Geekgineer / needle-rs
600 KB WASM runtime for Cactus Compute's Needle AI tool-calling models, Needle 3, 2 and 1 from one build. Browser, Cloudflare Workers, Node.js, Python, C FFI and no_std. Token-exact with the JAX reference. No backend, no API key.
Why this job: topics: inference-engine, quantization, on-device-ai, edge-ai
What it does
A pure-Rust + WebAssembly runtime for Needle by Cactus Compute — small transformers that map (query, tool list) to a JSON function call. Deploys to browsers, edge workers, CLIs, Python, and no_std embedded targets. No server, no API key, no data leaving the device.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 52 days ago
- Stars
- 107
- On GitHub
- Licence
- Custom
- Read before business use
- Downloads for
- 3 systems
- Mac, Windows, Linux
- Latest version
- v0.3.1
- Released 52 days ago
- Built with
- Rust
- 82% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 0% closed
- 3 still open
- Pull requests
- 4 merged
- 0 waiting
- Releases
- 5
- 5 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| ngxson / wllama | 1,380 | 2 days ago | MIT | No downloads |
| InferMatrixLab / vllm-rlt | 221 | 4 days ago | Apache-2.0 | No downloads |
| Scottcjn / legend-of-elya-n64 | 142 | 2 months ago | MIT | No downloads |
More: download files, languages, topics and project record
Download files, v0.3.1
- Mac6 files, 25 downloads
- Windows3 files, 24 downloads
- Linux6 files, 32 downloads
Languages
- Rust 82%
- Python 15%
- JavaScript 2%
- C 2%
Topics
- agent
- ai
- browser-ai
- cloudflare-workers
- edge-ai
- embedded-ai
- function-calling
- inference-engine
- int4
- llm
- no-std
- on-device-ai
Project record
- JobLocal LLMs
- StatusListed
- Commits121
- Forks12
- Watching2
- Stars in 28 days+2
- CreatedMay 17, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026