$ loading_
Ingest whole repositories into a large context window for coding agents.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "ctxfeed" yet — see the docs or source repo.
Use ctxfeed to ingest the entire code repository, then summarize the system architecture, main modules, and their dependencies from full context.
An architecture overview, module descriptions, and dependency summary based on full repository context.
Use ctxfeed to place the whole repository into context, analyze the cross-file call chain related to this error, and identify the most likely places to modify.
A cross-file call-chain analysis with likely root causes and suggested edit locations.
Use ctxfeed to ingest the entire large repository first, then answer multiple questions about module boundaries, public interfaces, and refactoring risks while reusing existing context.
Consistent answers to multiple code questions while reusing the large shared context.
When developers inherit a large repository, they can use it to load the whole codebase into a large context so a coding agent can understand architecture and module relationships globally.
When standard tools can only read a few files, this local MCP server helps coding agents access full repository context and reduces analysis errors caused by partial information.
For multi-turn questions about the same repository, it is useful to ingest the repository once and keep reusing that context to reduce query costs.
It is a local MCP server that ingests an entire code repository into a large context window for coding agents. Its goal is to bypass file-count limits and reduce query costs.
The provided description says it uses the GLM-5.2 1M-token large context window. For other model or compatibility details, see the source repository.
It focuses on ingesting the entire repository at once rather than reading only a few files. That makes it better suited for coding-agent tasks that need global context and can help reduce query costs.
Analyze code structure and Git history while drastically reducing AI token usage.
Turn any LLM into a codebase expert with search, mapping, and security insights.
Read, edit, and refactor code precisely with AST-based, token-efficient operations.
Provides code context, memory, search, and AI tooling for developers.
Search your entire codebase and feed rich context to coding agents.
Gives AI coding agents a structural map of your repository fast.