14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.

Portable CC-inspired skills for memory, verification, multi-agent coordination, context compression, and proactive coding-agent workflows.

The official repo for "LLoCo: Learning Long Contexts Offline"

97% token reduction for AI coding sessions — zero deps, 21 languages, MCP server

Pytorch implementation for "Compressed Context Memory For Online Language Model Interaction" (ICLR'24)

Context compression plugin for Claude Code. Trims large JSON, logs, stack traces, and source files before they enter the context window.

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

🦞 LobsterPress（龙虾饼） - Cognitive Memory System for AI Agents 基于认知科学的 LLM 永久记忆引擎

Stop re-explaining your codebase to AI. Infinite speed memory + code graph for Claude Code & Codex CLI. 17 MCP tools, subagent protocol, hybrid search, TUI dashboard, crash recovery. Save 80-200K+ tokens/session.

Local-first context compression for AI coding tools. One binary saves 85-93% of redundant tokens across every LLM call.

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.

A drop-in proxy that falls back to local Ollama when any LLM quota runs out

Squeeze verbose LLM agent tool output down to only the relevant lines

Rolling context compression for Claude Code — never hit the context wall. Auto-compresses old messages while keeping recent context verbatim. Zero config, zero latency. Works as a Claude Code plugin.

Biological code organization system with 1,029+ production-ready snippets - 95% token reduction for Claude/GPT with AI-powered discovery & offline packs

🌶️ OpenClaw skill that reduces token consumption by 30-60% through context compression and smart optimization

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflows. SQLite + FTS5 compact context packs, token savings, read-only mode, no external memory server.

Cursor uses AI to edit code — we use AI to edit AI's context. 🪆 Context map + compression + version control for LLM context windows.

Coding agents forget your repo. mcp-brain is the missing memory layer — repo-aware, team-aware, lifecycle-aware. 63% Hit@10, zero LLM cost. Works with any MCP client.

Awesome list of paper on vision-based context compression