An AI text generation tool for EditorJS with automatic environment variable detection

Open AI text tool for Editor.js

Model-facing web tools (web_search, web_fetch) over the DeepSeek Harness web capability seam (ctx.web)

Replay-safe model-free head/middle/tail pruning for tool-result surface nodes

Abstract filesystem capability seam (ctx.fs) for the DeepSeek Harness — vocabulary types, the FileSystem service (text IO + optional version-guarded atomic mutations), and the fs/* policy event vocabulary

Token-meter-driven compaction policy and LLM summarization backend for the DeepSeek Harness

Unified LLM API with automatic model discovery and provider configuration

The **[Groq provider](https://ai-sdk.dev/providers/ai-sdk-providers/groq)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the Groq chat and completion APIs, transcription support, and browser search tool.

Detect if code is running in an AI agent or automated development environment

Tool-result spill policy for the DeepSeek Harness — replaces oversized plain-text tool results with a retained preview plus a spill-file path (no service surface)

Model-facing fresh-agent Ralph loop over the workflow and subagent seams

Model-facing ask_user_question tool over the ctx.userInteraction seam

Model-facing view, create, literal replace, and line insert tool over the Harness filesystem service

Produced-files turn tail: the deliverables row a finished turn ends with

File-context policy plugin for the DeepSeek Harness — observed-state, read-before-edit, and version-guarded write/edit added over the ctx.fs provider seam through the fs/* event gate (no service API)

Model-facing subagent delegation tool over the ctx.subagents seam

Abstract spill storage seam (ctx.spillStore) for the DeepSeek Harness — save oversized tool text and return a retrieval locator

Sandbox-enforcing implementation of the DeepSeek Harness filesystem seam: fences write/edit by the per-call sandbox mode (read-only denies mutation, workspace-write contains it to the workspace + temp roots) while reads pass through

SAP AI Provider for Vercel AI SDK (powered by @sap-ai-sdk/orchestration and @sap-ai-sdk/foundation-models)

The shared dsh core as a profile bundle: every profile's first patch layer, inserting the base plugin rows over the empty profile root