Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A manifesto and playbook for AI-native software engineering in the LLM era / AI-Native的软件工程宣言
| Date | Stars |
|---|---|
| 2026-07-31 | 318 |
| 2026-08-06 | 318 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# AI-Native Engineering Manifesto (English) > 中文版请见：[AI-Native 工程宣言（中文）](./readme-zh.md) > Extended deep-dive chapters live under `chapters/`, expanding several of the 11 hard truths into full articles. > 📖 **E-book**: a curated, book-style web edition lives at [liminge.space/manifesto](https://liminge.space/manifesto). [](#march-2025) [](#may-2025-revision) [](#december-2025-revision) [](#may-2026-revision) --- ## Table of Contents - [AI-Native Software Engineering](#ai-native-software-engineering) - [AI-Native Engineering: 11 Hard Truths for 2025](#ai-native-engineering-11-hard-truths-for-2025) - [Extended Chapters: AI-Native Engineering Practices](#extended-chapters-ai-native-engineering-practices) - [March 2025](#march-2025) - [May 2025 Revision](#may-2025-revision) - [December 2025 Revision](#december-2025-revision) - [May 2026 Revision](#may-2026-revision) # AI-Native Software Engineering | **Author** | [Limin Ge](https://www.linkedin.com/in/limin-ge-573b4b28a/) | | --- | --- | | **First Draft** | March 2025 | | **Revisions** | May 2025, December 2025, May 2026 | --- <a id="ai-native-engineering-11-hard-truths-for-2025"></a> ## AI-Native Engineering: 11 Hard Truths for 2025 1. If a knowledge, methodology, or tech stack is older than 3 years, it’s obsolete until proven otherwise. 2. Your codebase, your docs, your meeting notes — none of these are your backbone. Your only reliable, compounding asset is your test case library. 3. To truly understand AI, you must understand its nature: AI is completely, fundamentally stateless. 4. We can accept AI making mistakes — as long as those mistakes don’t kill the team before the next model upgrade. 5. Software complexity must flatten. We’re moving from deep, vertical stacks to wide, horizontal systems. 6. The context window is the most critical computational resource every engineer must master. 7. Plan–Act, Test–Code, and Doc–Code–Doc are the new operating system of engineering. 8. The future of code isn’t abstraction — it’s tiny, isolated, AI-readable units that stand on their own. 9. AI will never solve the first mile or the last mile. Those remain stubbornly, unavoidably human. 10. AI-generated Artifacts are not side effects. They are a new software modality — and they become part of your engineering assets. 11. The real power of AI IDEs and Agents is not generation — it's ruthless, intelligent context selection. --- <a id="extended-chapters-ai-native-engineering-practices"></a> ## Extended Chapters: AI-Native Engineering Practices The following chapters provide more systematic, engineering-focused expansions of several "hard truths" above, using original expressions from interviews and practical records, preserving first-hand insights: - [*AI Statelessness and Context Window*](chapters/01-ai-statelessness-and-context-window.md) (corresponds to truths 3, 6) - [*Test–Code Loop: Why Test Code Is More Important Than Functional Code*](chapters/02-test-code-loop.md) (corresponds to truths 2, 7) - [*Debugging: Finding Bugs with AI in Deep Waters*](chapters/03-debugging-with-ai.md) (corresponds to truths 4, 9) - [*Tools and Context Selection: Why AI IDEs Sell "Context Selection Capability"*](chapters/04-tools-and-context-selection.md) (corresponds to truths 6, 11) - [*AI-Native Workflows: Plan–Act, Test–Code, Doc–Code–Doc*](chapters/05-ai-native-workflows.md) (corresponds to truths 2, 3, 7, 9) - [*From Vertical to Horizontal Complexity*](chapters/06-horizontal-complexity.md) (corresponds to truths 5, 8) - [*Human-in-the-Loop and Onboarding*](chapters/07-human-in-the-loop-and-onboarding.md) (corresponds to truths 4, 9) - [*Choosing AI-Compatible Technology St
Excerpt of 22,072 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:6bb111d61e004a1b, llm:Repository topics and description: 'agentic-coding, ai-agents, ai-coding, ai-native, best-practices, context-engineering, developer-productivity, engineering-culture, llm, manifesto, software-engineering' and description 'A manifesto and playbook for AI-native software engineering in the LLM era'.
matched fp:6bb111d61e004a1b, llm:Repository topics and description: 'agentic-coding, ai-agents, ai-coding, ai-native, best-practices, context-engineering, developer-productivity, engineering-culture, llm, manifesto, software-engineering' and description 'A manifesto and playbook for AI-native software engineering in the LLM era'.
matched fp:6bb111d61e004a1b, llm:Repository topics and description: 'agentic-coding, ai-agents, ai-coding, ai-native, best-practices, context-engineering, developer-productivity, engineering-culture, llm, manifesto, software-engineering' and description 'A manifesto and playbook for AI-native software engineering in the LLM era'.