Browse
Installable packages, the resource types built into kdeps, and the versioned assets kdeps runs on, in one catalog. The colored badge on each entry says which kind it is.
270 entries
kdeps harness: honesty
The `httpClient:` resource makes an outbound HTTP request and stores the parsed response body as its output. JSON responses are parsed automatically; other content types are stored as a string.
Make an HTTP request to a URL. Returns response status, headers, and body. Use for calling APIs, fetching web content, or interacting with external services. Requires: url. Optional: method (default GET), headers, data (JSON body), timeout.
kdeps provider: huggingface
kdeps event: identical-tool-calls
Return this agent's configured identity: name, email, and mailing address. Use this to answer questions about who you are, or to sign outputs (commits, emails) as this agent. Never returns credentials.
kdeps dockerfile: image
kdeps command: instruct
kdeps command: instruct-now
kdeps harness: internals
kdeps harness: invoke-example
Rerank a list of documents by relevance to a query using Jina AI's reranking API. Requires JINA_API_KEY.
kdeps event: judge-iterations
kdeps event: judge-max-rounds
kdeps harness: judge-roster-system
kdeps harness: judge-system
Settle your review of the candidate output. Must be called exactly once, when your review is complete.
kdeps command: judges
kdeps command: kartographer
kdeps manifest: manifests
kdeps command: konfig
kdeps theme: linux
List files and directories in a given directory path. Returns names and types (file/dir). Use to discover project structure before reading or editing files. Omit path to list the current working directory.
llama.cpp llama-server serving GGUF weights over OpenAI-compatible /v1
Official llama.cpp server image (OpenAI-compatible /v1) for GGUF
kdeps model: llamafile
Self-contained .llamafile binary serving OpenAI-compatible /v1
Load a document file and return its content as text. Supports PDF (go-pdf, pdftotext, pdfcpu), DOCX/EPUB/RTF/ODT (pandoc), HTML (goquery, lynx), CSV, text, directory, notion, markdown (textutil). Use for reading documents into the conversation for analysis or RAG pipelines. Returns document content with optional splitting into chunks. Requires: source (absolute file path). Optional: type (pdf, csv, html, text — auto-detected from extension), chunkSize (split into chunks of N characters).
Load the full instructions for a named skill. Call this when the user's task matches one of the skills listed in <available_skills>. Returns the skill's complete instructions to follow.
The `loader:` resource reads a file, URL, or directory into structured `Document` objects - plain text plus metadata - and optionally splits them into chunks. It is the ingestion step of a RAG pipeline: load, then feed the output into `vectorStore:` or `embedding:` for indexing.