1. Conduid
  2. RAG
  3. Inferna
MCP server · RAG

Inferna

by · github.com/shakfu/inferna

An experimental nanobind wrapper around llama.cpp, whisper.cpp, and stable-diffusion.cpp

Unclaimed agentsinferencellama-cppmcpnanobindragstable-diffusion-cppwhisper-cpp
InstallView source
34Low

Scored a month ago · breakdown

About Inferna

Inferna is an MCP server published by shakfu in the RAG category: an experimental nanobind wrapper around llama.cpp, whisper.cpp, and stable-diffusion.cpp.

The repository has 2 stars and 0 forks, with the last commit 10 days ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/shakfu/inferna

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Inferna

Powered by Claude · Grounded in docs

I know everything about Inferna. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

0.6.1inferna 0.6.1 · 7 Oct 2026Changes since the last Release Added Decision models (`inferna.llama.decision`)** answer llama.cpp's `/v1/systemone` requests in-process: typed `choice`, `score` and `noul` questions, each scored in one forward pass.…
0.6.0inferna 0.6.0 · 1 Oct 2026Changes since the last Release Changed `EmbeddedServer` uses cpp-httplib (MIT) instead of Mongoose (GPL-2.0-only or commercial).** The wheel declared MIT but linked GPL code. cpp-httplib is staged from llama.cpp's `vendor/` tree by…
0.5.1inferna 0.5.1 · 27 Sep 2026Changes since the last Release Added `LlamaModel.from_fileobj()`, `LlamaModel.lora_adapter_init_from_fileobj()` and `GGUFContext.from_fileobj()`** load from an open binary file or int fd, optionally at a byte offset, so a GGUF can ship…
0.5.0inferna 0.5.0 · 23 Sep 2026Changes since the last Release Added `SDContextParams.auto_fit`, `.disable_segmented_compute`, `.disable_prefetch`, `.linear_scale`, `.attn_scale` and `.tokenizer`, plus the matching `--auto-fit`, `--disable-segmented-compute`,…
0.4.0inferna 0.4.0 · 21 Sep 2026Changes since the last Release Added `scripts/rwt.py` checks the images the sd cases write** -- exit 0 from `inferna.sd` only meant a file was written, so a NaN render (all black) passed. A case now also fails if its PNG is the wrong size…
Questions

About Inferna

How do I install Inferna?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Inferna safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Inferna still maintained?

Yes — the latest release is 0.6.1 (7 Oct 2026), and the last commit was 10 days ago. The repository has 2 stars.