fgm-builds/dashr

README excerpt

Dashr: RLM Plugin for DSH ⚡ Quick Install Alternative: DSH Plugin CLI (NPM) After installation, launch dsh web and select the RLM Mode agent preset. 📖 Overview DeepSeek Harness ( dsh ): Everything is a plugin (Cordis framework). Prime Agent: Context is variable (RLM paradigm). Why not both? That's dsh in RLM mode — that's Dashr . Dashr is an open-source plugin for the DeepSeek Harness ( dsh ) agent runtime. It brings RLM (Recursive Language Models) and the "Context is Variable" paradigm to dsh , registering a dedicated rlm-mode agent preset upon installation. Instead of paying massive token costs on every round-trip tool call in standard multi-turn chat, Dashr equips the agent with a stateful, persistent Python kernel . The agent writes self-contained Python programs per cell, manipulating context, tools, and memory as native variables. 💡 RLM Reference: arXiv:2512.24601 1. Context is Variable (Stateful Kernel) In standard agent loops, reading large files or computing complex payloads dumps raw output directly into the conversation history. In Dashr: - State and computation persist inside a live IPython kernel session. - Intermediate variables survive across cells without re-enter…

Category