Source: https://seerepo.com/compare/mudler/LocalAI/vs/xorbitsai/inference
Markdown source: https://seerepo.com/compare/mudler/LocalAI/vs/xorbitsai/inference.md
Description: LocalAI and inference share 36 technologies: React, pyarrow, Hugging Face, OpenAI, anyio, FastAPI, Lightning, uvicorn, matplotlib, accelerate, bitsandbytes, conformer, einops, ModelScope, sentencepiece, tiktoken, torchvision, vector-quantize-pytorch, torch, transformers, diffusers, torchaudio, librosa, onnxruntime, funasr, kokoro, optimum, peft, safetensors, sentence-transformers, torchcodec, pillow, imageio-ffmpeg, loguru, OpenTelemetry, and highlight.js. LocalAI is written in Go and inference in Python.

# LocalAI vs inference

LocalAI and inference share 36 technologies: React, pyarrow, Hugging Face, OpenAI, anyio, FastAPI, Lightning, uvicorn, matplotlib, accelerate, bitsandbytes, conformer, einops, ModelScope, sentencepiece, tiktoken, torchvision, vector-quantize-pytorch, torch, transformers, diffusers, torchaudio, librosa, onnxruntime, funasr, kokoro, optimum, peft, safetensors, sentence-transformers, torchcodec, pillow, imageio-ffmpeg, loguru, OpenTelemetry, and highlight.js. LocalAI is written in Go and inference in Python.

- [mudler/LocalAI](https://seerepo.com/r/mudler/LocalAI): LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
- [xorbitsai/inference](https://seerepo.com/r/xorbitsai/inference): Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.

## What they share and what sets them apart

- In common: React, pyarrow, Hugging Face, OpenAI, anyio, FastAPI, Lightning, uvicorn, matplotlib, accelerate, bitsandbytes, conformer, einops, ModelScope, sentencepiece, tiktoken, torchvision, vector-quantize-pytorch, torch, transformers, diffusers, torchaudio, librosa, onnxruntime, funasr, kokoro, optimum, peft, safetensors, sentence-transformers, torchcodec, pillow, imageio-ffmpeg, loguru, OpenTelemetry, highlight.js
- Only in LocalAI: net/http, Echo, go-sqlite3, modernc.org/sqlite, s3, SQLite, NATS.io, Postgres, github.com/glebarez/sqlite, github.com/valkey-io/valkey-go, MCP, Qdrant, Tokio, react-router-dom, Vite, Hono, Gradio, fyne.io/fyne/v2, github.com/schollz/progressbar/v3, gorm.io/gorm, github.com/nats-io/jwt/v2, github.com/emersion/go-sasl, golang.org/x/oauth2, github.com/aws/aws-sdk-go-v2/credentials, github.com/coreos/go-oidc/v3, github.com/timbutler/zxcvbn, coqui-tts, flash-attn, go-openai, llama-cpp-python, llvmlite, Model Context Protocol, nemo-toolkit, neucodec, NVIDIA, oneccl-bind-pt, ONNX, onnxruntime-gpu, openai-go, phonemizer, rfdetr, s3tokenizer, scikit-image, spacy-pkuseg, texterrors, torchao, torchtune, github.com/gpustack/gguf-parser-go, github.com/mudler/nib, github.com/mudler/cogito, mlx, github.com/mudler/localrecall, opencv-python, insightface, mlx-lm, vLLM, github.com/yalue/onnxruntime_go, QWen, sglang, compel, datasets, faster-qwen3-tts, faster-whisper, github.com/go-skynet/go-llama.cpp, github.com/mudler/go-piper, github.com/streamer45/silero-vad-go, inference, mlx-audio, moonshine-voice, optimum-quanto, outetts, pocket-tts, rerankers, speechbrain, tinygrad, tokenizers, trl, voxcpm, whisperx, av, markupsafe, sox, github.com/go-audio/wav, github.com/pdfcpu/pdfcpu, github.com/emersion/go-imap/v2, github.com/yuin/goldmark, golang.org/x/image, github.com/charmbracelet/glamour, github.com/dhowden/tag, github.com/emersion/go-smtp, github.com/go-pdf/fpdf, github.com/klippa-app/go-pdfium, imageio, jinja2, github.com/google/jsonschema-go, github.com/mudler/xlog, github.com/mudler/go-processmanager, containerd, Docker, tracing, github.com/aws/aws-sdk-go-v2, github.com/aws/aws-sdk-go-v2/config, github.com/ipfs/go-log, github.com/Microsoft/hcsshim, go.opentelemetry.io/otel/exporters/prometheus, Prometheus, tracing-subscriber, fontsource-variable, CodeMirror, @lezer/highlight, yaml, dompurify, marked
- Only in inference: AIOHTTP, Next.js, python-jose, bcrypt, descript-audiotools, en-core-web-sm, misaki, opencv-contrib-python-headless, pynini, transformers-stream-generator, wetextprocessing, timm, x-transformers, qwen-vl-utils, julius, loralib, pyworld, flagembedding, gruut, silero-vad, torchdiffeq, vocos, controlnet-aux, fugashi, g2p-en, gguf, langdetect, tensorizer, eva-decord, Pydantic, jsonschema, opentelemetry-instrumentation-httpx, psutil, boto3, opentelemetry-exporter-otlp-proto-grpc, opentelemetry-instrumentation-fastapi, Tailwind CSS, next-themes, class-variance-authority, tailwind-merge, sonner, Radix UI, Lucide, react-icons, Nunjucks, react-markdown, rehype-katex, rehype-raw, rehype-sanitize, remark-gfm, remark-math

