Skip to content
| Marketplace
Sign in
Visual Studio Code>Programming Languages>InLine GhostingNew to Visual Studio Code? Get it now.
InLine Ghosting

InLine Ghosting

Preview

EVA

|
24 installs
| (0) | Free
High-quality, context-aware inline completions powered by Claude Sonnet through your existing Claude Code login.
Installation
Launch VS Code Quick Open (Ctrl+P), paste the following command, and press enter.
Copied to clipboard
More Info

InLine Ghosting

Repository-aware inline code completions for VS Code.

InLine Ghosting supports two completion lanes:

  • Local FIM lane for automatic low-latency ghost text through loopback backends such as Ollama, llama.cpp, or OpenAI-compatible local completion servers.
  • Cloud/manual lane through Claude Code and other CLI backends when you explicitly configure or invoke them.

The extension is independent and is not affiliated with Anthropic, GitHub, Microsoft, or Copilot.

Quick Start

For local automatic completions:

  1. Install a local backend such as Ollama or llama.cpp.
  2. Pull or run a base/FIM coding model, for example qwen2.5-coder:3b-base.
  3. Set wisp.backend to ollama, llamacpp, or auto.
  4. Keep wisp.privacyMode at localOnly if source context must stay on loopback.

For Claude CLI manual/cloud completions:

  1. Install Claude Code: npm install -g @anthropic-ai/claude-code.
  2. Run claude once and sign in.
  3. Set wisp.backend to claude.
  4. Use cloudManual privacy mode unless you intentionally want automatic cloud requests.

Open the control panel with Ctrl+Alt+G (Cmd+Alt+G on macOS). Use Ctrl+Alt+O to stop or resume automatic suggestions.

Current Capabilities

  • FIM-capable local backend path.
  • Backend/model selection and privacy mode controls.
  • Prefix-compatible radix cache and continuation reuse.
  • Recent edit context.
  • Lifecycle accounting for request/display/accept/reject paths.
  • Candidate ranking and cached candidate cycling with Alt+] / Alt+[.
  • Token-budgeted context sizing using a dependency-free estimator.
  • Language-aware multiline decisions for JavaScript, TypeScript, and Python.
  • Workspace trust and sensitive-path boundaries.

Still Experimental

The project is moving toward Copilot-like ghost text quality, but it does not claim exact Copilot parity. True streaming display, backend-generated multi-candidate responses, exact tokenizer budgets, partial-accept lifecycle hooks, parser-backed language adapters, and a larger comparative evaluation corpus are still tracked in docs/upgrade/.

Privacy and Usage

Local loopback backends are preferred for automatic suggestions. Non-local automatic dispatch is blocked unless wisp.privacyMode is set to cloudAutomatic.

Sensitive paths, dependency folders, VCS metadata, and common build outputs are excluded. Repository memory remains in RAM unless persistence is explicitly enabled.

Development

npm install
npm test
npm run package
  • Contact us
  • Jobs
  • Privacy
  • Manage cookies
  • Terms of use
  • Trademarks
  • Your Privacy Choices
  • Consumer Health Privacy
© 2026 Microsoft