Files
skillkit/packages/memory
Rohit Ghumare 821e9f714b chore: bump to 1.23.0, rewrite README, drop dead LLM SDK deps, add branded tags (#116)
Version bump
------------
1.22.1 -> 1.23.0 across all workspace packages. Minor bump covers the
slim-install dependency layout, safer first-time agent picker, and the
corresponding doc + branding changes.

Prune dead optional deps in @skillkit/core
------------------------------------------
@anthropic-ai/sdk, @google/genai, ollama, and openai were listed as
optionalDependencies but never imported. They were pulled through
@skillkit/cli transitively on every default install, adding ~57
packages and one deprecation warning (node-domexception via the
SDKs' own formdata-node / node-fetch transitives). Grep of
packages/core/src confirms no SDK import; providers in
src/ai/providers use direct fetch() against the provider HTTP APIs.
Drop them. better-sqlite3, sqlite-vec, and node-llama-cpp stay
because they are actually dynamic-imported by the vector store and
embedding pipeline.

Measured on a fresh npm cache (overrides-pinned file: tarballs):
  before:   475 pkgs / 18s / 3 deprecation warnings
  1.23.0:   418 pkgs / 18s / 2 deprecation warnings
  slim:     118 pkgs /  9s / 0 deprecation warnings
The two remaining warnings are upstream:
  - prebuild-install@7.1.3 from better-sqlite3 (must stay)
  - glob@9.3.5 from @opentui/solid -> babel-plugin-module-resolver

README rewrite
--------------
Punchier top fold. Palette-consistent SVG tag badges under
assets/tags/ replace most shields.io badges (still keep npm/CI/etc
on shields since they need live data). Collapsible detail blocks
for every feature instead of the linear wall. Same nav anchors the
site uses. No em dashes. No AI filler words. Writing style pulls
from the ai-engineering-from-scratch and awesome-claude-design
READMEs the user already runs.

Branded SVG tags
----------------
scripts/gen-tags.mjs generates 20 SVG pills under assets/tags/ in
the SkillKit palette (#09090b base, #fafafa text, #3f3f46 border,
accent per tag). Two variants: single pill with left accent bar
(new, slim-install, v1.23.0, etc.) and split badge (agents | 45,
packages | 118, install | 9s). Matches the aesthetic used on
awesome-claude-design, tailored to SkillKit's monochrome brand.
The tags directory is fork-and-remix friendly; README points to it.
2026-04-21 00:25:55 +01:00
..

@skillkit/memory

npm version License

Semantic memory with embeddings for SkillKit - CozoDB-backed persistent memory with vector search for AI agents.

Installation

npm install @skillkit/memory

Key Features

  • CozoDB Backend: Embedded graph database with HNSW vector index
  • Semantic Search: Cosine similarity search over embeddings
  • Xenova Transformers: Local embedding generation (no API keys)
  • Observations & Learnings: Store raw observations and compressed learnings
  • Memory Compression: Extract patterns from observations
  • Persistent Storage: SQLite-backed durability
  • Memory Reinforcement: Boost memory relevance through usage

Usage

Basic Memory Operations

import { MemoryStore, EmbeddingEncoder } from '@skillkit/memory';

// Initialize encoder
const encoder = new EmbeddingEncoder();
await encoder.init();

// Create memory store
const store = new MemoryStore('./my-project/.skillkit/memory');
await store.init();

// Store an observation
await store.addObservation({
  content: 'User prefers TypeScript strict mode',
  tags: ['typescript', 'preferences'],
  source: 'conversation',
});

// Search memories
const results = await store.search('typescript configuration', { limit: 5 });

Memory Compression

import { MemoryCompressor } from '@skillkit/memory';

// Compress observations into learnings
const compressor = new MemoryCompressor(store);
const learnings = await compressor.compress({
  minObservations: 3,
  maxAge: 7 * 24 * 60 * 60 * 1000, // 7 days
});
// Get embedding for a query
const embedding = await encoder.encode('React best practices');

// Search by vector
const results = await store.searchByVector(embedding, {
  limit: 10,
  threshold: 0.7,
});

Export Memories as Skills

import { MemoryExporter } from '@skillkit/memory';

// Export memories to a skill file
const exporter = new MemoryExporter(store);
const skill = await exporter.toSkill({
  name: 'project-patterns',
  tags: ['patterns', 'best-practices'],
});

API Reference

MemoryStore

interface MemoryStore {
  init(): Promise<void>;
  addObservation(obs: Observation): Promise<string>;
  addLearning(learning: Learning): Promise<string>;
  search(query: string, options?: SearchOptions): Promise<Memory[]>;
  searchByVector(embedding: number[], options?: SearchOptions): Promise<Memory[]>;
  reinforce(id: string): Promise<void>;
  close(): Promise<void>;
}

EmbeddingEncoder

interface EmbeddingEncoder {
  init(): Promise<void>;
  encode(text: string): Promise<number[]>;
  encodeBatch(texts: string[]): Promise<number[][]>;
  dispose(): Promise<void>;
}

Types

interface Observation {
  content: string;
  tags?: string[];
  source?: string;
  metadata?: Record<string, unknown>;
}

interface Learning {
  title: string;
  content: string;
  tags?: string[];
  confidence?: number;
}

interface Memory {
  id: string;
  content: string;
  embedding: number[];
  score?: number;
  createdAt: Date;
}

Documentation

Full documentation: https://github.com/rohitg00/skillkit

License

Apache-2.0