ranxianglei/opencode-acp

Dynamic context pruning plugin for OpenCode - intelligently manages conversation context to optimize token usage

A context-compression plugin for small context windows (a 100K context is enough), token savings (5x fewer tokens), and month-long single sessions (billions of tokens).上下文压缩插件，兼顾小窗口(100k上下文足矣)省token(省5倍token)和超长会话(数月级别几十亿token单会话)。billion-context is all you need

稳定可用 Use billion-context instead .Active Context Pruning for pi ，100K tokens is enough. ，主动压缩上下文，10w 上下文足矣

Context cleaning for Claude Code — prune bloated sessions, protect Agent Teams from context loss, auto-guard with tiered pruning

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

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.

Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.

Lossless context compression plugin for Claude Code & OpenCode.

Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.