## Side by side

| | LocalAI | inference |
|---|---|---|
| Size | 1,553,487 lines written, 3,372 code files | 922,374 lines written, 2,727 code files |
| Who writes it | 6% of its commits signed by AI. With Claude Code, GitHub Copilot, and Cursor | 0.3% of its commits signed by AI. With Gemini CLI, Claude Code, and Cursor |
| Activity | Last push November 13, 2026, 9,855 commits, 50,345 stars | Last push November 14, 2026, 2,791 commits, 9,655 stars |
| Tests | 3,400 test files. 62.5% of its code files have a test that imports them | 676 test files. 19.9% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, LocalAI or inference?

LocalAI, with 1,553,487 lines written; inference has 922,374.

The proof: [mudler/LocalAI's code at commit affff71](https://github.com/mudler/LocalAI/tree/affff715ba90b1975b0540e049f332fc77b4f2c0)

### Which has more GitHub stars, LocalAI or inference?

LocalAI, with 50,345 stars; inference has 9,655.

The proof: [mudler/LocalAI on GitHub](https://github.com/mudler/LocalAI)

### Which has more tests, LocalAI or inference?

LocalAI, with 3,400 test files; inference has 676.

The proof: [mudler/LocalAI's code at commit affff71](https://github.com/mudler/LocalAI/tree/affff715ba90b1975b0540e049f332fc77b4f2c0)

### Which was updated more recently, LocalAI or inference?

inference: its last push was on November 14, 2026, and LocalAI's on November 13, 2026.

The proof: [xorbitsai/inference's commits on GitHub](https://github.com/xorbitsai/inference/commits)

### Which has more commits signed by AI, LocalAI or inference?

LocalAI: an AI signed 6% of its commits, with Claude Code, GitHub Copilot, and Cursor; in inference, 0.3%.

The proof: [the commits each tool signed in mudler/LocalAI](https://seerepo.com/r/mudler/LocalAI/ai)

## Sources

- mudler/LocalAI: Read on November 13, 2026, at commit affff71 (https://github.com/mudler/LocalAI/tree/affff715ba90b1975b0540e049f332fc77b4f2c0)
- xorbitsai/inference: Read on November 14, 2026, at commit d2607af (https://github.com/xorbitsai/inference/tree/d2607afa6e252c8e69ee785e5be5d33216745186)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.