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 event: file-read-limit
kdeps command: fold
kdeps event: fold
kdeps event: force-answer-digest
End the current tool-calling loop and force a final text answer from whatever was gathered, instead of letting the model keep spinning.
kdeps command: frugal
Minimizes token usage: compacts and folds history sooner, injects far less memory context, truncates tool output harder, and caps tool-call budgets tighter. Best for cost-sensitive sessions or a small-context- window local model.
kdeps model: gguf
Alias for llama-server — GGUF weights via llama.cpp OpenAI-compatible /v1
kdeps kdeps-component: git
kdeps command: goal
kdeps harness: goal-confirm-system
kdeps harness: goal-plan-system
Mark the ACTIVE task finished and advance to the next one. Call this as soon as the active task's objective is met. Pass the active task's id and a one-line summary of what was achieved.
Give up on the ACTIVE task and advance to the next one. Use this instead of retrying when the task cannot be completed, so the goal keeps moving. Pass the active task's id and the reason.
Create a Google AI server-side cached content entry from a text system prompt. Returns the cache name (e.g. 'cachedContents/xyz123') for use in chat: googleCachedContent. Only available when GOOGLE_API_KEY is set.
Delete a Google AI cached content entry by name. Only available when GOOGLE_API_KEY is set.
List all Google AI cached content entries. Returns a JSON array of cache names. Only available when GOOGLE_API_KEY is set.
kdeps provider: groq
kdeps command: handshake
kdeps harness: handshake
kdeps harness: handshake-ack
kdeps harness: handshake-evidence
kdeps harness: handshake-evidence-praise
kdeps harness: handshake-evidence-retry
kdeps event: handshake-timeout
kdeps command: harness
kdeps command: help
kdeps command: history
kdeps event: history-window-trim