# smara

> smara — smara-io-smara. Use this tool when you need to maintain shared context across multiple AI sessions, enabling Claude, Cursor, and Codex to access and build upon previous interactions. Smara provides persistent memory, solving problems of lost context and session-specific knowledge. It accepts and stores data from AI tools, outputting a shared knowledge base accessible via git interface.

Canonical page: https://skillsregistry.net/skills/smara-io-smara  
JSON: https://api.skillsregistry.net/v1/skills/smara-io-smara

## Description

Persistent memory for AI tools. Give Claude, Cursor, and Codex shared context that survives across sessions.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/smara-io/smara)

## 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": "smara-io-smara"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/smara-io-smara` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/smara-io-smara/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