Updates while it runs
An orchid opens new flowers while it keeps growing. Nodecode makes its updates on the fly and the program evolves naturally.
It becomes yours and evolves over time.
$ curl -fsSL https://nodecode.ai/install.sh | shnodecode
An orchid opens new flowers while it keeps growing. Nodecode makes its updates on the fly and the program evolves naturally.
A cell is like a folder that teaches Nodecode something new: a provider login, a tool, a skill, a GitHub repo, a MCP server, you name it.
Like an organism, Nodecode decides what stays in its context and what goes, and nothing it lets go is lost. The idea behind Context Language Models (Shao et al., 2026).
Lisp evolves its own language: code is data, so a program can rewrite itself while it runs. Nodecode redefines itself naturally.
A cell is a folder that teaches Nodecode something new: a chat room it can live in, a provider login, a tool, a skill, a GitHub repo, you name it.
1(nle:define-cell weather2 (:section ("weather")3 ("units" :choice4 :options '("c" "f"))5 ("cities" :list))6 (:tool "weather" +schema+ 'look-up)7 (:command "weather" 'run-slash)8 (:hook :frame #'observe))
One form declares a cell: its settings, tools, commands and hooks.
nodecode addAdd a cell.
Upload your own cell. Anyone can use it.
Cyber v1
$0.45/1M inputexcluding taxes
$1.80 per 1M output
$0.009 per 1M cached input
Decide v1
$0.10/1M inputexcluding taxes
Output free
Image v1
$0.04/imageexcluding taxes
Per image made
Protecting our customers
0
prompts or answers kept, fully private.
One API
OpenAI-compatible. Point any client at api.nodecode.ai/v1 with your key.
Prices per 1M tokens, the same at every hourYour balance pays for the tokens you use. Nothing renews.
66% fewer tokens: 58M against 172M, in 2,822 against 2,298 model calls. 24% less in costs: $33 against $43 at public list prices. The same model, GPT-6.1 Sol, on the same 25 games, each game's best run. Codex scores a little higher, 99.9 to 99.5, with fewer actions per level. Codex had more than one run at 8 games and Nodecode at 3, and 20 of Codex's games ran under a 1,000-action cap, every other game under 1,500. than Codex on GPT-6.1 Sol, on novel interactive reasoning tasks such as ARC-AGI-3.