x-archive-rag

x-archive-ragis not a bigger prompt. It is a small local data layer for your archive.

Run it locally after importing an archive:

x-archive-rag web --db ./memory.sqlite --open

Try the UI with the included sample archive before touching private data:

git clone https://github.com/mameshivaa/x-archive-rag.git cd x-archive-rag python3 -m pip install -e . x-archive-rag demo --open

- Import your official X archive ZIP or extracted directory into a local SQLite database.
- Search it with keyword, semantic, or hybrid retrieval.
- Generate a persona profile from your own posts.
- Build citation-grounded draft prompts that show the tweets used as evidence.
- Expose the same local memory to AI clients through MCP tools.

The main interface is a small CLI with nine commands:

- ingestturns an archive into a reusable local database.
- searchretrieves relevant posts with citation IDs.
- profilesummarizes recurring topics, tone, and writing patterns.
- draftbuilds a grounded prompt from retrieved evidence.
- mcpexposes the same memory to AI clients that support MCP.
- webruns a local browser UI for search, profile inspection, and draft prompts.
- democreates a sample database and can open the local web UI.
- doctorchecks whether a database is ready for search, draft, and MCP use.
- exportwrites imported tweets as JSONL or Markdown for inspection and reuse.

Text output is designed for humans. JSON and Markdown output are designed for scripts, agents, and repeatable workflows.

Alpha. The current release is intentionally small:

- Importtweets.js/tweet.jsfrom an extracted archive directory or archive ZIP, including common long-form tweet text fields and expanded URL entities.
- Store normalized tweets in SQLite.
- Search with SQLite FTS5, dependency-free semantic retrieval, or hybrid retrieval.
- Generate a persona profile from your own posts.
- Build grounded RAG prompts with cited tweets.
- Expose archive search and draft prompts through a minimal MCP stdio server.
- Optionally call OpenAI-compatible chat completions usingOPENAI_API_KEY.

Most archive tools help you search old posts. This project focuses on a different workflow:

"Given what I have said before, draft something that sounds like me, while showing the evidence."

The assistant is designed for drafting and reflection, not impersonation or automated posting.

Uploading a ZIP is a one-off context dump.x-archive-ragis a reusable memory layer.

Want to test without private archive data first?

x-archive-rag ingest ./twitter-archive.zip --db ./memory.sqlite x-archive-rag profile --db ./memory.sqlite x-archive-rag search "personal AI memory" --db ./memory.sqlite --mode hybrid x-archive-rag draft "What do I think about OSS personal AI?" --db ./memory.sqlite x-archive-rag web --db ./memory.sqlite --open

Use the sections below when you need more control over import format, date filters, exports, OpenAI-compatible calls, or MCP.

Import an extracted X archive directory:

x-archive-rag ingest ./twitter-archive --db ./x-archive-rag.sqlite

Retweets are excluded by default so profiles and drafts focus on your own statements. Add--include-retweetsif you want to index retweets too.

x-archive-rag ingest ./twitter-archive.zip --db ./x-archive-rag.sqlite

x-archive-rag search "AI agents and personal tools" --db ./x-archive-rag.sqlite

Search and draft outputs include citation IDs such asT1, so generated text can refer back to specific retrieved posts.