Reading
Autofactory is a fully automated code workflow system inspired by the AI dark factory model It uses Temporal for persistent workflow orchestration, supports multiple AI backends such as OpenCode, Codex, and Claude, and enables end-to-end DevOps automation from Issue classification to PR auto-merge.
Section 01
Autofactory is a fully automated code workflow system inspired by the AI dark factory model. It uses Temporal for persistent workflow orchestration, supports multiple AI backends (OpenCode, Codex, Claude), and enables end-to-end DevOps automation from Issue classification to PR auto-merge. It also supports GitHub/GitLab platforms and provides REST API integration.
Section 02
The core vision of Autofactory is to introduce the "dark factory" (fully automated production without human intervention) concept into code development, aiming for end-to-end automation from Issue classification to PR verification and merge. Its tech stack prioritizes reliability and scalability: Temporal as workflow orchestration engine (ensures fault recovery), and multiple AI backends (OpenCode, Codex, Claude) for flexible choice based on needs and cost.
Section 03
Architecture: Autofactory uses a master-subagent pattern (Orchestrator for task decomposition/coordination; Subagents for specific tasks) following "Spec→Plan→Implementation↔Reviews" workflow. Temporal ensures workflow state recovery, long-task progress retention, concurrent resource sharing, and horizontal scaling. It supports pluggable AI backends with respective CLI installations:
npm install -g opencode-ainpm install -g @openai/codexnpm install -g @anthropic-ai/claude-codeCore Workflows:
Section 04
Multi-platform: Supports GitHub and GitLab. Configuration:
| Platform | Host Config | Auth Method |
|---|---|---|
| GitHub | Configurable via factory.github.host | GITHUB_TOKEN (env var) |
| GitLab | Configurable via factory.gitlab.host | GITLAB_TOKEN (env var) |
| Both support full pipeline. |
Deployment: System requirements: Node.js≥20, pnpm≥9, Docker, AI CLI tools. One-click install via install.sh (generates .env). Startup steps: edit .env→run start.sh→trigger workflow with pnpm autofactory run --repo .... State is persisted in ~/.autofactory/ (logs, workspaces, cost tracking).
Section 05
Applications:
Cost: AI backend calls incur fees; cost tracking is built-in (records LLM token usage in ~/.autofactory/costs/). Users can set workflow triggers based on budget (e.g., only specific Issue tags).
Section 06
Autofactory explores the frontier of AI-driven software development automation. It combines Temporal's reliability, multi-AI flexibility, and well-designed orchestration to demonstrate the feasibility of "AI dark factory" in code development. Currently in active development, it's suitable for teams exploring AI automation potential. As AI improves and costs decrease, such tools may become standard, freeing developers from repetitive work to focus on creative tasks like architecture design and problem-solving.
Keep going with more reads from the same topic.
Nornir MCP Server is an enterprise-level server based on the Model Context Protocol (MCP). It seamlessly integrates large language models (such as Claude) with the Nornir network automation framework, supporting natural language orchestration for multi-vendor network devices (Cisco, Arista, Juniper, etc.), and providing production-grade features like a dual-engine architecture (NAPALM + Netmiko), intelligent filtering, and a secure sandbox.
Bibliothèque Française LLM is a structured indexing and annotation project for French public domain literature designed specifically for large language models (LLMs). It integrates multiple authoritative sources such as DraCor, Common Corpus, and Wikisource, providing metadata indexing categorized by genre, author, and era, as well as in-depth annotations for dramatic texts (including characters, lines, stage directions, etc.). Its aim is to enable LLMs to efficiently read and understand classic French literary works.
Splinter is a minimalist, high-performance key-value (KV) and vector storage system enabling zero-latency inter-process communication via shared memory and atomic operations. With only 766 lines of core code, it supports millions of operations per second and 768-dimensional vector storage, offering a new architectural approach for local LLM inference and data-intensive applications.
Folkering OS is the world's first AI-native bare-metal operating system, entirely written in Rust no_std without relying on Linux, POSIX, or libc. It can generate commands from scratch, compile them into WASM, and run them in 10 seconds, achieving true self-evolution.