your agent.

  3. Connect your agent. Run the line for the agent you use, then restart it. ember init asks whether to run locally or use a server.

    ember init --opencode --global                    # opencode, every project
    claude mcp add --scope user ember -- ember-mcp    # Claude Code, every project
    ember init --codex                                # Codex CLI, this project
    ember init --kilocode                             # Kilo Code, this project
    

    Claude Code doesn’t use ember init. To point it at a server, pass the address:

    claude mcp add --scope user ember -e EMBER_SERVER_URL=https://ember.example.com -e EMBER_AUTOSTART=0 -- ember-mcp
    
  4. Check the setup. ember doctor reports the platform, the model, the server, and where ember is registered for each agent.

    ember doctor
    
  5. Ask a judgment question. Try “Is this bug report urgent, and which team should own it?” The agent calls ember’s advise tool. When ember runs on your Mac, the model starts on that first call.

To make ember part of a project’s routine, add a policy your agents follow, such as “check change risk before every push”:

ember agents show snippet >> AGENTS.md    # Claude Code reads CLAUDE.md instead
ember agents install --agent claude       # the playbook skill, for Claude Code

If something looks wrong, run ember doctor, then ember logs. The Overview covers every option, including remote servers.

Try it on your next judgment call

Setup takes a few commands, on your Mac or against a server.