Coding Tools
Open Source AI Software Factory Automates Coding Agents
Cole Medinhigh confidence
Why it matters
- →Provides an open-source blueprint for autonomous end-to-end software development.
- →Demonstrates how to orchestrate coding agents with minimal human intervention.
- →Shows practical token optimization strategies for long-running AI tasks.
Developer Cole Medin has released an open-source project called the AI Software Factory, designed to automate the creation of software using large language models. The system allows a coding agent to provision a virtual private server, configure the environment, and install necessary tools via a single prompt. Once deployed, the factory accepts product requirements or issues and autonomously generates, validates, and ships code. While it leverages GPT-6 Astra for strategic decision-making, the architecture is designed to minimize token usage by delegating routine tasks. The project demonstrates a practical implementation of agentic coding workflows that operate continuously.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Together AI's Inference Engine Outperforms Competitors
Together AI Blog · May 19, 2026 · Related
- 2AI Agents Revolutionize Coding with Claude Code
WIRED AI · May 26, 2026 · Related
- 3Benchmarking Open Models for Agentic Use
Hugging Face Blog · June 18, 2026 · Related
- 4Agentic AI Loops: The Next Big Step?
TechCrunch AI · June 22, 2026 · Related
- 5Cole Medin's MIT-licensed Claude Code skills
Cole Medin · August 13, 2026 · Related
- 6Cole Medin's AI Dark Factory: Autonomous Coding Workflow
Cole Medin · August 14, 2026 · Same story
- 7Warp Introduces Warp Factories for AI Development
TechCrunch AI · August 18, 2026 · Related
- 8OpenAI's Coding Agents Boost Research Speed
OpenAI · September 6, 2026 · Related
What happened next
- 9OpenAI launches Dots agentic assistant
The Verge AI · September 29, 2026 · Related
- 10OpenAPPA tackles agent prompt injection
Fireship · September 30, 2026 · Related
- 11Together Link bridges open models to coding agents
Together AI Blog · October 5, 2026 · Related
- 12ML-Intern: Autonomous AI Agent for Model Training
Hugging Face Blog · October 8, 2026 · Related
- 13GitHub Agentic Autofix for Code Scanning GA
GitHub Changelog · October 15, 2026 · Related
Follow this story
Open the full story →AI Software Factory: Open Source Alpha Released
2 developments
- Sep 3 · Cole Medin
AI Software Factory: Open Source Alpha Released - Sep 12 · Cole Medin
Open Source AI Software Factory Automates Coding Agents (This article)↳ Cole Medin’s tool automates coding agents into a self-contained pipeline using GPT-6 Astra for orchestration and token-saving offloading.
More from Cole Medin
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
llama.cpp Releases