@intelagent/knowledge-grid - npm Package Compare versions

Comparing version 0.1.0 to 0.1.1

package.json

 {
   "name": "@intelagent/knowledge-grid",
-  "version": "0.1.0",
-  "description": "Layered knowledge grid for AI agents — vector indexing, domain inference, intent-driven retrieval, and prompt composition. Zero dependencies.",
+  "version": "0.1.1",
+  "description": "Structured context for AI agents — a layered knowledge grid with vector indexing, domain inference, intent-driven retrieval, and token-budgeted prompt composition. Better context, better agent performance. Zero dependencies.",
   "license": "MIT",
@@ -12,5 +12,8 @@ "repository": {
     "knowledge-grid",
+    "agent-context",
+    "context-management",
     "rag",
     "retrieval-augmented-generation",
     "ai-agent",
+    "llm-context",
     "vector-search",
@@ -21,3 +24,5 @@ "knowledge-base",
     "domain-inference",
-    "prompt-builder"
+    "prompt-context",
+    "prompt-builder",
+    "context-window"
   ],
@@ -24,0 +29,0 @@ "main": "./dist/index.js",

README.md

 # @intelagent/knowledge-grid
 
-A layered knowledge grid for AI agents. Vector indexing, domain inference, intent-driven retrieval, and prompt composition — zero dependencies.
+Better context for AI agents. A layered knowledge grid that gives your agent structured, relevant context — so it performs better on every interaction. Zero dependencies.
 
@@ -11,5 +11,5 @@ ```
 
-Most RAG systems treat all knowledge equally — every document chunk lives in one flat vector store with one similarity score. But real expertise doesn't work like that. An expert knows the difference between "what the manual says" (reference), "what worked last time" (experience), and "what's happening right now" (live state).
+AI agents are only as good as the context they receive. Most RAG systems dump flat vector results into the prompt — no structure, no priority, no awareness of what *kind* of knowledge is being retrieved. The result is diluted context and inconsistent agent behaviour.
 
-**Knowledge Grid** organises agent knowledge into a **4-layer lattice** crossed with **9 domains**, so retrieval understands not just *what* is relevant but *what kind of knowledge it is* and *how authoritative it should be*.
+**Knowledge Grid** organises agent knowledge into a **4-layer lattice** crossed with **9 domains**, giving your agent structured context that distinguishes live state from learned experience from reference docs from system knowledge. The agent gets the right context, in the right priority, every time — and performs better because of it.
 
@@ -230,24 +230,4 @@ ```
 
-## What's NOT in this package
-
-The open-source grid gives you a working knowledge system. The commercial **Knowledge Grid Intelligence** add-on (available on the [Intelagent Platform](https://intelagent.com)) adds compounding intelligence:
-
-| Feature | Open Source | Intelligence |
-|---------|:----------:|:------------:|
-| Vector indexing + dedup | Yes | Yes |
-| Domain inference | Yes | Yes |
-| Static layer weights | Yes | Yes |
-| 2 SDK connections | Yes | Unlimited |
-| 3 domains | Yes | All 9+ custom |
-| System seed (10 best practices) | Yes | Yes |
-| Template-based guides | Yes | Yes |
-| **Pathways** (learned associations) | — | Yes |
-| **Maturation** (adaptive expertise) | — | Yes |
-| **Dynamic tool selection** | — | Yes |
-| **LLM-powered research** | — | Yes |
-| **Web search fallback** | — | Yes |
-| **Awareness indexer** | — | Yes |
-
 ## License
 
 MIT

No alert changes

Worsened metrics

Total package byte prevSize

159317

-0.37%

Number of lines in readme file

232

-7.94%

No dependency changes