Remnic Search

Remnic Search is an AI Engineering skill for Claude Code, published by joshuaswarren in remnic.

193 stars23 forkson joshuaswarren/remnicAdded 2026/09/06+1% in starsRepository updated 2026/09/03

ai-agentai-memoryclaude-codeengramhermes-pluginknowledge-graphllmlocal-firstlong-term-memorymarkdownmcpmcp-servermemory-pluginokfopen-knowledge-formatopenaiopenclawsemantic-searchtypescript

Install in seconds

Install Remnic Search

Copy Remnic Search into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/joshuaswarren/remnic/tree/main/packages/plugin-claude-code/skills/remnic-search ~/.claude/skills/remnic-search

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/joshuaswarren/remnic.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: packages/plugin-claude-code/skills/remnic-search/SKILL.md in joshuaswarren/remnic
Installs to: ~/.claude/skills/remnic-search
Collection: One of 12 skills cataloged from this repository
Category: AI Engineering — 3278 skills

What Remnic Search does

Remnic Search runs a literal full-text query across Remnic memories when recall misses something or exhaustive matching is needed. Use it for direct searches, date/category filters, and follow-up lookups.

Remnic Search is cataloged under AI Engineering on DirSkills. Remnic Search comes from a repository tagged ai-agent, ai-memory, claude-code, engram and hermes-plugin.

Documentation

README

Excerpt

When to use

Use when remnic-recall did not surface something the user insists exists, or when the task genuinely needs exhaustive coverage rather than a ranked semantic summary.

Triggers:

"Search memories for …"
"Deep search on …"
/remnic:search <query> slash command invocation.
Follow-up after remnic-recall returned nothing useful.

Inputs

query (required) — literal phrase or keyword string; this is full-text, not semantic.
Optional: date range, category filter, entity constraint.

Procedure

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Remnic Search

What else does joshuaswarren publish alongside Remnic Search?
Remnic Search is one of 12 skills that DirSkills catalogs from joshuaswarren/remnic, the repository it ships in. Its siblings there include Remnic Entities, Remnic Entities and Remnic Memory Workflow. Each one is a separate skill with its own page in this directory, installs the same way Remnic Search does, and is maintained by joshuaswarren in that same repository. The rest of the collection is listed on the joshuaswarren/remnic page.
How does Remnic Search compare to other AI Engineering skills?
Remnic Search ranks #2894 by stars among the 3278 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Remnic Search against them. Open each page to compare what they document and how they install.