billion-context-dsh
Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.
DeepSeek Harness 的模型驱动上下文管理（主动上下文剪枝 / ACP）——模型决定何时及压缩什么。从 billion-context-pi (ranxianglei) 移植；acp-kernel 原样复用。CompactionEngine 后端，提供 compress/decompress/search_context/acp_status 工具。
How to install
dsh plugin add billion-context-dsh Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 12
- mo. downloads
- –
- Last push
- 2026-08-15
- Created
- 2026-08-13
Basic safety check
- Findings
- None
- Sources
- curated:0xsline/awesome-deepseek-harness
- Topics
- acp, billion-context, context-management, dsh-plugin
Related plugins
ruflo
ruvnet/claude-flow
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
sandbase-harness
sandbaseai/sandbase-harness
Open-source CMA-compatible agent runtime for any model, with MCP tools, sandboxed sessions, audit, replay, and a local console. Includes a native DeepSeek Harness bundle over stdio MCP.
modlens
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
pydantic-ai
pydantic/pydantic-ai
How Python does AI: agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.