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.

Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph eviction (0-LLM) + byte-exact recall from an append-only log

Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.

Model-controlled context blocks for DeepSeek Harness PTC mode

Session handoffs for Claude Code: skills that capture decisions, failed approaches and next steps, plus a Claude Code mod (/compact-handoff) that replaces the conversation with a validated handoff and keeps going. A better /compact.

Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.

The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.

Deterministic Unit-Record Memory Engine for AI coding agents. Eliminates context-window amnesia and compaction bloat via zero-turn workspace hydration, byte-exact registers, and live context telemetry.

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

Topic-based automatic memory for Claude Code — never lose context across sessions or compactions.