node-llama-cpp
by withcataiIn its repository's words: “Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level”
Facts from GitHub
- Licence
- MIT (MIT License), permissive, our reading
- Activity
- Last push 18 Nov 2026: pushed to in the last 90 days
- Latest release
- not fetched yet
- Stars
- 2.2k
- Main language
- TypeScript
- On GitHub since
- 12 Aug 2023
- Topics
- ai, bindings, catai, cmake, cmake-js, cuda, embedding, function-calling, gguf, gpu, grammar, json-schema, llama, llama-cpp, llm, metal, nodejs, prebuilt-binaries, self-hosted, vulkan
What it says it supports
- Loads
- GGUF
Each item is on our list for this tool and named in its README. A mention is not a test: check the project's documentation for your setup.
Other tools in Libraries
- transformers huggingface, 169k stars
- mlx ml-explore, 29k stars
- guidance guidance-ai, 22k stars
- candle huggingface, 21k stars
- transformers.js huggingface, 16k stars
- ggml ggml-org, 16k stars
Tool data from the GitHub API, fetched 19 Nov 2026, 15:36 UTC. Listing is not endorsement and nobody can pay to be listed. Something wrong here? Write to hello@weightsnotwalls.com.