by kage-core · MCP Server · ★ 23
Kage Verified repo knowledge for coding agents Every claim is cited against your current code — and you see exactly what it saves you. Kage rejects memory that cites files that don't exist, withholds memory whose evidence was deleted, and warns you the moment your changes invalidate what your team knows. Plain files in your repo, reviewed in the same PR as the code. No API key, no database, no daemon. Website · Docs · Viewer · npm · Book a demo 🌐 English · 简体中文 · 日本語 · 한국어 · Español · [Português (Brasil)](transl
| Stars | 23 |
| Forks | 1 |
| Language | TypeScript |
| Category | MCP Server |
| License | GPL-3.0 |
| Quality Score | 64.1019072703781/100 |
| Open Issues | 7 |
| Last Updated | 2026-07-06 |
| Created | 2025-07-19 |
| Platforms | claude-code, codex, mcp, node |
| Est. Tokens | ~16k |
These tools work well together with Kage for enhanced workflows:
Explore other popular mcp server tools:
Kage is Persistent, verified memory for coding agents — so they stop re-explaining your codebase and never act on stale knowledge. Every memory is checked against your actual code; lives in your repo as plain. It is categorized as a MCP Server with 23 GitHub stars.
Kage is primarily written in TypeScript. It covers topics such as agent-memory, ai-agents, claude-code.
You can find installation instructions and usage details in the Kage GitHub repository at github.com/kage-core/Kage. The project has 23 stars and 1 forks, indicating an active community.
Kage is released under the GPL-3.0 license, making it free to use and modify according to the license terms.