Viewing profile — AmiteK

GitHub: https://github.com/LogicStamp/logicstamp-context It compiles TypeScript codebases into deterministic, structured context. Happy to answer questions.

I’ve been building LogicStamp Context, an open-source CLI that analyzes TypeScript codebases using the TypeScript AST and compiles them into deterministic JSON “contracts”. These d…

I built an open source CLI that analyzes TypeScript codebases using the TypeScript AST (via ts-morph) and extracts structured architectural contracts and dependency graphs. The goa…

I agree - that’s on me for the wording. I’m not claiming repeatability of agent inference or LLM sessions. By “repeatability” I mean the extraction itself: given the same repo stat…

I think the disagreement is about where inference belongs, not whether LLMs are capable. Git diffs + LLM inference work well for understanding changes once. What I’m targeting is r…

That’s a reasonable hypothesis, and I agree LLMs are very good at inferring structure from raw TypeScript within a local reasoning window. However, that inference has to be repeate…

I think we’re optimizing for different constraints. If your goal is zero extra round trips and you’re happy with AGENTS.md auto-injection + LSP queries, then I agree LogicStamp won…

On tool-call overhead: in the MCP flow it’s typically 1–2 calls per task (watch_status once, then read_bundle for the relevant slice). In watch mode we also skip snapshot refresh e…

I think there’s a conflation here between artifact determinism and agent behavior. LogicStamp’s determinism claim is about the generated context: same repo state + config ⇒ identic…

That’s fair, and I agree LSP-style search is excellent for interactive, local exploration. LogicStamp isn’t trying to replace that. The problem it targets is different: producing s…

Yes. In the MCP setup the agent doesn’t decide to regenerate arbitrarily. When stamp context --watch is active, the MCP server detects it. The agent first calls logicstamp_watch_st…

Adding a bit more context since I didn’t see your expanded comment at first: AGENTS.md and LogicStamp aren’t mutually exclusive. AGENTS.md is great for manual, human-curated guidan…

Good question. LogicStamp treats context as deterministic output derived from the codebase, not a mutable agent-side model. When code changes mid-session, watch mode regenerates th…

Hi HN, I built a CLI that extracts a deterministic, structured representation of a TypeScript codebase (components, hooks, APIs, routes) directly from the AST. The goal is to produ…

After working with LLMs on real React/TypeScript codebases, I kept running into issues caused by missing structure - invented props, broken hook assumptions, and style leakage. log…

I think this distinction matters less to users than to builders. From a user perspective, what’s novel here is policy and intent (no ads, no AI, privacy-first), not whether the ind…

One thing that seems under-discussed is what kind of state is worth persisting. Raw chat logs are cheap; distilled decisions, constraints, and preferences are harder but much more …