AI

Created By
Nasdanikaa year ago
Things related to artificial intelligence built on top of Nasdanika capabilities
Overview

What is AI?

AI is a project focused on artificial intelligence that operates on top of interconnected models and resource sets, abstracting AI components from low-level implementation details.

How to use AI?

To use AI, you can interact with the CLI to manage embeddings, perform semantic searches, and chat with models. You can also integrate it with a static site and semantic search commands.

Key features of AI?

  • Embeddings generation from OpenAI and Ollama.
  • Vector store for efficient data retrieval.
  • CLI tools for managing embeddings and vector stores.
  • Chat completions and integration with Vue.js for chat applications.

Use cases of AI?

  1. Semantic search for retrieving relevant information based on context.
  2. Chatting with AI models for interactive experiences.
  3. Managing and utilizing embeddings for various AI applications.

FAQ from AI?

  • What types of models can be used with AI?

AI can work with various models and resource sets, allowing for flexible integration.

  • Is there a graphical interface for AI?

Currently, AI primarily operates through CLI, but there are plans for web-based interfaces.

  • How does AI handle data storage?

AI uses a vector store to manage embeddings and facilitate semantic searches.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
Nasdanika
Star
0
Language
Java
License
EPL-2.0 license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago