chitta

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. 🧠

What does this entry provide?

chitta is an MCP server entry in ChatHome Skills, sourced from GitHub MCP Search and scored 18/100. 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 conte. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding chitta to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.

Snapshot facts

Source: GitHub MCP Search
Quality: 18/100
Install method: source code
Repo: Nipurn123/chitta
Repo updated: Jul 13, 2026

Source checkout

git clone https://github.com/Nipurn123/chitta.git

Install method: source code

Review the upstream source before running this command.

GitHub project

Quality

Repo stars

Repo updated

Jul 13, 2026

How is this score calculated?

Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.

Security signals

highMatched in: skillBody
Downloads a script and pipes it straight into a shell, executing remote code with no review.
curl -fsSL https://bun.sh/install | bashDispute this flag?

Scan coverage: Install metadata and repository README.

Automated signals from install metadata and a bounded skill body — not a full code security audit and not a recursive source or dependency review.

MCP manifest

{
  "fullName": "Nipurn123/chitta"
}

Discovery note

Report an issue with this listing