BEbeepdyboop·Sep 18, 2026Submission
12-Factor Agents – Principles for building reliable LLM applications
2 points · Open discussionhumanlayer
12-factor-agents
TypeScript2025–2026
humanlayer / 12-factor-agents
12-factor-agents
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
10Distinct people
11Mentions
0Explicit recommenders
27.1KGitHub stars
What to know before exploring
What it is
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 12:54:37 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by month11 dated mentions
Observed mentions: 2025-04-11 09:24:35 UTC to 2026-09-18 13:02:24 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Apr 2025 | 2025-04-01 00:00:00 UTC | 2025-05-01 00:00:00 UTC | 3 | 2 | 1 |
| May 2025 | 2025-05-01 00:00:00 UTC | 2025-06-01 00:00:00 UTC | 1 | 0 | 1 |
| Jun 2025 | 2025-06-01 00:00:00 UTC | 2025-07-01 00:00:00 UTC | 2 | 0 | 2 |
| Jul 2025 | 2025-07-01 00:00:00 UTC | 2025-08-01 00:00:00 UTC | 0 | 0 | 0 |
| Aug 2025 | 2025-08-01 00:00:00 UTC | 2025-09-01 00:00:00 UTC | 0 | 0 | 0 |
| Sep 2025 | 2025-09-01 00:00:00 UTC | 2025-10-01 00:00:00 UTC | 0 | 0 | 0 |
| Oct 2025 | 2025-10-01 00:00:00 UTC | 2025-11-01 00:00:00 UTC | 0 | 0 | 0 |
| Nov 2025 | 2025-11-01 00:00:00 UTC | 2025-12-01 00:00:00 UTC | 1 | 1 | 0 |
| Dec 2025 | 2025-12-01 00:00:00 UTC | 2026-01-01 00:00:00 UTC | 0 | 0 | 0 |
| Jan 2026 | 2026-01-01 00:00:00 UTC | 2026-02-01 00:00:00 UTC | 0 | 0 | 0 |
| Feb 2026 | 2026-02-01 00:00:00 UTC | 2026-03-01 00:00:00 UTC | 0 | 0 | 0 |
| Mar 2026 | 2026-03-01 00:00:00 UTC | 2026-04-01 00:00:00 UTC | 0 | 0 | 0 |
| Apr 2026 | 2026-04-01 00:00:00 UTC | 2026-05-01 00:00:00 UTC | 0 | 0 | 0 |
| May 2026 | 2026-05-01 00:00:00 UTC | 2026-06-01 00:00:00 UTC | 1 | 0 | 1 |
| Jun 2026 | 2026-06-01 00:00:00 UTC | 2026-07-01 00:00:00 UTC | 0 | 0 | 0 |
| Jul 2026 | 2026-07-01 00:00:00 UTC | 2026-08-01 00:00:00 UTC | 1 | 1 | 0 |
| Aug 2026 | 2026-08-01 00:00:00 UTC | 2026-09-01 00:00:00 UTC | 1 | 1 | 0 |
| Sep 2026 | 2026-09-01 00:00:00 UTC | 2026-10-01 00:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
11 sources12-Factor Agents – Principles for building reliable LLM applications
3 points · Open discussionOwn your control flow! A key point from 12 factor agents.
"One thing that I have seen in the wild quite a bit is taking the agent pattern and sprinkling it into a broader more deterministic DAG." - https://github.com/humanlayer/12-factor-agents/blob/main/REA...
In Agents need control flow, not more promptsShow HN: Radkit – Build reliable AI agents with Rust
We (me and my co-founder) have been working on this library for a while and would love to get your thoughts.
github.com/agents-sh/radkit
radkit.rs/getting-started/
Most of the agent librararies out there just adds a huge prompt, put all the tool definitions and call the LLM on a loop hope and for the best.
This is not a way to build reliable ai agents. A better way to build ai agents is described in 12-factor agents by Dex Horthy here.
https://www.youtube.com/watch?v=8kMaTybvDUw
https://github.com/humanlayer/12-factor-agents
Another limitations of current agentic frameworks is their support for interoperability among agents is very limited.
