$ loading_
Provide offline dependency docs and API context to AI coding assistants.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "devenv-cache" yet — see the docs or source repo.
Use devenv-cache to look up the APIs of the SQLite-related dependency in this project and explain how to open a connection and run a simple query.
Returns relevant API context for the dependency and a sample explanation for connecting and querying.
I'm developing offline. Use devenv-cache to find the documentation for the HTTP client dependency in this project and summarize common request methods and parameter patterns.
Outputs key documentation points, common methods, and parameter usage patterns to support coding.
Before refactoring this code, use devenv-cache to read the related dependency API context, then identify calls that may be outdated or mismatched.
Provides more accurate refactoring suggestions or risk notes based on cached dependency docs and API information.
When internet access is unavailable or external requests should be minimized, developers can let AI read dependency docs and APIs from a local cache. This gives the model better context for coding, explanation, and completion.
In development workflows that frequently query dependency information, this MCP tool uses a local SQLite cache for low-latency access. It fits coding scenarios that need fast package docs and API lookups.
It is an MCP tool that provides a local SQLite cache of package documentation and APIs, allowing AI coding assistants to access dependency context offline. The original description also says access latency can be under 10ms.
It is useful when an AI coding assistant needs third-party dependency docs, API definitions, or contextual information, especially in offline or low-latency workflows. It is more about dependency knowledge access than code execution.
The provided material only says it uses a local SQLite cache and exposes capabilities via MCP, but it does not include installation steps or prerequisites. See the source repository for details.
Search and cite past engineering work from a local-first indexed memory.
Give AI full visibility into your local development environment for faster troubleshooting.
Build a persistent code cache for fast semantic lookup and lower token usage.
Crawl sites and repos into searchable Markdown for AI agents and local LLMs.
Build persistent code memory for cross-session analysis, search, and documentation.
Understand codebases with structural search, definition lookup, and git blame analysis.