Maple Harness 2.6.2 released! What's new in 2.6.2

The coding agent that doesn't stop when your account does

A terminal coding agent for GitHub Copilot's models, Claude and models on your own machine. It shows where your tokens go, and you can drive it from your phone.

curl -fsSL https://raw.githubusercontent.com/kinncj/maple-harness-dist/main/install.sh | bash
irm https://raw.githubusercontent.com/kinncj/maple-harness-dist/main/install.ps1 | iex

No account or token needed. The installer checks every file against the release's SHA256SUMS. Other ways to install, and what gets installed

One install, three parts

Start the proxy once. The agent, your phone and your other tools all talk to it.

The agent

A coding agent in your terminal

  • Asks before it writes a file or runs a command. deny rules are absolute.
  • Reads Claude Code's subagents, slash commands, skills, hooks and MCP servers from the repo, so an existing project needs no second setup.
  • Compile errors right after each edit, from the language servers you already have.
  • A live status bar: context used, tokens spent, the model and your remaining allowance. Paste or drop an image into the prompt.
Your first session →
The terminal interface in a demo session: bash tool calls that run the tests and commit a fix, the /context report, the input box and the status bar showing mode, context, model and tokens.
A demo session against a scripted model, not a real project.

The proxy

Your accounts and models in one place

  • Sign in to GitHub Copilot in the browser, or save an Anthropic API key. Keys go in your system keyring, not a config file.
  • Ollama, LM Studio, oMLX, Lemonade and Unsloth are detected and probed. Any OpenAI-compatible server works.
  • When an account runs out, requests move on to the next account or model, mid-task.
  • Speaks the OpenAI and Anthropic APIs, so Claude Code, OpenCode and other tools can use your models too.
  • A setup page at 127.0.0.1:11539, only on this machine, with an optional password: what's configured at a glance, Find a setting, and the team features only when you ask for them.
The proxy and its setup page →
The proxy's setup page in the light theme on a fresh install: its menu in two groups, Watch and Configure, with Find a setting, and Get started with the sign-in to Anthropic or GitHub Copilot and the Auto mode card. The proxy's setup page in the dark theme on a fresh install: its menu in two groups, Watch and Configure, with Find a setting, and Get started with the sign-in to Anthropic or GitHub Copilot and the Auto mode card.
The setup page on a fresh install. The address shown is an example.

Your phone

Approve and steer from your phone

  • Pair with a short code that works once, or scan a QR code. Set it up with Tailscale for a real HTTPS certificate.
  • See the exact diff before you approve a tool call. Start new sessions in folders you allowed.
  • Notifications when a session needs you, with no commands, paths or error text in them.
  • Share one session read-only: a link that lets one person watch it live, with no sending and no approvals, until the share ends.

Used from an iPhone on a home network. Other setups are not yet verified.

Control it from your phone →
The phone page showing an approval card for an edit to app.go with a diff of the changed line, and Allow, Always and Deny buttons.
The phone page's session list in the light theme, showing three sessions: one needing approval, one working and one idle.
An approval with its diff, and every shared session in one list.

Why Maple

What it does for you behind the scenes, in plain words. What's inside Maple →

  • Keeps going when an account runs out

    Add a second account or another model. When the first runs out of quota, is rate limited or is down, the task continues on the next one, with nothing for you to do.

    Fallbacks
  • Remembers your project

    Notes about your project, a map of your code, and search by meaning, so a new session doesn't start from scratch. The optional model for search by meaning runs inside the proxy, on your own machine.

    Memory and the code map
  • Long sessions, kept in check

    Requests shaped so your provider's cache can reuse them, what leaves the model's view in a long conversation kept and searchable, and a stop when the agent keeps failing at the same thing.

    Long conversations
  • See where your tokens go

    /cost and the proxy's Cache tab show the cache hit rate, tokens read and written, and AI units per request. Your usage log is yours to query.

    What /cost tells you
  • A control panel, not a config file

    The proxy's setup page: what's on at a glance, a search box for any setting, and team features only when you ask for them.

    The setup page
  • Local and on-device models

    Your own model server, or Apple's on-device model on a Mac with no network at all (macOS 26 on Apple silicon).

    Connect a model server
  • From one laptop to a whole team

    Share one proxy with people and budgets, chain proxies into hubs, and sign in with your company account. All off until you set it up.

    Share Maple with a team
  • Careful by default

    Permission rules, file tools that refuse your keys and shell history, a contained shell, and scoped, revocable device tokens.

    Security

Don't take our word for it

Costs vary from task to task and run to run. Measure your own work, and read what we measured with its limits.

Check it yourself

  • /cost in a session: what the task used, and what was read from the cache.
  • The proxy's Cache tab: the hit rate and AI units per request, for every tool that uses the proxy.
  • maple-harness bench: repeated, paired runs of your own tasks, with a spending cap.
How to check it yourself →
Measured

Against GitHub Copilot CLI, on the same model

In seven paired runs over four tasks, Maple Harness used fewer AI units than Copilot CLI in every pair: task by task, between 21% and 40% fewer, and about 27% fewer at the median.

When
27 September 2026, one day
Account
One GitHub Copilot business-seat account, used by both tools
Model
gpt-6-sol for both
Tasks
Four small coding tasks (Go tests, BDD specifications, a small web app): three run twice and one once per tool, seven paired runs in all
Counted by
GitHub's own AI-unit count for each tool's requests

Copilot CLI finished each task faster, by about 14% at the median. Both tools passed the tasks' automated checks on the same one run of seven, so this compares cost, not quality. One account, one model, one day: a real result, not a promise for your tasks.

Measured

A larger task, one run each

Both agents were given the same specification (an offline expense-tracker app with 20 named BDD scenarios), the same model (gpt-6-sol) and the same machine. Each side's figures come from its own accounting, and wall time is taken from outside the process. This is a single run: a later comparable run on another machine went the other way, so treat it as an example, not a rule, and measure your own with /cost and the proxy's Cache card.

The Copilot CLI's report gives the AI-unit total and the wall time but not the token breakdown, so only those two rows are directly comparable. Both runs produced every required document, a clean tree and passing checks.
Maple HarnessCopilot CLI
Wall time17m 16s49m 13s
AI units188.001,165.66
Input served from cache6,504.1k of 6,585.8k tokensnot reported
Turns142not reported
Files produced6557
Commits5, clean tree6, clean tree

Download and licence

Binaries for macOS, Linux and Windows are on the public releases page, with checksums.

Latest release All releases

Free for everyone to use, personal and commercial alike. You may redistribute the binaries unmodified with the licence text attached.

Closed source, all rights reserved. Maple Harness belongs to its author; the source code is not licensed for reuse. It is provided as is, without warranty, and you are responsible for how you use it, including the costs of the model providers you connect. Read the full licence; for anything else, write to kinncj@gmail.com.