Skills
.Work. You
Rest

SemanticMemory

Community

Recall past work with hybrid semantic memory

Software Engineering#indexing#embeddings#memory#knowledge-graph#semantic-search#context-loading#tunnels
AuthorCarbeneAI
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Help users find, recall, and reuse past AI sessions, learnings, research, and personal notes so context and decisions are not lost between conversations or projects.

Core Features & Use Cases

  • Hybrid semantic search combining BM25 (FTS5) and vector similarity to surface relevant past work and snippets.
  • Temporal knowledge graph for time-bounded facts, entity timelines, and relation invalidation.
  • Layered context loading (Identity → Essential → On-Demand → Deep) to minimize token usage while surfacing the right context at the right time.
  • Cross-project "tunnels" discovery to find topic bridges across sessions, learnings, Obsidian notes, and research.
  • CLI tools for indexing, syncing, searching, knowledge-graph management, watcher daemon, and diagnostics to integrate into automation and workflows.

Quick Start

Run a semantic search for past work by invoking the SemanticSearch tool with your query, for example: bun ~/.claude/skills/SemanticMemory/tools/SemanticSearch.ts "How did we configure Traefik SSL?"

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: SemanticMemory
Download link: https://github.com/CarbeneAI/Forge/archive/main.zip#semanticmemory

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.