TypeScript runtime for LLM agent graphs with bounded loops, live updates, isolated Git worktrees, and explicit integration. Framework-agnostic core, OpenAI-compatible runner, and plugins for Pi and DeepSeek Harness.
DSH plugin for agent-driven span compaction: compress chosen conversation spans into self-written checkpoints instead of the official head-anchored full-context sweep.
CDS 模式（Chen's DS）— a multi-agent development mode for DeepSeek Harness. You talk to one persona; it dispatches 56 personas that hand work to each other directly.
A structured multi-panelist review workflow for the DeepSeek Harness: N panelists score in isolated subagents, blind to each other; a chair reconciles disagreement by anchor match then Δ-level adjudication; an independent critic audits the process. Works for design, code, paper or project review.
RETIRED 2026-10-05 — the official DeepSeek Harness now ships the Agent Teams subsystem (dsh-experimental-agent-team). Use native Agent Teams, or a better-adopted alternative such as @nanmicoder/dsh-agent-teams.
Conversation history recall for DeepSeek Harness (DSH) — literal/fuzzy/semantic retrieval of every past conversation, fully local & offline. AI never forgets what you told it.
Generic stateless dialogue compression that mimics human memory. LLM conversations stay bounded forever — no session management, no context overflow. Ships a ready-to-use adapter for DeepSeek Harness (DSH).
