context-management

context-attachment-manager

+208

Long image chats in Codex and Claude, without the lag. The model manages its own images, pulling back only what it needs, and any image you made before is one search away: just describe what you remember.

ragflow

+429

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

dsh-mnemon

+124

Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.

Tianshu-harness

+75

天枢harness是一个的终端编程智能体，它要回答的核心问题是：模型何以稳定地交付——目标不漂移、完成有证据、验证有闭环，不说"应该修好了"。为此它在模型与真实世界之间建立一层认知执行环境（CVM），把目标、状态、证据、资源、权限与终止条件从对话历史中外部化，由运行时持续管理。同时对deepseek v4极度优化。

datahub

+51

The Context Platform for your Data and AI Stack

magic-context

+37

Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.

VCPToolBox

+19

VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。

intentional-arrangement-skos

+5

Build, validate, visualize, and publish SKOS taxonomies in your browser — standards-first, single self-contained file, with a REST API and MCP server.

billion-context-dsh

+5

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.