yantrikos/yantrikdb-server

本页由 AI 翻译，技术细节请以原文为准。查看原文

177 stars 14 forks 质量 84 趋势 58Apache-2.0

Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, Apache-2.0, ships as library / MCP server / HTTP cluster.

概览

⚠ Phase 3 benchmark writeups committed earlier today (docs/phase3a/, docs/phase3b/, docs/phase3c/, docs/phase3d/) used a Python simulator for the "structured memory" condition — NOT the actual yantrikdb engine. Rerun with real yantrikdb is in docs/phase3e/. Full audit trail, preliminary corrected numbers, and the exact publication gate for a findings post are in CORRECTIONS.md. Vector databases store memories. They don't manage them. After 10,000 memories, recall quality degrades because there's no consolidation, no forgetting, no conflict resolution. Your AI agent just gets noisier. YantrikDB is different. It's a — embed it, run it as a server, or connect via MCP. It thinks about what it stores. MCP setup for Claude Code / Cursor / Windsurf → (one pip install, one config block). YantrikDB is the memory layer being built on the road to YantrikOS — an AI-native operating system where agents are first-class primitives, not apps on top.

README

以下为原文 README 节选，完整内容请查看原文。

YantrikDB

⚠ Correction notice (2026-04-19): Phase 3 benchmark writeups committed earlier today (docs/phase3a/, docs/phase3b/, docs/phase3c/, docs/phase3d/) used a Python simulator for the “structured memory” condition — NOT the actual yantrikdb engine. Rerun with real yantrikdb is in docs/phase3e/. Full audit trail, preliminary corrected numbers, and the exact publication gate for a findings post are in CORRECTIONS.md.

A memory database that forgets, consolidates, and detects contradictions.

Vector databases store memories. They don’t manage them. After 10,000 memories, recall quality degrades because there’s no consolidation, no forgetting, no conflict resolution. Your AI agent just gets noisier.

YantrikDB is different. It’s a cognitive memory engine — embed it, run it as a server, or connect via MCP. It thinks about what it stores.

Shortest path to try it: MCP setup for Claude Code / Cursor / Windsurf → (one pip install, one config block).

The bigger picture: YantrikDB is the memory layer being built on the road to YantrikOS — an AI-native operating system where agents are first-class primitives, not apps on top. Memory was the bottleneck, so we’re shipping it first.

📄 New paper (May 2026): Skill as Memory, Not Document — measuring three failure modes when agent skill catalogs scale to 5,000 skills. Code + raw CSVs reproducible in benchmarks/skill_recall/.

99.9% token savings vs file-based memory

Memories	File-Based (CLAUDE.md)	YantrikDB	Token Savings	Recall Precision
100	1,770 tokens	69 tokens	96%	66%
500	9,807 tokens	72 tokens	99.3%	77%
1,000	19,988 tokens	72 tokens	99.6%	84%
5,000	101,739 tokens	53 tokens	99.9%	88%

At 500 memories, file-based memory exceeds 32K context. At 5,000, it doesn’t fit in any model — not even 200K. YantrikDB stays at ~70 tokens per query. Precision improves with more data — the opposite of context stuffing.

在 GitHub 查看完整 README

安装

docker run -p 7438:7438 ghcr.io/yantrikos/yantrikdb:latest

配置

{
  "mcpServers": {
    "yantrikdb": {
      "command": "yantrikdb-mcp"
    }
  }
}