v1.17.2 · MIT
One session. Two commands. Full team. Zero meetings.
v0.2.26 · MIT
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.
v0.1.6 · MIT
RDB durable session backend for DeepSeek Harness: implements both session-persistence and session-branch (rewind / retry / fork) providers.
v0.2.26 · MIT
Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.
— · Apache-2.0
AI-powered spec generation and review using multi-repo code graph intelligence for backend teams that ship to production.