Self-hosted AI had a big week: a private workspace, a memory layer, and a local ChatGPT clone
Four tools caught my eye this week, and they all point the same direction: stop renting your AI assistant from a cloud vendor and run it on your own hardware. The privacy pitch is finally backed by tooling that doesn't take a PhD to set up. odysseus is the one everyone's talking about. It's a self-hosted AI workspace that bundles chat, autonomous agents, email triage, and research into one app, and it can serve open models directly. The clever part is the Cookbook: it looks at your actual hardware and recommends models you can really run, then wires them up for you. It launched to a massive audience overnight, so expect rough edges. And read the security note first. The project itself tells you to treat it like an admin console and never put it on a public IP. The other three fill in the stack. supermemory gives your agent a long-term memory that survives across conversations. Open WebUI is a polished ChatGPT-style interface for whatever models you're running locally. DeepSeek-GUI puts a real review step in front of an AI coding agent, so you see the diffs before anything changes. The common thread: you own your data, and you pay for it in hardware and setup time instead of a monthly bill. Whether that trade is worth it comes down to what you've got sitting under your desk.
Self-hosted AI workspace.
The Lens
Odysseus is a self-hosted AI workspace that runs on your own hardware. The pitch is privacy: instead of sending every chat, document, and email to a cloud assistant, you run the whole thing locally and keep your data on your machine. It bundles chat, autonomous agents, tool use, email triage, and research into one app, and it can serve open models directly so you are not dependent on anyone's API. The clever part is the Cookbook. It looks at your hardware and recommends models you can actually run, then serves them for you across vLLM, llama.cpp, or Ollama with far less manual wiring than usual. It supports MCP servers too, so you can connect it to other tools. The flip side is obvious: local models need local compute. Without a capable GPU or a lot of RAM you are limited to smaller models, and you bring your own keys to call hosted ones. It is MIT and free. For a privacy-minded solo developer with decent hardware, this is a genuinely exciting way to get a private alternative to a ChatGPT or Claude subscription. Small teams can experiment, but treat it as early. It is a very young, fast-moving project that launched to a huge audience overnight, so expect rough edges and frequent changes. The catch is security, and the project says so itself. The documentation warns you to treat Odysseus like an admin console and never expose it directly to the internet. It is powerful, it touches your email and your files, and it is brand new. Run it locked down, not on a public IP.
Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.
The Lens
Supermemory is a memory and context engine for AI apps. It extracts facts from conversations and documents, keeps a profile of each user, and runs hybrid search that blends RAG with personalized recall, all behind one API. The company reports top scores on the major memory benchmarks. The main repository is MIT, and plugins exist for Claude Code, Cursor and Codex.
Running it locally is one command, npx supermemory local, which starts a single binary with the same API as the hosted platform. It works fully offline with a local model through Ollama, and your data stays on your machine. The local server is single-user and licensed for up to 10,000 documents, though, and the connectors for Google Drive, Gmail, Notion and OneDrive, plus the Supermemory MCP, only exist on the hosted platform.
Hosted pricing is published and credit-based. Free includes $5 of credits a month and pauses when they run out. Pro is $19/mo with pay-as-you-go top-ups, Max is $100/mo, and Scale at $399/mo adds S3 and web crawler connectors, unlimited seats and a self-hosted option. Teams building production memory will land on Pro or Scale.
The catch is maturity. The local server is still version 0.0.x, and one August release was an emergency patch after an upgrade silently wiped search vectors. The consumer app and browser extension were retired in September too. Build on the API, pin versions, and back up your data.
AI agent workspace for DeepSeek models, with Code and Claw modes built into your application.
The Lens
DeepSeek-GUI wraps DeepSeek's AI coding agent in a desktop workspace instead of a terminal. You point it at a real project and it edits files, shows you the diffs, and waits for your approval before changing anything, with permission levels from read-only to full access. MIT-licensed and free to install. It's for people who want DeepSeek working on actual code with a review step, not just a chat window. It ships three modes. Code mode is the project workspace with file monitoring and task cards for jobs like debugging. Write mode is a Markdown editor with inline AI and export to HTML, PDF, or DOC. Claw mode runs background automation, hooking into Lark/Feishu, webhooks, and scheduled tasks. It also manages MCP servers and skills. Prebuilt installers cover macOS and Windows; Linux builds from source and needs Node 20 or newer. The app is free, but it's a front end, not a model. You bring your own DeepSeek API key, and that usage costs money, though DeepSeek's pricing sits among the lowest of the major providers. Solo developers already using DeepSeek who want a GUI with approval controls: worth a look. Teams get visibility into what the agent changed before it lands. The catch is that this is one developer's project tied to one model provider. You're betting on both the maintainer keeping pace and DeepSeek's API staying available and cheap. If you want a model-agnostic agent workspace, look at cmux or the broader AI coding tools that aren't locked to a single provider. Outside the DeepSeek ecosystem, this does nothing for you.
Self-hosted AI interface for LLMs
The Lens
Open WebUI gives you a ChatGPT-style interface for your own models, whether they run locally through Ollama, through OpenAI's API, or any compatible endpoint. Chat with models, upload documents for RAG (retrieval-augmented generation, meaning the AI reads your files and answers questions about them), manage conversations, and share prompts. All of it on your own server. The polish is the surprise. It feels like a commercial product rather than a weekend project: multi-user accounts, conversation history, model management, function calling, web search integration, and image generation. It is the most feature-complete self-hosted LLM front end available, and standing it up is a Docker command plus whatever inference backend you point it at. There is no first-party cloud, by design; the pitch is that you run it, on-premise, private cloud, or air-gapped. Standard internal use is free, with the branding left exactly as shipped. Solo and small teams: run it, there is no catch at your size. The catch shows up at scale, and it is mostly about whose name is on the screen. The license is not open source. It is BSD-3 plus a branding clause: you may not remove, alter, or replace the Open WebUI name and logo once a deployment passes fifty end users in a rolling thirty-day window, unless you buy an enterprise license or get written permission. A few enterprise-exclusive capabilities sit behind that same license too, so "everything is free" is not quite right. Read the license before building a business on top of it. The other cost is hardware, since a 7B model wants 8GB of RAM or a decent GPU and Open WebUI itself is the light part.
Get the next issue in your inbox
Free. No spam. Unsubscribe anytime.