Gnosis, a knowledge base for what the code can't tell you
Details
- External ID
- 47920641
- Source
- HN
- Company
- —
- Product
- Gnosis, a knowledge base for what the code can't tell you
- Website domain
- github.com
- Launched
- April 27, 2026
- Cohort
- —
- Upvotes
- 6
- Upvotes percentile
- 0.2808483290488432
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
For the past few years, I've been frustrated at how we document our products. The code can tell you what you ended up doing, maybe why you ended up doing it (if your team is disciplined about comments/documents), but it can't tell you why you didn't do what you didn't do.Time and time again, I've seen teams try to change something to a better way, only to realize why it was done the "worse" way in the first place. Documenting decisions not taken is just really hard, ADRs help but doing it for everything is just too noisy and time-consuming. What's more, most of the decisions just detail what was decided, which is the easy part.I've been wanting to change this for a long time, and with LLMs, we now can. LLMs are diligent about documenting, and all you need is an instruction in AGENTS.md. That's why I built gnosis.Simply tell your agent to run it after planning and when done, and gnosis provides the agent with all direction necessary.Gnosis tells the agent to document only information it got from the human, not anything it can find by itself, and especially to document why alternatives were rejected. It uses a JSONL append-only log and a SQLite index (for retrieval), making it simple, fast, and convenient.I'd appreciate it if you tried it out and gave me feedback!
Enrichment
- Theme
- AI agent frameworks and developer tools
- Vertical
- Horizontal
- Function
- Dev tools
- Audience
- Developer
- AI stance
- Not AI
- Project type
- Commercial product
- Normalized one-liner
- knowledge base for undocumented code context
- Manually corrected
- False
Could you build this?
Yes This is a documentation and knowledge base tool designed to record architecture and design decisions (like ADRs or rejected alternatives), which is a standard CRUD app with text editing and metadata indexing.
Discussion
4 comments analyzed.
Competitors mentioned: Mintlify (design decision documentation)
Concerns raised: Stale rejection entries become outdated when constraints/dependencies change, Agent lacks context outside what human provides for autonomous deprecation
Feature requests: Mechanism to surface or flag stale decision entries for revisit, Automated detection of when rejection conditions have changed
Competitors
Other products that read as similar to this one — 49 launches clear the similarity bar, closest 8 shown.
Attention rank: #39 of 50 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 177 days after the earliest competitor.
- Instantly get the transcript from the agent that wrote any line of code · hn · 2026-09-03 · 5 upvotes · similarity 0.44
- Why write code if the LLM can just do the thing? (web app experiment) · hn · 2025-11-01 · 436 upvotes · similarity 0.38
- SQLens · ph · 2026-09-09 · 1 upvotes · similarity 0.37
- Kelet · hn · 2026-04-14 · 47 upvotes · similarity 0.36
- git-lrc · hn · 2026-06-16 · 9 upvotes · similarity 0.36
- Capy · hn · 2026-08-05 · 13 upvotes · similarity 0.35
- Lathe · hn · 2026-06-07 · 402 upvotes · similarity 0.35
- AI·rete·RAG · hn · 2026-09-22 · 44 upvotes · similarity 0.35
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a dev tools tool for Sales yet.