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.
Turn your devices into a fleet — dsh plugin for decentralized multi-device collaboration: mDNS discovery, key pairing, SSH direct exec. Tools auto-register for dsh agents.
Memory ecosystem bridging the DeepSeek web app and local DSH — one local memory pool shared by a browser extension (harvest/inject), a zero-dependency local service (sole writer), and a DSH adapter (pre-step injection).
Claude Code-style @path imports for DeepSeek Harness: expands @imports in AGENTS.md/CLAUDE.md and injects referenced files into context at session start
A model-native meta-agent plugin for DeepSeek Harness that uses the underlying model’s reasoning and planning capabilities to synthesize task-specific workflows at runtime and coordinate tools and subagents.
dsh plugin: run work as a small crew of role agents (product manager, researcher, architect, engineer, QA, code reviewer, security reviewer, doc reviewer) that share work through files on disk
