@sandrinio/vbounce 1.3.0 → 1.3.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +21 -0
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -24,6 +24,27 @@ The next time an agent writes code, it reads the `_manifest.json` and the `LESSO
24
24
 
25
25
  ---
26
26
 
27
+ ## 🛠️ The Tech Stack
28
+
29
+ V-Bounce OS is built to be **local-first, privacy-conscious, and blazing fast**.
30
+
31
+ - **Vector Database**: [LanceDB](https://lancedb.com/) — A serverless, local vector DB used to store and query project context.
32
+ - **Embeddings**: [Xenova Transformers](https://github.com/xenova/transformers.js) — Local execution of `all-MiniLM-L6-v2`. **No private code is ever sent to external embedding APIs for RAG.**
33
+ - **Runtime**: Node.js — Powering the validation pipeline and semantic search engine.
34
+ - **Data Contract**: YAML Frontmatter + Markdown — Ensures human-readable agent handoffs that are also strictly machine-parsable.
35
+
36
+ ---
37
+
38
+ ## 🧠 Semantic Context (Local RAG)
39
+
40
+ V-Bounce OS doesn't just dump your entire codebase into a prompt. It uses **Retrieval-Augmented Generation (RAG)** to find only the rules that matter right now.
41
+
42
+ 1. **Indexing**: The `pre_bounce_sync.sh` script crawls your `product_plans/`, `LESSONS.md`, and `Roadmap ADRs`, converting them into searchable vectors.
43
+ 2. **Querying**: Agents use the built-in `./scripts/vbounce_ask.mjs` tool to ask questions like *"What are the architectural constraints for auth?"* or *"What mistakes did we make with the last React component?"*.
44
+ 3. **Targeted Context**: The agent receives only the most relevant 3-5 snippets of project history, preventing context-window bloat and improving instruction following.
45
+
46
+ ---
47
+
27
48
  ## 🚀 Quick Start
28
49
 
29
50
  One command to install the entire methodology directly into your AI assistant.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@sandrinio/vbounce",
3
- "version": "1.3.0",
3
+ "version": "1.3.1",
4
4
  "description": "V-Bounce OS: Turn your AI coding assistant into a full engineering team through structured SDLC skills.",
5
5
  "type": "module",
6
6
  "bin": {