Sema

Love Cursor? You'll love Sema.

Sema is a VS Code extension, an agentic assistant, and a semantic indexer — a Cursor-style chat that already knows your codebase, except you pick the provider and the model, and you can switch mid-conversation.

• The indexer gives every provider real semantic search. Through the extension, all providers use it; and Claude Code and Codex can use it directly in their official apps or CLIs — over MCP, no sema extension needed (see docs). Either way they stop burning tokens hunting for files.
• The extension gives you one chat panel with eight engines — Claude Code, Codex, Open Code, Anthropic, OpenAI, DeepSeek, OpenRouter, Together AI.
• Agent permission controls let Claude Code and Codex pause protected actions for an inline Allow/Reject decision in the Sema chat, or use their clearly marked bypass mode in a trusted sandbox. Each provider keeps its own permission choice.
• DevOps guard lets your AI provider run real infra commands — kubectl, Terraform, AWS CLI, Helm — safely. Every command is classified (safe / needs-approval / prohibited) and secret-redacted before it runs, never after; mutating actions are held until you explicitly approve them, and irreversible ones are refused outright, no exceptions (see docs).

Sema uses your existing Claude Code and Codex subscription — no extra API key, no re-login. Or bring your own key for any API provider.

Use both, or either one alone.

Experimental · macOS and Linux · Requires Python 3.11+ · Nothing leaves your machine. Disclaimer

Install

1. Install the CLI (bootstraps uv + Python if needed):

curl -fsSL https://raw.githubusercontent.com/masihmoloodian/sema/main/install.sh | sh

2. Install the extension from the VS Code Marketplace (or search "sema" in the Extensions view). Want to build it yourself? See the docs.

3. Index and register. Open your project, then use the extension's Manage panel to build the index and register your AI CLIs in a click — or do it from the CLI:

cd your-project
sema index .     # build the local semantic index
sema setup       # register with every detected client: Claude Code, Codex, opencode, Grok Build, Cursor

Keep the local coding-agent CLIs current so newly released models and effort levels are available:

sema update --check              # show installed Claude/Codex/opencode versions
sema update                      # run every installed agent's official updater
sema update --provider codex     # update one agent only (repeatable)

The extension exposes the same workflow under Manage → Update agent CLIs…. Reload VS Code after an update so its model picker reflects the installed CLI.

Want just the extension or just the index? Both work standalone. Plus manual installs, requirements, and troubleshooting — for more details see the Installation guide.

4. Or skip the editor entirely — sema chat is a full coding agent in your terminal, with the same modes, providers, and tools as the extension:

uv sync --extra chat      # or: pip install 'sema-mcp[chat]'
sema chat                 # interactive TUI
sema chat --print "where is auth handled?"   # one-shot, for scripts

Sessions are shared with the VS Code extension, so a conversation started in the editor resumes in the terminal and back. Terminal app guide →

📦 sema-mcp on PyPI · 🧩 Extension on the VS Code Marketplace

Why

Cursor is great — it's also a subscription and a walled garden. Claude Code and Codex are great too, but they lock you to one model per session, and they start every session cold: burn tokens just navigating before they answer anything.

Sema indexes your code once, locally. Your assistant searches it instead — typically 4–11× fewer tokens per question. And check_reuse() tells it whether a helper already exists before it writes a fourth one.

Why sema exists, in full → · Benchmarks →

Documentation

Start here: Installation · sema for VS Code · CLI reference

License

MIT — see LICENSE. Copyright (c) 2026 Masih Moloodian.

Masih Moloodian · masihmoloodian@gmail.com · Issues