# ostk-recall

> ostk-recall — os-tack-ostk-recall. Use this tool when you need to perform efficient cross-corpus retrieval across various data types, such as markdown, code, and Claude Code sessions. It solves problems related to information retrieval and knowledge management by providing a hybrid search functionality that combines dense and BM25 search methods. The ostk-recall tool takes in queries and returns relevant results, making it ideal for use cases involving code search, knowledge base querying, and information discovery in local-first environments.

Canonical page: https://skillsregistry.net/skills/os-tack-ostk-recall  
JSON: https://api.skillsregistry.net/v1/skills/os-tack-ostk-recall

## Description

Local-first cross-corpus retrieval MCP server — model2vec embeddings + LanceDB (Tantivy BM25) + SQLite. One binary; hybrid (dense + BM25) search across markdown, code, and Claude Code sessions.

## Trust

- **Trust score (0–1):** 0.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** database
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/os-tack/ostk-recall)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "os-tack-ostk-recall"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/os-tack-ostk-recall` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/os-tack-ostk-recall/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt