Privacy and advertising choices

Git-Stars uses essential storage for site operation. Optional analytics and ad-measurement scripts stay disabled unless you accept them; partners such as Google may then use cookies or similar identifiers where required. Privacy Policy

LogoGit-Stars
  • Top Stars
  • Trending
  • AI Agent
  • Daily Picks
  • Insights
  • Methodology
LogoGit-Stars

Discover top GitHub projects with real rankings and AI insights

GitHub
Built withLogo of Git-StarsGit-Stars
Rankings
  • Top Stars
  • Trending
  • AI Agents
  • Daily Picks
  • Explore
Resources
  • Insights
  • Methodology
  • Editorial Policy
About
  • About
  • Contact
Legal
  • Privacy Policy
  • Terms of Service
© 2026 Git-Stars. All Rights Reserved.
CA

cactus-compute/needle

AI Agent

26m agentic model for tiny devices

3.2k Stars245 Forks25 Open Issues3.2k WatchersPythonMIT
AI AgentLLM Tool
Source and compliance noteLast synced: Jul 21, 2026

Git-Stars is independent and not affiliated with GitHub or this project. Analysis may be AI-assisted and based on public repository metadata plus short README-derived summaries. We do not mirror full README files, docs, issues, or social comments.

Original GitHub sourceMethodologyEditorial Policy
Editorial Evaluation

cactus-compute/needle is tracked as a Python project in the AI Agent, LLM Tool area. This evaluation combines public GitHub metadata, category signals, short source summaries, and Git-Stars editorial rules rather than copying project documentation.

Momentum check: the repository has 3.2k total stars, with +0 today, +219 this week, and +0 this month. These growth windows help distinguish durable adoption from short-lived visibility spikes.

Maintenance check: current activity is Active; the latest push was 1 days ago, and the open issue queue is 25, about 0.77% of total stars. Treat this as an adoption signal, not a substitute for engineering due diligence.

Adoption check: 245 forks and 3.2k watchers suggest how often the project is reused or followed. License signal: MIT. Always verify license compatibility before commercial or internal use.

Practical fit: this project is most relevant when you need AI prototypes, LLM workflows, and agent-style applications. Be cautious when you need a legal review, security audit, or production SLA.

Source check: Git-Stars currently has 2 explicit source reference(s) for this report and a recent growth signal of 219. Follow the original GitHub repository for final install, security, and release information.

Best For
  • AI prototypes, LLM workflows, and agent-style applications
  • Python teams evaluating ecosystem-native tooling
  • use cases where recent maintenance matters
Avoid When
  • you need a legal review, security audit, or production SLA
Adoption Signals

Momentum

3.2k Stars

Reuse

245 Forks

Attention

3.2k Watchers

Maintenance

active

License

MIT

Open issues

25

Overview

Needle is a 26m parameter Simple Attention Network distilled from Gemini 3.1, designed for efficient single-shot function calling on consumer devices. It runs at high speed on Cactus infrastructure and can be finetuned locally on a Mac or PC.

Key Features

- Distilled from Gemini 3.1 into a 26m parameter model with 6000 toks/sec prefill and 1200 decode speed. - Fully open weights and dataset generation, with easy finetuning via web UI or CLI. - Outperforms larger models (FunctionGemma-270m, Qwen-0.6B) on single-shot function call tasks.

Tool Positioning

AI Agent

Agent frameworks, autonomous workflows, and tool-use systems

LLM Tool

Libraries and tools for LLM apps, RAG, prompts, and evals

Quick Start
git clone https://github.com/cactus-compute/needle.git && cd needle && source ./setup
View on GitHub Project Homepage
Project Activity

83

Health Score

Active

Commit Activity

Feb 24, 2026

Created

Jul 20, 2026

Last push

Source Trail

GitHub repository metadata

metadata

GitHub README

readme_summary

Star History

+0

Today's growth

+0

7-day growth

+0

30-day growth

Jul 21, 2026Jul 21, 2026
Community Health
245

Forks

25

Open

3.2k

Watchers

Owner
CA

cactus-compute

GitHub profile
Topics & Language
Pythoncactusgeminigemmallmon-device-ai
Ecosystem & Usage
GitHub Repository Project Website
Alternatives & Comparison

codecrafters-io/build-your-own-x

Master programming by recreating your favorite technologies from scratch.

529k

sindresorhus/awesome

😎 Awesome lists about all kinds of interesting topics

487k

freeCodeCamp/freeCodeCamp

freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

452k

public-apis/public-apis

A collective list of free APIs

452k

EbookFoundation/free-programming-books

:books: Freely available programming books

393k
License
MIT
CreatedFeb 24, 2026
Last pushJul 20, 2026
Last syncedJul 21, 2026
Community Standards

✓

License

✓

Forked

✓ Active

Maintained

AI AnalysisAnalyzed by Git-Stars

Problem Solved

Needle solves the problem of running capable AI agents on resource-constrained devices without cloud dependency, offering a tiny model that outperforms larger ones (e.g., FunctionGemma-270m, Qwen-0.6B) on single-shot function calling. It enables local finetuning on consumer hardware, reducing latency and privacy concerns compared to cloud-based solutions.

Capabilities

Developers can build personal AI assistants that execute function calls (e.g., weather queries, tool invocations) directly on-device with low latency. Real-world use cases include smart glasses that fetch information hands-free, smartwatches that control IoT devices, and mobile apps that process user commands offline. The ceiling includes complex multi-step agentic workflows, though the model is optimized for single-shot tasks and may struggle with conversational depth.

Bottom Line

Needle is ideal for developers building lightweight, on-device AI agents for single-shot function calling, especially in privacy-sensitive or low-latency applications. It should be avoided for tasks requiring deep conversational understanding or broad general knowledge. The key trade-off is extreme efficiency and specialization at the cost of versatility and scope.

Full AI Analysis