Hindsight Local

Gives Claude persistent memory across conversations by storing learnings, preferences, and procedure outcomes in a local vector database. Before each task, Claude recalls relevant context. After completing work, it retains what it learned. The underlying system extracts structured facts and builds relationships automatically, so you pass full context (conversation transcripts, detailed observations) rather than pre-summarized snippets. Requires one-time setup with an LLM provider. Most useful if you're working on the same project over multiple sessions and want Claude to remember what worked last time, which commands failed, or your coding preferences without repeating yourself.

skills.sh installs: 518
GitHub stars: 60.1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add vectorize-io/hindsight --skill hindsight-local --agent claude-code

Installs into .claude/skills of the current project.

Files

Hindsight Memory Skill (Local)

You have persistent memory via the hindsight-embed CLI. Proactively store learnings and recall context to provide better assistance.

Setup Check (First-Time Only)

Before using memory commands, verify Hindsight is configured:

uvx hindsight-embed daemon status

If this fails or shows "not configured", run the interactive setup:

uvx hindsight-embed configure

This will prompt for an LLM provider and API key. After setup, the commands below will work.

How Hindsight Works

When you call retain, Hindsight does not store the string as-is. The server runs an internal pipeline that:

Extracts structured facts from the content using an LLM
Identifies entities (people, tools, concepts) and links related facts
Builds temporal and causal relationships between facts
Generates embeddings for semantic search

This means you should pass rich, full-context content — the server is better at extracting what matters than a pre-summarized string. Your job is to decide when to store, not what to extract.