Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: self-hosted
OpenAI's Managed Agents API: Hosted Sandboxes vs Self-Hosted Execution
How OpenAI's managed agent harness works in public beta: hosted Linux workspaces, self-hosted exec servers, context compaction, tool search and subagents.
8 min readTen Self-Hostable Open-Source Agent Platforms, Sorted by What a Business Actually Needs
Compare ten open-source AI agent platforms for business: enterprise no-code, Activepieces, Kestra, Windmill, Dify, Langflow, Coze Studio, MaxKB, AnythingLLM and RAGFlow.
15 min readHybrid Search for a Homelab: Qdrant RRF, BM25 and Custom Chunking
A self-hosted homelab assistant that chunks notes, spreadsheets, Draw.io diagrams and Loki logs, then retrieves with dense and sparse vectors, RRF and cross-encoder reranking.
6 min readPhlox-GW: Open-Source LLM Gateway with Budgets, Guardrails, and HA
Phlox-GW is an open-source LLM gateway you self-host: budgets and chargebacks, rate limits, PII guardrails, audit logs, OpenAI and Anthropic endpoints, HA.
11 min readSelf-hosted LLM networking: one gateway instead of a host per model
Adding open-weight models should not mean new hostnames and peering for every app. A LiteLLM-style gateway keeps one endpoint while backends change behind it.
5 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.