Aggressive context compaction for local-first agents. Runs Qwen3.8‑27B on self‑hosted llama.cpp at low context, shrinking history so the live prompt stays small, fast, and private—delivering a big‑window experience without API cost or data egress. 面向本地的激进上下文压缩插件。自托管 llama.cpp 低上下文运行 Qwen3.8‑27B,不断收缩历史、保持常驻 prompt 小而快,兼顾隐私与大窗口体验,零 API 成本、数据不出本机。
Role-based multi-agent expert team for DeepSeek Harness: one sentence in, a staged and gated team delivery out. 12 role subagents, 9 gated phases, shared-workspace artifacts, zero runtime dependencies.
Self-evolving memory + skill lifecycle for DeepSeek Harness — durable cross-session memory with zero-token deterministic recall, tiered approval, reinforcement learning from repetition, and anti-bloat convergence for both skills and memory.
File-based cross-session memory for DeepSeek Harness (DSH) — every memory is a plain Markdown file. 纯 Markdown 存储,无数据库、无 worker、无端口;从 Claude Code 无损迁移记忆与人格,带记忆星图与可选的记忆整理。
Archived-session manager for DSH Web UI: reopen an archived session and keep chatting, unarchive it back in place, or hard-delete a session — grouped panel with message search and native view sync.
Session manager for the DeepSeek Harness web UI: move, archive, restore, backup/export and import conversations across workspaces. Trilingual (English / 简体 / 繁體).