Google came up with https://a2a-protocol.org/latest/ (now under linux foundation) to address this, but the agent frameworks trying to do as much as possible and keep the end users locked into their "ec
Read the rest
osystem" instead of supporting such protocols.
Everyone is so focused on MCP for some reason. (no hate for mcp, radkit supports mcp as well).
We belive in an agentic future where businesses expose ai agents and not mcp servers or rest apis. If you build an agent using radkit, it is a2a-protocol compliant from the get go.
With all of this in mind, we are building `radkit`.
It is still early stages. But we have reached a milestone and wanted to share with the community.
Thanks! Our favorite resources on this (both have been posted on HN a few times):
- https://www.anthropic.com/engineering/building-effective-age...
- https://github.com/humanlayer/12-factor-agents
That's also why we implemented pretty much all relevant patterns in the docs (i.e. https://pickaxe.hatchet.run/patterns/prompt-chaining).
If there's an example or pattern that you'd like to see, let me know and we can get it released.
In Show HN: Pickaxe – A TypeScript library for building AI agentsI'm a big fan of https://github.com/humanlayer/12-factor-agents because I think it gets at the heart of engineering these systems for usage in your app rather than a completely unconstrained demo or MCP-based solution.
In particular you can reduce most concerns around security and reliability when you treat your LLM call as a library method with structured output (Factor 4) and own your own control flow (Factor 8). There should never be a case where your agent is calling a tool with unconstrained input.
In A practical guide to building agents [pdf]For SWEs interested in "AI Engineering" (either getting involved in how models work, or building applications on them), there's a critical paradigm shift in that using "AI" requires more of an experimental mindset than software engineering typically does.
- I strongly recommend Chip Huyen's books ("Designing Machine Learning Systems" and "AI Engineering") and blog (https://huyenchip.com/blog/).
- Andreessen Horowitz' "AI Cannon" is a good reference listicle (https://a16z.com/ai-canon/)
- "12 factor agents" (https://github.com/humanlayer/12-factor-agents)
In Ask HN: Go deep into AI/LLMs or just use them as tools?I am wondering how libraries like DSPY [0] fits in your factor-2 [1]
As I was reading, I saw mention of BAML
> (the above example uses BAML to generate the prompt ...
Personally, in my experience hand-writing prompts for extracting structured information from unstructured data has never been easy. With DSPY, my experience has been quite good so far.
As you have used raw prompt from BAML, what do you think of using the raw prompts from DSPY [2]?
[0] https://dspy.ai/
[1] https://github.com/humanlayer/12-factor-agents/blob/main/con...
[2] https://dspy.ai/tutorials/observability/#using-inspect_histo...
In 12-factor Agents: Patterns of reliable LLM applications12-factor Agents: Patterns of reliable LLM applications
I've been building AI agents for a while. After trying every framework out there and talking to many founders building with AI, I've noticed something interesting: most "AI Agents" that make it to production aren't actually that agentic. The best ones are mostly just well-engineered software with LLMs sprinkled in at key points.
So I set out to document what I've learned about building production-grade AI systems: https://github.com/humanlayer/12-factor-agents. It's a set of principles for building LLM-powered software that's reliable enough to put in the hands of production customers.
In the spirit of Heroku's 12 Factor Apps (https://12factor.net/), these principles focus on the engineering practices that make LLM applications more reliable, scalable, and maintainable. Even as models get exponentially more powerful, these core techniques
Read the rest
will remain valuable.
I've seen many SaaS builders try to pivot towards AI by building greenfield new projects on agent frameworks, only to find that they couldn't get things past the 70-80% reliability bar with out-of-the-box tools. The ones that did succeed tended to take small, modular concepts from agent building, and incorporate them into their existing product, rather than starting from scratch.
The full guide goes into detail on each principle with examples and patterns to follow. I've seen these practices work well in production systems handling real user traffic.
I'm sharing this as a starting point—the field is moving quickly so these principles will evolve. I welcome your feedback and contributions to help figure out what "production grade" means for AI systems!
12-factor-agents: principles to build LLM software good enough for production
1 points · Open discussion