The economical
coding agent.

It's so lean you can use it for free!

╶──╮ ╶──┤ 3code v0.4.0 the economical coding agent ╶──╯ provider baseten model GLM-4.7 type a prompt. :help for commands. :q or Ctrl-D to exit. ❯

Never stop coding

When your subscription runs out, or you don't have one, keep vibecoding with 3code. There are many open-weight model providers, some of them free. 3code gives you a nice, familiar interface and special tuning so you can use them for coding.

Get started

Get a provider

nvidia gpt-oss free / decent

z.ai glm-5.1 excellent / affordable

More providers

Install 3code and enter your API key

# macOS / Linux
$ curl -fsSL https://3code.capocasa.dev/install | sh
# Windows (PowerShell)
> irm https://3code.capocasa.dev/install.ps1 | iex
$ mkdir myprojectdir && cd myprojectdir
$ 3code

  ╶──╮
  ╶──┤    3code v0.4.0   the economical coding agent
  ╶──╯

  no provider configured. let's add one. (ctrl+d to quit)
  supported: deepinfra, ovh, nvidia, nebius, fireworks

  api key              : ************************
  provider name or url : nvidia
  verifying... ok
  saved to ~/.config/3code/config

Run your first prompt

❯ Build me a Hello World program in Nim

Why 3code

3code, the economical coding agent is as useful as any top coding agent, but also takes special care not to burn any more tokens, computer power or brain cycles than it absolutely needs to.

How 3code pulls it off

programmed in Nim - expressive power saves tokens and tiny footprint comes for free
aggressive token caching covers all bases
simple-yet-robust algorithmic security model - no AI decisions, no interactive permissions
partial self-context-resetting plan/execution skill for larger tasks
smart defaults and the freedom to experiment

We eat our own dog food! 3code is to a large extent written in 3code. Right now we use GLM 5.1 on the z.ai coding plan.

Design: The 3E E's

E₁

Token efficiency

Can't do anything about token burn that's needed- but a lot of it isn't needed, and 3code doesn't do that.

E₂

Computer efficiency

It's a chat program. It shouldn't use a lot of power on your computer, and it doesn't.

E₃

Brain efficiency

No one wants to save tokens by having to do everything by hand, and having ones cake and eating it too is our core value- so we're clever about still achieving convenience!

Data to back it up

Binary size

disk footprint of a single install, no runtime

3code 1.6 MB

opencode ~22 MB

goose ~35 MB

claude code ~85 MB*

3code measured from release binary. opencode and goose from release artifacts. *claude code has no standalone binary; figure includes the Node.js runtime it requires.

System prompt size

tokens sent before your first word (base instructions only, tool schemas excluded)

3code ~600

opencode ~2,100

goose ~1,000†

claude code ~2,900

Benchmarks ongoing - explorative dogfooding suggests 30-50% token savings.

Technical Details

1.6 MB binarysingle executable, no runtime dependencies
cross-platformlinux x86-64/arm64 · macos universal · windows
no daemon, no web UIrun it, use it, done
low visual noisehigh information density; terse output, nothing wasted
40 known-good combosvalidated provider + model pairings, just works out of the box
loop guarddetects runaway autonomous edits, halts at configurable thresholds
session persistencehuman-readable .3log format; resume any past session
native web searchstartpage built-in, no curl dependency
context compactionsupersede-aware; later writes elide stale reads to shrink context
context clear toolwipe accumulated context mid-session to start a subtask fresh
self-clearing executionplan/execute skill resets context between phases for larger tasks
experimental modeunlock models beyond the validated set for power users
no telemetrysessions stay local, nothing phoned home
MIT licensedo whatever you want with it

The economicalcoding agent.