Index your codebase to save 94% on AI coding tokens by enabling agents to search instead of reading files.
code-context-engine is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view elara-labs/code-context-engine --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
Code Context Engine creates a searchable index of your codebase so AI coding assistants can find relevant code instantly without reading every file. This reduces the number of tokens sent to the AI, saving you up to 94% on costs. It works locally, keeps your code private, and integrates with popular tools like Claude Code, Cursor, and VS Code.
Code Context Engine (CCE) is an open-source, local MCP server that indexes your codebase and allows AI coding agents to search for relevant code context instead of reading entire files. By providing a semantic and keyword search over your code, CCE dramatically reduces the number of input tokens consumed by AI assistants, leading to up to 94% token savings as benchmarked on real-world codebases like FastAPI. CCE runs entirely on your machine with no cloud dependency, ensuring code privacy. It auto-detects your editor and works with multiple AI coding tools including Claude Code, Codex CLI, GitHub Copilot, Cursor, Gemini CLI, and more. The tool is free, MIT-licensed, and requires minimal setup—just one command to start indexing. It also supports cross-session memory, multi-editor teams, and faster response times by reducing context size.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 65 days ago.
151 GitHub stars indicate community interest.
17 open issues signal maintenance load.
MIT license detected.
Reduce Claude Code costs by 94% through fewer input tokens per session.
Keep code private with fully local indexing, no cloud uploads.
Enable multi-editor teams to share a single index across Claude Code, Cursor, VS Code, and Gemini CLI.
Maintain cross-session memory so decisions and context survive restarts.
Speed up AI responses by providing less context to the model.
151
Stars
17
Forks
17
Issues
MIT
License
Local codebase intelligence CLI and MCP server for AI coding agents with change-safety gates and audit evidence.
An offline MCP server that indexes your codebase for semantic search, code search, and git history retrieval.
Official MCP reference servers from Anthropic. Includes servers for filesystem, GitHub, Postgres, Slack, and more.
Index your codebase to save 94% on AI coding tokens by enabling agents to search instead of reading files.
Developers using AI coding assistants who want to reduce token costs., Teams working with multiple AI coding tools who need a unified code context., Privacy-conscious developers who require local-only code indexing.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Review repository permissions, executed commands, data sent to external services, and dependencies before use.
Similar or complementary options to evaluate include roam-code, code-memory, MCP Server Collection.
Jun 6, 2026
0 security/trust notes recorded.
Setup difficulty is 1/5.