# chitta

> chitta — nipurn123-chitta. Use this tool when you need to efficiently manage and recall local memory for various AI models, such as Claude Code and Codex, with features like knowledge graph and vector search. It solves problems of high latency and token usage, providing fast recall and reduced context per query. Ideal for applications requiring persistent memory and multi-agent collaboration, with a simple interface using a single SQLite file and TypeScript SDK.

Canonical page: https://skillsregistry.net/skills/nipurn123-chitta  
JSON: https://api.skillsregistry.net/v1/skills/nipurn123-chitta

## Description

Persistent local memory for Claude Code, Cursor, Codex & 14 more - an MCP server + TypeScript SDK. One SQLite file, ~100ms recall, 0 LLM tokens, 143x less context per query. Inside: knowledge graph, vector search, self-correcting beliefs, bi-temporal queries, per-user ACL, multi-agent memory. 🧠

## Trust

- **Trust score (0–1):** 0.85
- **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/Nipurn123/chitta)

## 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": "nipurn123-chitta"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nipurn123-chitta` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nipurn123-chitta/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