self-hosted-ai

Here are 18 public repositories matching this topic...

KaiFelixBennett / hermes-claude-code-local

Run Hermes Agent + Claude Code locally on llama.cpp — zero API costs. A 4h / 7M-token session that would have cost $94 on Claude Opus 4.7

telegram-bot wsl2 autonomous-agent ai-agent llama-cpp local-llm llm-inference gguf speculative-decoding litellm private-ai self-hosted-ai claude-code agentic-coding multi-token-prediction hermes-agent qwen3-6-27b hip-rocm

Updated Jun 8, 2026
Shell

psyb0t / aigate

Sponsor

Star

A self-hosted AI platform — inference, tool use, browser automation, image generation, speech synthesis, transcription, object storage, agentic code execution, and more — behind a single OpenAI-compatible endpoint. One docker-compose up.

docker text-to-speech ai docker-compose inference image-generation browser-automation llm llmops ollama litellm ai-gateway self-hosted-ai mcp-server openai-compatible claude-code

Updated Aug 21, 2026
Shell

Jewelzufo / granitepi-4-nano

Star

Run IBM Granite 4.0 locally on Raspberry Pi 5 with Ollama.This is a privacy-first AI. Your data never leaves your device because it runs 100% locally. There are no cloud uploads and no third-party tracking.

linux open-source raspberry-pi ai ibm arm64 embedded-linux ai-project edge-ai huggingface on-device-ai llm local-ai ollama small-language-models offline-ai private-ai self-hosted-ai mamba-2

Updated Jul 20, 2026
Shell

engineering87 / sibillaos

Sponsor

Star

Linux distro with a built-in LLM. Detects your hardware, picks vLLM or Ollama, downloads a model that fits, and serves an OpenAI-compatible API from first boot.

linux ubuntu debian-packages inference self-hosted linux-distribution distro huggingface llm vllm local-ai ollama self-hosted-ai iso-builder

Updated Aug 20, 2026
Shell

smansf / juso

Star

Defense-in-depth platform for running OpenClaw agents on personal hardware

security ubuntu ubuntu-server utm security-tools ai-agents defense-in-depth self-hosted-agent ollama self-hosted-ai openclaw openclaw-security

Updated Jun 11, 2026
Shell

engineering87 / dgxspark-llm-repo

Sponsor

Star

Production-ready guide to serve multiple local LLMs (chat, embeddings, reranking) on NVIDIA DGX Spark using vLLM, an nginx TLS gateway, and systemd automation

ai large-language-models llm vllm local-llm self-hosted-ai dgx-spark nvidia-dgx-spark

Updated Jun 12, 2026
Shell

LouisDM / airgap-coder

Star

Run Codex CLI with self-hosted models in air-gapped networks via LiteLLM.

developer-tools codex air-gapped openai-codex vllm litellm offline-ai sglang self-hosted-ai responses-api

Updated Aug 25, 2026
Shell

kasimmj / local-ai-stack

Star

🐳 One-command self-hosted AI stack — Ollama + Open WebUI + Qdrant + n8n. Your private ChatGPT, fully offline.

Updated May 22, 2026
Shell

Qauttrolab / icloudpd-synology-setup

Star

Automatisches iCloud Foto/Video Backup auf Synology NAS — Multi-Account, Docker Compose, DSM Aufgabenplaner

docker photos backup docker-compose multiuser synology icloud synology-nas nas homelab self-hosted-ai icloudpd

Updated Mar 28, 2026
Shell

BiblioGalactic / Robotsdelamanecer

Star

Saga robots

macos linux bash machine-learning automation privacy command-line offline-first artificial-intelligence developer-tools dev-tools ai-workflows llama-cpp local-llm self-hosted-ai

Updated Jun 26, 2026
Shell

Fateorcloud / volans-lobehub

Star

One-command self-hosted LobeHub deploy — Docker Compose (PostgreSQL/PGVector, Redis, RustFS S3, SearXNG), optional Cloudflare Tunnel for public access.

ai docker-compose self-hosted ai-platform cloudflare-tunnel llm pgvector lobehub lobe-chat deepseek self-hosted-ai rustfs

Updated Jun 28, 2026
Shell

BiblioGalactic / volumen_memoria

Star

Scripts para ejecutar IA local con lógica de memoria personalizada.

macos linux bash machine-learning automation privacy command-line offline-first memory artificial-intelligence developer-tools dev-tools long-term-memory ai-workflows llama-cpp local-llm context-management self-hosted-ai

Updated Apr 21, 2026
Shell

BiblioGalactic / light-sculpture

Star

Inspired by the idea that programming can be a form of sculpture, each script is a tool for carving time, sound, and color.

macos linux bash automation privacy command-line offline-first artificial-intelligence developer-tools dev-tools machine-learn ai-workflows llama-cpp local-llm self-hosted-ai

Updated Apr 21, 2026
Shell

kyl3kan3 / openclaw-starter-kit

Star

One-command, self-hosted OpenClaw starter — Raspberry Pi + Ollama friendly, hardened defaults, curated skills.

raspberry-pi self-hosted ai-agent llm ollama self-hosted-ai openclaw

Updated Jul 19, 2026
Shell

k0f1 / casedesk-examples

Star

Deployment examples for open-source AI models - GPU VMs, Kubernetes, and OpenAI-compatible API

kubernetes gpu gke llama aks eks ollama deepseek self-hosted-ai openai-compatible

Updated Jun 23, 2026
Shell

tdiprima / ollama-orchestrator

Star

Bash automation for self-hosted Ollama: model management, Open WebUI Docker deployment, and API querying from the command line.

automation llm ollama open-webui self-hosted-ai

Updated May 19, 2026
Shell

BiblioGalactic / volumen_bucle

Star

self-organized looped AI examples

macos bash machine-learning automation privacy command-line offline-first job-scheduler artificial-intelligence developer-tools event-loops background-tasks dev-tools linus llama-cpp local-llm ai-workflow self-hosted-ai

Updated Apr 21, 2026
Shell

sithukyaw007 / local-ai-workload

Star

Docker-first, local-first AI workload toolkit for macOS Apple Silicon using Ollama, llama.cpp, LiteLLM, and Claude-compatible local endpoints.

Updated Apr 3, 2026
Shell

Improve this page

Add a description, image, and links to the self-hosted-ai topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the self-hosted-ai topic, visit your repo's landing page and select "manage topics."

Learn more