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。
A DeepSeek Harness (dsh) bundle that shows OpenCode Go subscription usage in the Web GUI's composer dock — the same seat as the built-in conversation stats line.
Isolated install-and-smoke test drives for DeepSeek Harness plugins: installs a repo or npm package into a throwaway DSH_HOME profile, verifies the bundle patch layer and boot logs, records a structured pass/fail result matrix (JSON/Markdown) for scoring pipelines, and quarantines every temp directory it owns
A Command Code LLM provider plugin for DeepSeek Harness (dsh) — supporting all subscription plans (incl. Go & Pro) via Studio API / gateway.专为 DeepSeek Harness (dsh) 打造的 Command Code LLM 接入插件，全面支持包括 Go/Pro 在内的各类订阅方案。
DeepSeek Harness QoL plugin for the local Qwen3.8 line (27B/Flash-Next): per-request thinking budgets, a compaction backend that stops burning the output cap on thinking, and a settings tab. 本地 Qwen3.8 线的 DSH QoL 插件：逐请求 thinking 预算、不再把输出帽烧在 thinking 上的压缩后端、设置 tab。
Evoflux is an open-source, local-first workspace where AI agents build software, conduct deep research, automate browser tasks, and collaborate in parallel. Connect any model, keep control of your workspace and data, and take complex work from idea to completion—all in one place.
DeepSeek Harness (dsh) browser companion: Chrome side panel embedding the full dsh web UI + host plugins for page reading, HTTP capture, and browser control.
Self-evolve memory plugin for DeepSeek Harness: learns from your own sessions, injects token-budgeted preference summaries into every step. /memory commands, memory tool, settings panel. Local-only data.
Unified static-image generation router for DeepSeek Harness: one image_generate tool with standard parameters, config-driven engine routing (OpenAI Images, Zhipu CogView, and any compatible endpoint) with health-aware fallback, durable workspace attachments, per-session quota accounting, and a Plugins settings panel
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.
