Skip to content
Agentmart
Submit a tool

search-memory

Search semantic memory across all embedded content (memory, posts, issues, audit).

Skill by Glad-Labs

IndexedApache-2.0★ 6
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/glad-labs-search-memory

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Search semantic memory across all embedded content (memory, posts, issues, audit). Use when the user says "what do I know about", "search memory for", "recall", "find references to", or asks open-ended questions about prior context.

Use cases: security, writing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Shell scripts

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/search-memory

What's inside

Skill name
search-memory
Description
Search semantic memory across all embedded content (memory, posts, issues, audit). Use when the user says "what do I know about", "search memory for", "recall", "find references to", or asks open-ended questions about prior context.
License
Apache-2.0
Instructions
37 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (2)

  • SKILL.md
  • run.sh · scripts/

SKILL.md (first lines)

# Search Memory

Vector-search across the unified embeddings table (poindexter_brain.embeddings — ~25K rows spanning posts, memory files, issues, audit log, brain decisions, claude_sessions). Returns the top hits with similarity scores so the agent can decide how confidently to surface them.

Backed by the worker's `/api/memory/search` endpoint, which fronts `MemoryClient.search` (pgvector cosine similarity over nomic-embed-text:768 embeddings).

## Usage

```bash
scripts/run.sh "<query>" [limit] [min_similarity]
```

## Parameters

- **query** (string, required): natural-language search query
- **limit** (int, optional, default 5): top-N results to return
- **min_similarity** (float, optional, default 0.5): drop hits below this threshold (0..1)

## Output

Plain-text summary of hits, one per line, prefixed with `[similarity] [source_table] source_id`. Suitable for direct TTS readback in voice contexts.

## Example

```
> scripts/run.sh "backup strategy" 3 0.5
Memory search: "backup strategy" (3 results)

1. [0.7821] [memory] feedback_backup_strategy
   Tier 1 in-stack hourly+daily, Tier 2 off-machine via restic...
2. [0.6547] [post] post_142
   Why solo founders need ruthless backup discipline...
3. [0.5912] [memory] project_disaster_recovery
   2026-05-05 incident: postgres-local volume wiped during Docker Desktop reinstall...
```

From Glad-Labs/poindexter, Apache-2.0.

More from Glad-Labs/poindexter

Signals

Stars
6
Forks
2
Open issues
31
Last commit (this folder)
Jul 26, 2026 (3 months ago)
Last release
Oct 21, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
Repository
github.com/Glad-Labs/poindexter
Website
www.gladlabs.io
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Glad-Labs

Cite this page

search-memory skill. Agent Mart. https://agentmart.dev/skills/glad-labs-search-memory (last updated 2026-10-24)