cactus-compute/needle

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

Open original source ↗

From the publisher

README & documentation

Source preview

Read the project’s overview, installation instructions and usage examples. The original README is the source of truth.

A foundation model for mobiles, wearables, robots, smart home, automotive and microcontrollers. The whole model is a single 8-29 MB binary built on our Simple Attention Network, and we trade general chat capacity to beat models 10x its size on mobile tool calls and match 2-3x bigger models on extraction. Needle 3 is a Laddered Simple Attention Network: a Monarch Hadamard MLP in place of the FFN, GQA attention with causal conv taps, engram n-gram memory read by gather, and multi-lane hyper-connections, trained so that every depth from 2 to 20 layers is a deployable model. Most of its parameters sit in the engram, so the 121M model does the arithmetic of a 50M one. A byte-level grammar compiled from your schemas constrains every token, and every response carries a calibrated confidence score from a learned head. The architecture diagram is on the release page. Tool calling is exact-match accuracy…

cactus-compute/needle on GitHub A short preview, not the full document.

Read the full README ↗ · Preview checked 2026-09-20T06:37:41.591Z

Inside the original README — Document outline
  1. Benchmarks
  2. Get started
  3. Guides
  4. Customisation
  5. Deploy
  6. Citation

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the README

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

What this repository does

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

Repository facts

Owner
cactus-compute
Primary language
Python
Stars
11,706
Forks
750
Open issues + pull requests
29
License
Apache-2.0
Archived
No
Default branch
main
Created
2026-02-24T04:50:47.000Z
Last push
2026-09-19T21:48:45.000Z

Topics and intended use

Owner-supplied topics: cactus, edge-ai, foundation-model, function-calling, llm, on-device-ai, tinyml, tool-calling

Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.

Evaluate before installing

Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.

README and project files

Issues and maintenance discussion

Releases and changelog

Source and freshness

Source: GitHub. Metadata observed 2026-09-20T06:35:42.692Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related repositories

public-apis/public-apis

EbookFoundation/free-programming-books

donnemartin/system-design-primer

vinta/awesome-python

practical-tutorials/project-based-learning

NousResearch/hermes-agent