{"data":{"slug":"jaylfc-taos","name":"taOS","tagline":"Self-hosted AI agent OS with memory, chat, and multi-framework group chat support.","github_url":"https://github.com/jaylfc/taOS","owner":"jaylfc","repo":"taOS","owner_avatar_url":"https://avatars.githubusercontent.com/u/30096482?v=4","primary_language":"Python","stars":495,"forks":36,"topics":["agent-framework","ai-agents","ai-platform","apple-silicon","data-sovereignty","distributed-computing","kv-cache-quantization","llm","llm-inference","local-first","local-llm","offline-first","orange-pi","privacy","raspberry-pi","rockchip-npu","self-hosted","turboquant","vllm"],"archived":false,"github_pushed_at":"2026-08-25T10:49:28+00:00","maintenance_label":"Very active","stars_delta_30d":36,"url":"https://www.graphcanon.com/tools/jaylfc-taos","markdown_url":"https://www.graphcanon.com/tools/jaylfc-taos.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jaylfc-taos","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jaylfc-taos","description":"Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).","homepage_url":"https://taOS.my","license":"AGPL-3.0","open_issues":302,"watchers":6,"ai_summary":"taOS is a self-hosted operating system designed for AI agents, featuring offline AI memory, local-first functionality, full web desktop environment, and support for various hardware including Orange Pi, Raspberry Pi, and Apple Silicon. It offers auto-clustering capabilities for consumer hardware and integrates multiple AI frameworks.","readme_excerpt":"## Quick Start\n\n**Controller (server):**\n\n```bash\n\n---\n\n# Debian / Ubuntu / Fedora / Arch / Alpine / macOS, one-line install\ncurl -fsSL https://raw.githubusercontent.com/jaylfc/taOS/master/scripts/install-server.sh | sudo bash\n```\n\nRun without `sudo` to install as a user-mode systemd unit instead. The script is idempotent, safe to re-run on an existing install. Supports env-var overrides for install path, branch, and port.\n\n---\n\n# Linux / macOS, one-line worker install (auto-detects headless,\n\n---\n\n# service otherwise; works on a fresh Debian install or your existing box)\ncurl -fsSL https://raw.githubusercontent.com/jaylfc/taOS/master/scripts/install-worker.sh | sudo bash -s -- http://your-server:6969\n\n---\n\n# Windows 10/11, one-line worker install (PowerShell, mirrors the\n\n---\n\n### Agent Deployment\n5-step wizard: pick framework → choose model → configure → deploy into an isolated container (LXC on bare metal, Docker on VPS, auto-detected). Each agent gets its own memory system (taOSmd instance), its own file storage, and its own network identity. The framework runs inside the container but taOS manages everything around it: memory, channels, secrets, model access, scheduled tasks, and inter-agent communication. This means the framework is a swappable component, not a lock-in decision.\n\n> **Running taOS *inside* an LXC (e.g. Proxmox)?** Deploying an agent creates a *nested* container, which an **unprivileged** LXC cannot do -- the kernel can't remap the nested container's filesystem, so the deploy fails with an `idmapped storage / change ownership` error. Run the taOS LXC as **privileged with nesting enabled**. On Proxmox: untick *Unprivileged container* and set Options → Features → `nesting=1` (plus `keyctl=1`, `fuse=1`), then redeploy. Bare-metal and VM installs are unaffected. (taOS detects this and surfaces the fix in the deploy error.)\n\n<p align=\"center\">\n  <img src=\"docs/images/mobile-agents-empty.jpg\" alt=\"Agents app empty state on mobile -- one tap to deploy\" width=\"30%\">\n</p>\n\n<p align=\"center\"><sub>The Agents app on mobile -- one tap from empty to your first deployed agent.