Edge Ai Python Packages

mblt-model-zoo

Mobilint Model Zoo Project

litert-lm-builder

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

abstractintegratedmodule

[~] IntegratedPipeline is a standalone AI Agent Library for Non-LLM memory Augmented Agentic Framework, Specifically designed to provide Agentic capability for any Autonomous Agentic Framework locally and Coordinatively that runs efficiently on Consumer based machine to High end embedded systems, While continuously learning and runs efficiently.

litert-lm-api

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

litert-lm

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

sc-neurocore

Universal Stochastic Computing Framework for Neuromorphic Hardware — Rust SIMD engine, Python simulation, Verilog RTL, HDC/VSA, SCPN integration

litert-lm-builder-nightly

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

maixpy

Easily create AI projects with Python on edge device

taosmd

Local-first AI memory — runs offline on any machine with 8 GB+ RAM (SBC, mini PC, laptop, workstation). Zero-loss verbatim archive, knowledge graph, hybrid retrieval. Framework-agnostic, no cloud.

pytorchwildlife

Microsoft AI for Good Lab — Biodiversity research hub. Open-source AI models, edge devices, and tools for biodiversity monitoring and conservation. Your source for MegaDetector, SPARROW, PytorchWildlife, Bioacoustics, and more.

fedn

Scaleout Edge: Sovereign Edge AI orchestration and Federated Learning

pico-type

A tiny byte-level multi-head content classifier (~1.5M params, ~200KB ONNX, <6ms). Classifies code, text, markup, config, images, binary, secrets, 62 code languages, 30 text languages, 90 MIME types from raw bytes — no tokenizer needed.

emx-onnx-cgen

Deterministic ONNX-to-C compiler for embedded and safety-critical systems, generating static, auditable C code with no dynamic memory or runtime dependencies.

litert-lm-api-nightly

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

litert-lm-nightly

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

trio-retina

Model-agnostic state layer for world models — turn any detector (YOLO · VLM · DINO) into one standard, queryable stream of events + latent state. numpy-only, runs on CPU at the edge.

faceflash

Face search engine: 100% recall at 96x less memory than HNSW. Register photos, identify people from camera/video/images. AVX-512 + Rust. No GPU needed.

cuvis-ai

Cuvis.AI is an open-source, extensible framework for building modular AI pipelines that process, analyze, and deploy hyperspectral video data in real-time applications.

encoderfile

Distribute and run transformer encoders with a single file.

fedml

FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs on any GPU cloud or on-premise cluster. Built on this library, TensorOpera AI (https://TensorOpera.ai) is your generative AI platform at scale.

bithuman-mcp

Public mirror of the bitHuman SDK — pip install bithuman. Generated/published from the private bithuman-sdk-internal monorepo. [public]

ollama-herd

Local AI load balancer for Ollama fleets — auto-discovery, smart routing, OpenAI-compatible API, zero config. Perfect for Mac Minis & Studios.

hipcortex

Persistent causal memory for AI agents. 295x faster than Mem0. LangChain, LlamaIndex, AutoGen, CrewAI. Rust, zero deps.

dpdfnet

DPDFNet: causal single-channel speech enhancement that boosts DeepFilterNet2 with dual-path RNN blocks for stronger long-range temporal and cross-band modeling. Repo includes PyTorch implementation + checkpoints, ONNX & TFLite models with inference code, and a real-time demo.