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.
411 entries
kdeps command: thorough
Maximizes context retention: compacts and folds much less often, injects far more memory context, keeps more of every tool result, and allows larger tool-call budgets. Best for long research/investigation sessions where losing history hurts quality more than the extra tokens cost.
kdeps provider: together
kdeps harness: tool-call-early-praise
kdeps harness: tool-call-recovery-praise
kdeps harness: tool-call-sandbox-recovery-praise
kdeps event: tool-error-truncate
kdeps event: tool-result-truncate
kdeps command: tools
kdeps harness: tools
kdeps harness: tools-reminder
kdeps kdeps-component: transcribe
kdeps kdeps-component: transcribe_audio
Transcribe an audio or video file to text through a Whisper API: openai (default), groq, or local (a self-hosted OpenAI-compatible Whisper server). Supports mp3, mp4, mpeg, mpga, m4a, wav, webm. Returns the transcribed text. For offline transcription with no API key use transcribe_audio_offline.
kdeps kdeps-component: transcribe_audio_offline
Transcribe an audio file to text offline with whisper.cpp (whisper-cli): no API key, no network. Supports flac, mp3, ogg, wav. Uses the GGML model at modelPath, or ggml-base.en.bin in the kdeps models dir. The model is not downloaded: place the GGML file there first. Returns the transcribed text.
kdeps event: trivial-prompt-max
kdeps event: trivial-prompt-short
Shorten oversized content to a size budget, appending a marker noting what was cut, instead of refusing the operation outright.
kdeps event: tui-activity-lines
kdeps command: turo
kdeps kdeps-component: twiml
kdeps tool: twiml
kdeps event: unproductive-rounds
kdeps command: update
kdeps command: upgrade
kdeps harness: use-kdeps-tools
kdeps schema: v1
kdeps kdeps-component: vector_store
Run one vector store operation against an external vector database: add_documents to upsert documents, or similarity_search to query them. Call it through the vector_store component. Requires: collection, operation, embedModel (except bedrock). Optional: provider, url, apiKey, documents, query, topK, embedBackend, embedBaseURL.