context-compression

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

AI context optimization platform for files, conversations, RAG, code, logs and AI agents with context compression, evidence preservation, content-addressed recovery and auditable Context Receipts.

Stop paying to re-read the same output. OMNI turns repeated bytes into retrievable handles: 97.2% off a file your agent reads twice, 14.9% across 6,656 real commands. Nothing deleted, nothing invented, and every number replays on your own corpus.

Official Implementation for the ACL 2026 paper "SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression"

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

An effective and efficient coding-agent setup in under 30 seconds: best tools, unified instructions, any OS.

A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without losing what the model actually needs to know.

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

Context compression for MCP. Same upstream call, exact results recoverable.

Context compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, and logs—before it enters the context window.

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

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

Zed extension for Headroom — context compression for AI agents

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

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

⚡ 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.

Unified agent memory and context compression stack for 2026 NVIDIA + edge (Vera CPU, Grace, Jetson Thor, 3090). Glues busyBee-cpu, honey-comb, and rust-brain. Better effective reasoning per token.

Convert long AI conversations into portable conversation state graphs for LLM handoffs.

LLM reliability layer -keeps agents alive with smart routing, context compaction, and local fallback

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.