context-mode

Context-window optimization layer that sandboxes tool output before it reaches the model (claimed 98% reduction) and persists session memory across 17 agent platforms via MCP and hooks—progressive disclosure applied to tool results, not just instructions.

mcpmemorysandbox

Stars: 33.1k
Adoption surface: mostly simple
Autonomy: n/a
Recovery: n/a
License: ⚠️ Elastic-2.0 restricted (Elastic-2.0)
Category: Progressive disclosure harnesses

Repository ↗ Example: Project README ↗

Related in Progressive disclosure harnesses

Headroom
awesome-cursorrules
agents.md
langgraph-bigtool
MCP-Zero
ToolGen

Maintain context-mode? Add the badge

Paste this into your README so readers can find the list and see how context-mode compares:

[![Best of Agent Harnesses](https://img.shields.io/badge/%F0%9F%8F%86_Best_of-Agent_Harnesses-5ac4bf)](https://github.com/RyanAlberts/best-of-Agent-Harnesses)