Tag
This article introduces how to use a $6 VPS and an AI agent to build your own Hysteria2 proxy server, replacing shared proxy services, gaining control over network egress, and details the steps, security considerations, and usage principles.
A guide on avoiding rate limits and reducing costs when using the GLM 5.2 model, covering prompt batching, caching, free model alternatives, effort levels, context window management, and self-hosting.
A thread recommending an article covering everything you need to know to run large language models locally at home and maintain ownership of your AI.
A tweet curates 10 powerful open-source GitHub repositories that serve as free alternatives to popular paid software, covering finance, AI, customer support, document signing, business intelligence, automation, and more.
A user runs GLM-5.2 locally on CPU only, demonstrating how to run a large model on a modest setup.
Recommends multiple open-source self-hosted movie/TV projects (such as Movie-Web, GoFilm, LibreTV, etc.), which users can quickly deploy via Docker, Vercel, and other methods, freeing themselves from subscription fees and resource restrictions.
A personal story about the author's journey towards AI independence, including the stack and projects built along the way.
The article compares three approaches to AI coding at home: self-hosting open source models, renting models via API services like OpenRouter, and using frontier subscriptions from OpenAI and Anthropic. It recommends a blend of frontier subscriptions for complex tasks and API-based open source models for routine work to build cost-effective AI workflows.
This tweet compares the high costs of popular paid services (Google One, 1Password, Netflix, etc.) with free self-hosted alternatives like Nextcloud, Vaultwarden, Jellyfin, and others, advocating for self-hosting as a cost-effective and privacy-respecting approach.
Introduces 6 open-source free 4K movie/TV sites that can be deployed with zero ads and zero membership, replacing paid platforms like iQiyi, Youku, etc., using tech stacks like Vue, Golang, Next.js.
A detailed technical guide on self-hosting email with a dedicated IPv4 block, covering reputation, SPF, DKIM, DMARC, and server setup using tools like Dovecot and Roundcube.
Maven is a free, open-source agent harness built for practical automation across personal and professional use cases, with native voice support, multi-step workflows, and self-hosting, inspired by but diverging from OpenClaw.
A tutorial on setting up local git remotes using bare repositories for personal projects, allowing offline-friendly push/pull workflows.
A user reports successfully running Qwen3 8B locally on an older RTX 1070 GPU, demonstrating that modern LLMs can run on decade-old hardware with decent performance.
A user breaks down the actual costs of self-hosting AI inference hardware vs renting cloud compute, concluding self-hosting is not cheaper per token but is worth it for privacy, control, and tinkering.
Multica is an open-source platform that transforms coding AI into a digital colleague that can assign tasks, track progress, and accumulate skills, supporting self-hosting and multiple AI models.
A developer created otterly, an npm package that turns the local Claude CLI into an OpenAI-compatible HTTP server, allowing applications like OpenClaw to use a Claude Code subscription instead of expensive pay-per-token API rates. The tool runs on a Raspberry Pi and shares Claude Code's rate limits.
The author migrated their blog from a 10-year-old Ubuntu 16.04 VPS to a more cost-effective FreeBSD VPS, detailing the motivation, setup, and introduction to FreeBSD Jails with Bastille.
A practitioner seeks advice on running AI agents 24/7 without high API costs, asking about local models, cloud GPUs, or hosted APIs, and wants cost-efficient setups balancing reliability and reasoning quality.
Self-hosting Hermes Agent on Hetzner VPS requires understanding where commands run from and the meaning of localhost in different contexts.