</sub></p>\n\n---\n\n## Supported Hardware\n\n| Category | Hardware | Notes |\n|----------|----------|-------|\n| **Apple Silicon** | Mac Mini, MacBook, Mac Studio, Mac Pro (M1-M5) | Ollama (Metal) or MLX backend, 8-192GB unified memory |\n| **ARM + Rockchip NPU** | Orange Pi 5/5 Plus, Rock 5B | 6 TOPS NPU, primary SBC target |\n| **Raspberry Pi** | Pi 4 (8GB), Pi 5 (8/16GB) | CPU-only or with accelerator HATs |\n| **Pi Accelerators** | Hailo-10H (40T), M5Stack LLM-8850 (24T) | LLM-capable accelerators |\n| **NVIDIA** | GTX 1050 Ti through RTX 4090/5090 | CUDA 4-32GB or Vulkan legacy |\n| **AMD** | RX 6600 through RX 7900 XTX | ROCm 4-24GB |\n| **Android** | Flagship phones/tablets (12-16GB) | 7-8B models at 15-30 tok/s via Termux + llama.cpp |\n| **iOS/iPadOS** | iPad Pro M4, iPhones (6-8GB+) | Dashboard via PWA, future native worker app |\n| **CPU Only** | Any device | Smallest quantized models |\n| **Mixed Cluster** | All of the above combined | A Mac, a Pi, a gaming PC, and an old phone, all working together |\n\n---\n\n## What the install creates on your box\n\nFull transparency on every file, service, user, and port the installers touch. Nothing is hidden behind a vendored binary; everything is plain Python, plain systemd, plain shell.\n\n---\n\n### Controller install (`scripts/install-server.sh`)\n\nRun `curl -fsSL https://raw.githubusercontent.com/jaylfc/taOS/master/scripts/install-server.sh | sudo bash` on a fresh Debian / Ubuntu / Fedora / Arch / Alpine box to get the controller fully installed, repo cloned to `~/tinyagentos/`, venv created, all deps installed, and both `tinyagentos.service` (port 6969) and `qmd.service` (port 7832) registered and started.\n\n| Where | What |\n|---|---|\n| `/etc/systemd/system/tinyagentos.service` | Main controller systemd unit. Runs uvicorn on port 6969. |\n| `/etc/systemd/system/qmd.service` | Embedding backend (embed / rerank / query ex","github_created_at":"2026-04-05T15:33:40+00:00","created_at":"2026-07-11T11:46:36.418665+00:00","updated_at":"2026-08-25T12:01:21.206106+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"agent-framework","name":"agent-framework"},{"slug":"ai-platform","name":"ai-platform"},{"slug":"data-sovereignty","name":"data-sovereignty"},{"slug":"distributed-computing","name":"distributed-computing"},{"slug":"llm-inference","name":"llm-inference"},{"slug":"local-first","name":"local-first"},{"slug":"offline-first","name":"offline-first"},{"slug":"privacy","name":"privacy"}],"trust":{"provenance":{"is_fork":false,"github_id":1202093119,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-25T12:01:20.370Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-08-21T17:07:35Z","stars_delta_30d":36,"open_issues_delta_30d":-6},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:46:37.649Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-25T12:01:20.831Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-25T12:01:20.831Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-25T12:01:20.831Z"},"license_spdx":{"value":"AGPL-3.0","source":"github.license","observed_at":"2026-08-25T12:01:20.831Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["You require an AI agent OS that prioritizes your hardware ownership and offline capabilities, ensuring your data remains private without needing continuous internet access.","Your environment consists of diverse hardware like Orange Pi or Raspberry Pi, where you aim to deploy auto-clustering for more efficient resource utilization."],"when_not_to_use":["You prioritize cloud-based AI services with real-time data processing over self-hosted and offline solutions.","Your infrastructure is primarily composed of enterprise-grade servers that already support advanced clustering software, making taOS's auto-clustering less beneficial."],"source":"enrich:decision_facts","observed_at":"2026-07-12T01:11:20.255Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"taOS is a self-hosted AI operating system tailored for environments requiring data sovereignty and privacy. It offers unique offline-first capabilities along with multi-framework support on consumer hardware."}]}}