#local-llm (30 Repositories)

siddsachar/row-bot

Row-Bot - Personal AI Sovereignty. A local-first AI assistant with integrated tools, a personal knowledge graph, voice, vision, shell, browser automation, scheduled tasks, health tracking, and messaging channels. Run locally via Ollama or add opt-in cloud models. Your data stays on your machine.

michaelwilhelmsen/humla

Open-source AI meeting notes for Mac. Records mic + system audio with no bot, transcribes on-device or via OpenAI / Deepgram / Groq, identifies speakers offline, and writes summaries that fuse your notes with the transcript. Ask your notes and get cited answers. Tauri 2 + Rust + Swift.

axoviq-ai/synthadoc

Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.

defilantech/LLMKube

Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.

Blackwellboy/model-serving-minefield

Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quant kernel paths, CUDA toolchains, KV allocation, eval harnesses, versioning. Symptom-first, with the check that catches each.

mohitsoni48/TurboLLM

Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Claude Code at your own machine in one command. No Electron, no Python, offline-first.

raullenchai/Rapid-MLX

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

autonomous-ai/autonomous-grid

Your AI intranet: network the computers you already own for inference and training.

LearningCircuit/local-deep-research

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.

razzant/ouroboros

Ouroboros — self-creating AI agent. Born Feb 16, 2026.

mlx-node/mlx-node

leonickson1/Swiftlet

Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone.

scouzi1966/maclocal-api

'afm' command cli: macOS server and single prompt mode that exposes Apple's Foundation and MLX Models and other APIs running on your Mac through a single aggregated OpenAI-compatible API endpoint. Supports Apple Vision and single command (non-server) inference with piping as well . Now with Web Browser and local AI API aggregator

ddalcu/mlx-serve

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

tetherto/qvac

Open-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more. Cross-platform: Linux, macOS, Windows, Android, iOS.

giannisanni/pulsar

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs. Zero-config multi-GPU: measures PCIe bandwidth, places attention and hot experts where they fit.

syv-ai/qwen38-27b-rtx3090

Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks

OleksandrChekhovskyi/hax

A minimalist, terminal-native coding agent written in C.

notatestuser/ds4-control

macOS menubar app for fast local DeepSeek V4 Pro/Flash, with 1M context.

kennss/SiliconScope

Sudoless Apple Silicon system monitor (native SwiftUI GUI) with ANE / Media Engine / memory-bandwidth tracking

HKUDS/nanobot

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

orneryd/NornicDB

Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.

NightMean/OlliteRT

Turn your Android phone into an OpenAI-compatible LLM inference server — Fully local, private and Open Source

yuhp/opencode-models-discovery

A universal OpenCode plugin for dynamic model discovery with flexible configuration for OpenAI-compatible providers.

SyntheticAutonomicMind/SAM

Synthetic Autonomic Mind - An AI assistant for everyone.

jegly/OfflineLLM

Private on-device AI chat for Android — runs any GGUF model locally via llama.cpp with ARM-optimised SIMD. Zero network permissions, encrypted settings, biometric lock, tamper detection. + GPU Acceleration

endend2003-cmd/Tactical-Matrix-Console

WarMatrix 2026: Next-Gen Tactical Simulation & AI Command Console

deveix/react-native-apple-llm

React Native Apple LLM plugin using Foundation Models

Nathanw1014/strix-halo-llamacpp

Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; portable dir, Docker, and distrobox.

hogeheer499-commits/strix-halo-guide

Strix Halo guide for AMD Ryzen AI MAX+ 395 / Radeon 8060S local LLM setup and benchmarks: Ollama, llama.cpp, Vulkan/RADV, ROCm, GGUF, and raw evidence.