Skip to content

Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.

docs: document [train] install extra and telemetry opt-out in llms.txt (#99)

LeonSGP628b51e088e4
diff --git a/llms.txt b/llms.txt
index a9def39..cff97b2 100644
--- a/llms.txt
+++ b/llms.txt
@@ -7,10 +7,11 @@ This file is written for AI coding assistants. It is enough to write correct Nee
## Install
```sh
-pip install cactus-needle
+pip install cactus-needle # runtime (inference only)
+pip install "cactus-needle[train]" # adds JAX + training deps for finetune/build
```
-`import needle` is lightweight (no JAX). JAX is imported lazily and only by fine-tuning/export/build. The engine binary auto-downloads from Hugging Face on first `Needle(...)` use.
+`import needle` is lightweight (no JAX). JAX is imported lazily and only by fine-tuning/export/build, and the training dependencies live behind the `[train]` extra - a runtime-only install cannot run `needle finetune`/`build`. For GPU training use `[train,gpu]` (CUDA) or `[train,metal]` (Apple Silicon). The engine binary auto-downloads from Hugging Face on first `Needle(...)` use.
## Core API
@@ -160,6 +161,7 @@ LoRA on the frozen base, merged at export. Data is JSONL, one example per line;
```
```sh
+pip install "cactus-needle[train]" # training deps (JAX, flax, optax)
export OPENROUTER_API_KEY=sk-or-...
needle generate-data --tools my_tools.json --num-samples 500 --output data.jsonl # optional
needle finetune data.jsonl --epochs 3 --generate 300 # LoRA; auto-downloads base
@@ -211,4 +213,8 @@ Adapt by swapping the Literal values for your own and keeping the shapes: closed
- `import needle` does not import JAX; only `needle finetune`/`build` do.
- `weights=` expects a `.cact` (from `needle build`), not a `.pkl` checkpoint.
- The engine cannot unload weights: once a tuned `.cact` is bound, constructing or calling a base-model agent raises instead of silently answering with those weights. Construct agents that want the base model before any tuned one, or run them in separate processes.
+
+## Telemetry
+
+Anonymous usage counts only (function name, package version, OS, random install id - never prompts, outputs, or data). Opt out with `NEEDLE_TELEMETRY=0` or `DO_NOT_TRACK=1`; `CI` environments are excluded automatically.
```