Gambit
AI
agent framework
SHOW HN2026
How HN took it
5 positive, 3 neutral or asking, 1 mixed, 1 critical, out of 10 comments about the project. Thread score +0.20.
Idea: 2 for, 0 againstPrivacy: 0 for, 1 againstDesign: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Clean separation of logic, code and prompts
From 1 comment
I've been playing with this for the past 24 hours or so. I like the atomic containment of the LLM, and the clear separation of logic, code, and prompts. You have some great…
elgrantomate on HN
Good architecture and typed deck composition
From 2 comments
Nice architecture. The typed deck composition pattern is exactly right for making agent workflows testable. One thing I've been thinking about is that schema validation catches…
niyikiza on HNthis is awesome are things like file system baked in? fan of the design of the system. looks great architecturally
sofdao on HN
Objections
Parameter and prompt constraints are hard to get the model to follow
From 1 comment
I've been playing with this for the past 24 hours or so. I like the atomic containment of the LLM, and the clear separation of logic, code, and prompts. You have some great…
elgrantomate on HN
PII guarantee claim is overstated
From 1 comment
> - Rubric based grading to guarantee you (for instance) don’t leak PII accidentally That does not sound like a "guarantee", at all.
yencabulator on HN
Requests
Gemini API support
From 1 comment
also, it seems like this works with openrouter, and perhaps OpenAI -- what about Gemini API?
elgrantomate on HN
File loading as input
From 1 comment
I've been playing with this for the past 24 hours or so. I like the atomic containment of the LLM, and the clear separation of logic, code, and prompts. You have some great…
elgrantomate on HN
Questions
How context is handled when agents call agents
From 1 comment
nice work. the idea of breaking agents into short-lived executors with explicit inputs/outputs makes a lot of sense - most failures i've seen come from agents staying alive too…
benban on HN
Comparison to Mastra
From 1 comment
Is this an alternative to https://mastra.ai/docs How would it compare?
Trufa on HN
Integration with cryptographic warrant authorization
From 1 comment
Nice architecture. The typed deck composition pattern is exactly right for making agent workflows testable. One thing I've been thinking about is that schema validation catches…
niyikiza on HN
Alternatives named
Mastra
From 1 comment
Is this an alternative to https://mastra.ai/docs How would it compare?
Trufa on HN
LangChain
From 1 comment
This looks quite interesting in terms of the architecture. Seems like a fresh take on stuff like Langchain, which at least last time I checked sucks.
franciscomello on HN