macOS and Linux
Downloads the latest stable release and installs it in a user-owned path.
curl -fsSL https://context-engine.app/install.sh | shCommunity Preview
Choose your platform, run one command, and connect your coding agent to the live semantics of your codebase.
Install
Downloads the latest stable release and installs it in a user-owned path.
curl -fsSL https://context-engine.app/install.sh | shDownloads the latest stable release and installs it for the current user.
irm https://context-engine.app/install.ps1 | iexInstall and update Context Engine through Homebrew or Scoop.
Install Context Engine from the organization-owned tap.
brew install context-engine-app/tap/context-engineAdd the organization-owned bucket and install Context Engine.
scoop bucket add context-engine https://github.com/context-engine-app/scoop-bucket
scoop install context-engine/context-engineActivate
Create a free key, then expose it to Context Engine in your shell. Keep it private and never commit it to a workspace.
Get free API keyexport CONTEXT_ENGINE_API_KEY="<your key>"$env:CONTEXT_ENGINE_API_KEY = "<your key>"Verify
Run the license check from a new terminal after setting your API key.
context-engine license-checkGuide your agent
After connecting Context Engine, copy this into AGENTS.md, CLAUDE.md, GEMINI.md, or the equivalent file your coding agent reads. Its built-in tools remain available.
## Context Engine
Use Context Engine as the primary way to understand and navigate the codebase. Prefer it over broad text search or reading entire files.
Choose the tool based on what you know:
- Exact file and line: use `line_context`.
- Visible call, method, type, or constructor: use `jump`.
- Full or partial symbol name without a location: use `grep_definition` (add a glob for partial names).
- Known file: use `outline`. If the outline is insufficient, use `extract` only on the required handles.
- References, callers, or change impact: use `show_usage`.
- Type, signature, parameter names, or documentation at a known location: use `hover`.
- Exact line range when no semantic tool fits: use `smart_read`.
Batch related requests when a tool accepts multiple files, symbols, handles, or locations. This reduces tool calls and saves tokens.
Use narrow text search only for arbitrary text such as strings, comments, configuration values, or expressions. Inspect relevant search hits with `line_context` before tracing further.
Use `type_annotated` output by default. Use `plain_text` or `both` only when editing requires exact source text.
Never guess dependency APIs. Resolve visible dependency symbols with `jump`.
If Context Engine returns the answer, do not repeat the same investigation with built-in tools.Next step