Serena

Created By
oraiosa year ago
a powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server & Agno integration)
Overview

What is Serena?

Serena is a powerful AI coding tool that acts as a coding agent, integrating with existing large language models (LLMs) to provide semantic code retrieval and editing capabilities directly on your codebase.

How to use Serena?

To use Serena, you can integrate it with your preferred LLM by setting up an MCP server or using the Agno framework. Follow the installation instructions provided in the documentation to configure it for your project.

Key features of Serena?

  • Fully-featured coding agent that works directly on your codebase.
  • Integrates with existing LLMs for enhanced coding capabilities.
  • Free to use without additional API keys or subscriptions.
  • Supports multiple programming languages through language servers.

Use cases of Serena?

  1. Analyzing and editing code in large projects.
  2. Assisting in coding tasks such as planning, writing, and executing code.
  3. Providing semantic code retrieval and editing tools for developers.

FAQ from Serena?

  • Is Serena really free to use?

Yes! Serena is free to use and does not require any subscriptions or API keys.

  • What programming languages does Serena support?

Serena provides direct support for Python, Java, and TypeScript, with indirect support for Ruby, Go, and C#.

  • How can I integrate Serena with my LLM?

You can integrate Serena using the model context protocol (MCP) or the Agno framework, following the setup instructions in the documentation.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
oraios
Star
998
Language
Python
License
MIT 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