Top all-time · #9030
Archestra
Company blog · archestra.ai/blogaistartupsprogramming
Archestra is the company blog at archestra.ai, writing about ai, startups and programming. Since 2025, 8 different Hacker News readers have linked it 25 times, most often “Brew by Weight? Brew by AI”. No feed was found, so read it on the site itself.
Too few sampled comments (4) to say how often HN recommends it.?
Why HN links it
HN readers link Archestra's posts on stopping AI bot spam in GitHub repos with a captcha-gated commit check, and on prompt injection defence using a Dual LLM pattern. The comments cite these posts without judging the writing.
Summarised by Claude from a sample of 4 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Move AI into production without losing control of data, access, and actions.
Most-linked posts?
- Brew by Weight? Brew by AI3 people · 4 mentions · first linked 2025-12-29
- We stopped AI bot spam in our GitHub repo using Git's –author flag2 people · 4 mentions · first linked 2026-04-17
What Hacker News says?
We do, it's a part of our hiring pipeline: https://archestra.ai/careers
Comment linking /careers
on “We stopped AI bot spam in our GitHub repo using Git's –author flag”Submitted We stopped AI bot spam in our GitHub repo using Git's –author flag as a story · 65 points
HN discussionHi HN community, I wanted to share our approach to reduce amount of AI slop PR's and issues in our repo. We enabled "require prior contribution" flag on GH and created a CI script that creates a tiny commit co-authored with you, if you pass captcha on our website. Worked really well and we were able to block at least 500 bots in the first week. Sharing a screenshot from cloudflare: https://archestra.ai/hn-comment-cl…
Comment linking /hn-comment-cloudflare-challenge-outcomes-do-not-delete.webp
on “We stopped AI bot spam in our GitHub repo using Git's –author flag”Submitted We Tested Jev on 100 Agent Tool Calls as a story · 12 points
HN discussionHi Hacker News! Matvey, Ildar, Joey, and Dominik here. Anthropic introduced the Model Context Protocol (MCP) almost a year ago, and the community has built thousands of open-source MCP servers, but there are a few issues. Local MCP servers are executables, and running straight from GitHub is quite dangerous. Also, to start the local MCP server and connect it to, for example, Gmail, one needs to register a Google Clo…
Comment linking /
on “Archestra – open-source MCP orchestrator for everyone”Submitted We gave a coding agent the lethal trifecta: data, internet, a public repo as a story · 11 points
HN discussionIt is quite simple to start it with n8n https://www.archestra.ai/docs/platform-n8n-example and experiment with Dual LLM protection
Comment linking /docs/platform-n8n-example
on “Show HN: Open-Source Gateway to Stop Tool-Abusing Prompt Injections”Submitted Debugging on weak models reveals more bugs as a story · 9 points
HN discussionhey there Joey here from Archestra. Good question. I recently was evaluating what you mention, against the latest/"smartest" models from the big LLM providers, and I was able to trick all of them. Take a look at https://www.archestra.ai/blog/what-is-a-prompt-injection which has all the details on how I did this.
Comment linking /blog/what-is-a-prompt-injection
on “Archestra's Dual LLM Pattern: Using "Guess Who?" Logic to Stop Prompt Injections”Submitted We've raised $10M to build open source AI security as a story · 9 points
HN discussionBots are killing opensource, but they pump product metrics so nobody cares. I maintain an open source repo and we've made a decision to limit all bot activity, even if it makes us less sexy in front of VCs. We figured out a workaround to limit activity to prior contributors only, and add a CI job that pushes a coauthored commit after passing captcha on our website. It cut the AI slop by 90%. Full write-up https://ar…
Comment linking /blog/only-responsible-ai
on “GitHub's Fake Star Economy”Submitted Show HN: Open-Source Gateway to Stop Tool-Abusing Prompt Injections as a story · 9 points
HN discussionAt the end it's a company choice: do you buy BS metrics or you don't. We've recently decided to complicate life of AI bots in our repo https://archestra.ai/blog/only-responsible-ai , hoping they will just choose those AI startups who are easier to engage with.
Comment linking /blog/only-responsible-ai
on “GitHub's Fake Star Economy”Submitted A Drizzle migration linter that catches unsafe schema changes in CI as a story · 6 points
HN discussionHi HN, Matvey from Archestra here. Recently, OpenAI shipped "Sites", a mini-apps AI builder. It's similar to "Databricks Apps" or Loveable. We worked on this concept for the last few months, and tried to approach it from the most "open source friendly" and interconnectable way, providing the ability to build mini apps re-using the MCP data layer, re-using MCP authentication while accessing those apps, and also expos…
Comment linking /blog/new-apps
on a deleted threadSubmitted Archestra's Dual LLM Pattern: Using "Guess Who?" Logic to Stop Prompt Injections as a story · 6 points
HN discussionSubmitted Let's talk about AI slop in open source as a story · 5 points
HN discussionSubmitted Archestra LLM Gateway Now Supports All Types of LLM Auth as a story · 3 points
HN discussionSubmitted Brew by Weight? Brew by AI as a story · 2 points
HN discussionSubmitted The catalogue of prompt injection attacks as a story · 1 points
HN discussionSubmitted MCP Context Window Too Many Servers: Why 100 MCP Servers Crush Your Agent as a story · 1 points
HN discussionSubmitted Enterprise-Managed Authorization for MCP as a story · 1 points
HN discussionSubmitted MCP for a Coffee Machine... Worked! as a story · 1 points
HN discussionSubmitted Brew by Weight? Brew by AI – Archestra Blog – Archestra as a story · 1 points
HN discussionSubmitted Brew by Weight? Brew by AI as a story · 1 points
HN discussion
