Atlas - Persistent Semantic Memory

VerifiedCaution

Ingest project documentation and code into persistent semantic memory using Qdrant and Voyage embeddings. Maintain context across sessions and search previous work.

Sby Skills Guide Bot
ProductivityIntermediate
506/2/2026
Claude Code
#persistent-memory#semantic-search#vector-database#context-ingestion#qdrant

Recommended for

Our review

Atlas ingests project documentation and code into persistent semantic memory using Qdrant and Voyage embeddings, enabling context retrieval across sessions.

Strengths

  • Persistent memory across sessions, solving context overflow.
  • High-performance semantic search with dual-indexing (semantic keys + timestamps).
  • Recursive directory ingestion supporting multiple file types.
  • Low latency (10-50ms) and high recall accuracy (Recall@10 > 0.98).

Limitations

  • Requires a locally running Qdrant instance and a Voyage API key.
  • Memory intensive (1.4GB RAM) for large vector collections.
  • Only supports listed file types; no images or PDFs.
When to use it

Use Atlas when you need to retain large context across sessions or make documentation queryable via semantic search.

When not to use it

Do not use it if your project is very small or you don't need persistent cross-session memory.

Security analysis

Caution
Quality score85/100

The skill executes bun scripts to ingest files and send chunks to Voyage for embedding. While the user explicitly sets the API key, this could lead to unintended data exfiltration if sensitive files are ingested. No destructive commands are present, but the combination of file access and external API usage warrants caution.

Findings
  • Uses external embedding API (Voyage) which sends document text chunks to a third-party service. Users should ensure sensitive data is not inadvertently ingested.
  • Requires Docker and local Qdrant instance; though the skill does not run Docker directly, it relies on a running service that could be misconfigured.

Examples

Remember architecture decision
Remember the API architecture we discussed and store it in Atlas so I can retrieve it later.
Ingest project documentation
Ingest all markdown files from the docs/ folder recursively into Atlas.
Search previous work
Search Atlas for all mentions of authentication patterns in the codebase.

name: atlas description: Ingest project documentation and code into persistent semantic memory (Qdrant + Voyage embeddings). Use when user wants to remember context across sessions, ingest docs, or search previous work. Requires Qdrant running locally and VOYAGE_API_KEY set. allowed-tools: Bash(bun:*)

Atlas - Persistent Semantic Memory

Atlas provides automatic context ingestion and retrieval using Voyage embeddings + Qdrant vector database. Solves the context overflow problem by storing knowledge persistently across sessions.

Quick Start

Prerequisites

  1. Qdrant running locally:
docker run -d -p 6333:6333 qdrant/qdrant
  1. VOYAGE_API_KEY set (get from https://voyageai.com):
export VOYAGE_API_KEY="your-key-here"
  1. Verify setup:
curl http://localhost:6333/health

Ingesting Context

Store files in Atlas memory for persistent retrieval:

Ingest Single File

cd ~/production/atlas
bun run --filter @inherent.design/atlas atlas ingest /path/to/file.md

Ingest Directory (Recursive)

cd ~/production/atlas
bun run --filter @inherent.design/atlas atlas ingest /path/to/docs/ --recursive

Ingest Multiple Paths

cd ~/production/atlas
bun run --filter @inherent.design/atlas atlas ingest README.md src/index.ts docs/ -r

What gets ingested:

  • Supported: .md, .ts, .tsx, .js, .jsx, .json, .yaml, .qntm, .rs, .go, .py, .sh, .css, .html
  • Ignored: node_modules, .git, dist, build, coverage, .atlas

Processing:

  • Chunks text (768 tokens, 13% overlap) for semantic coherence
  • Embeds with Voyage-3-large (1024-dim)
  • Stores in Qdrant with dual-indexing (semantic QNTM keys + temporal timestamps)
  • Preserves original text for future consolidation

Searching Context

Retrieve relevant context semantically:

Basic Search

cd ~/production/atlas
bun run --filter @inherent.design/atlas atlas search "typescript patterns"

Limited Results

cd ~/production/atlas
bun run --filter @inherent.design/atlas atlas search "memory consolidation" --limit 10

Temporal Filtering (Since Date)

cd ~/production/atlas
bun run --filter @inherent.design/atlas atlas search "sleep patterns" --since "2025-12-25"

Chronological Timeline

cd ~/production/atlas
bun run --filter @inherent.design/atlas atlas timeline --since "2025-12-01"

When to Use This Skill

Use Atlas when:

  • User asks to "remember this across sessions"
  • Project context is too large for single session
  • User wants to search previous work/decisions
  • Documentation needs to be queryable
  • Building on previous research or code

Examples:

  • "Remember the API architecture we discussed"
  • "What did we decide about the database schema?"
  • "Find all mentions of authentication patterns"
  • "Ingest all the .atlas research files"

Architecture

Built on .atlas research (Steps 1-4 + Sleep Patterns):

Stack:

  • Voyage-3-large embeddings (1024-dim, 9.74% better than OpenAI)
  • Qdrant HNSW index (M=16, int8 quantization, 4x compression)
  • RecursiveCharacterTextSplitter (semantic boundaries)
  • Dual-indexing (QNTM semantic keys + RFC 3339 timestamps)

Production Config (from Step 3 research):

  • Recall@10: >0.98
  • Latency: 10-50ms (p95)
  • Memory: 1.4GB RAM + 5GB disk per 1M vectors

Technical Details

For implementation details, see:

Packages:

  • @inherent.design/atlas-core - Core library (embeddings, storage, search)
  • @inherent.design/atlas - Command-line interface
  • @inherent.design/atlas-mcp - MCP server for Claude Code integration
Related skills