什么是 io.github.ldclabs/KIP?
基于 Knowledge Graphs 的能力组件,用于实现持久记忆、知识演化与可解释交互。
README
🧬 KIP (Knowledge Interaction Protocol)
<p align="center"> <em>A graph-oriented interaction protocol designed specifically for Large Language Models,<br/>bridging the gap between LLM and Knowledge Graph.</em> </p>What is KIP?
KIP (Knowledge Interaction Protocol) is a standard interaction protocol that bridges the gap between LLM (Probabilistic Reasoning Engine) and Knowledge Graph (Deterministic Knowledge Base). It is not merely a database interface, but a set of memory and cognitive operation primitives designed specifically for intelligent agents.
Large Language Models (LLMs) have demonstrated remarkable capabilities in general reasoning and generation. However, their "Stateless" essence results in a lack of long-term memory, while their probability-based generation mechanism often leads to uncontrollable "hallucinations" and knowledge obsolescence.
KIP was born to solve this problem through Neuro-Symbolic AI approach.
Key Benefits
- 🧠 Memory Persistence: Transform conversations, observations, and reasoning results into structured "Knowledge Capsules"
- 📈 Knowledge Evolution: Complete CRUD and metadata management for autonomous learning and error correction
- 🔍 Explainable Interaction: Make every answer traceable and every decision logically transparent
- ⚡ LLM-Optimized: Protocol syntax optimized for Transformer architectures with native JSON structures
Quick Start
// Query: Find all drugs that treat headache
FIND(?drug.name)
WHERE {
?drug {type: "Drug"}
(?drug, "treats", {name: "Headache"})
}
LIMIT 10
// Store: Create a new knowledge capsule
UPSERT {
CONCEPT ?aspirin {
{type: "Drug", name: "Aspirin"}
SET ATTRIBUTES { molecular_formula: "C9H8O4", risk_level: 2 }
SET PROPOSITIONS { ("treats", {type: "Symptom", name: "Headache"}) }
}
}
WITH METADATA { source: "FDA", confidence: 0.95 }
// Explore: Discover schema
DESCRIBE PRIMER
Documentation
| Document | Description |
|---|---|
| 📖 Specification | Complete KIP protocol specification (English) |
| 📖 规范文档 | 完整的 KIP 协议规范 (中文) |
| 🤖 Agent Instructions | Operational guide for AI agents using KIP |
| ⚙️ System Instructions | System-level maintenance and hygiene guide |
| 📋 Function Definition | execute_kip function schema for LLM integration |
Core Concepts
Cognitive Nexus
A knowledge graph composed of Concept Nodes and Proposition Links, serving as the AI Agent's unified memory brain.
graph LR
subgraph "Cognitive Nexus"
A[Drug: Aspirin] -->|treats| B[Symptom: Headache]
A -->|is_class_of| C[DrugClass: NSAID]
A -->|has_side_effect| D[Symptom: Stomach Upset]
end
KIP Instruction Sets
| Instruction Set | Purpose | Examples |
|---|---|---|
| KQL (Query) | Knowledge retrieval and reasoning | FIND, WHERE, FILTER |
| KML (Manipulation) | Knowledge evolution and learning | UPSERT, DELETE |
| META (Discovery) | Schema exploration and grounding | DESCRIBE, SEARCH |
Schema Bootstrapping
KIP uses a self-describing schema where type definitions are stored within the graph itself:
$ConceptType: Meta-type for defining concept node types$PropositionType: Meta-type for defining proposition predicatesDomain: Organizational units for knowledge
Resources
This repository includes ready-to-use resources for building KIP-powered AI agents:
📦 Knowledge Capsules (capsules/)
Pre-built knowledge capsules for bootstrapping your Cognitive Nexus:
| Capsule | Description |
|---|---|
| Genesis.kip | Foundational capsule that bootstraps the entire type system |
| Person.kip | Person concept type for actors (AI, Human, Organization) |
| Event.kip | Event concept type for episodic memory |
| persons/self.kip | The $self concept instance |
| persons/system.kip | The $system concept instances |
🧠 Hippocampus (hippocampus/)
A dedicated LLM layer that manages the Cognitive Nexus on behalf of business agents — no KIP knowledge required:
| File | Description |
|---|---|
| HippocampusFormation.md | System prompt for memory encoding (messages → structured knowledge) |
| HippocampusRecall.md | System prompt for memory retrieval (natural language → KIP → answer) |
| HippocampusMaintenance.md | System prompt for memory maintenance (sleep mode) |
| RecallFunctionDefinition.json | recall_memory function schema for business agent integration |
┌─────────────────────┐
│ Business Agent │ ← No KIP knowledge needed
└────────┬────────────┘
│ Natural Language
▼
┌─────────────────────┐
│ Hippocampus │ ← Formation / Recall / Maintenance
└────────┬────────────┘
│ KIP (KQL/KML/META)
▼
┌─────────────────────┐
│ Cognitive Nexus │ ← Persistent Knowledge Graph
└─────────────────────┘
🔌 MCP Server (mcp/)
kip-mcp-server - Model Context Protocol server that exposes KIP tools over stdio:
- Tools:
execute_kip,list_logs - Resources:
kip://docs/SelfInstructions.md,kip://docs/KIPSyntax.md - Prompt:
kip_bootstrapfor ready-to-inject system prompt
🎯 Agent Skills (skill/)
kip-cognitive-nexus - Publishable skill for AI agents:
- Python client script for
anda_cognitive_nexus_server - Complete syntax reference and agent workflow guide
Implementations
| Project | Description |
|---|---|
| Anda KIP SDK | Rust SDK for building AI knowledge memory systems |
| Anda Cognitive Nexus | Rust implementation of KIP based on Anda DB |
| Anda Hippocampus | Autonomous Graph Memory for AI Agents |
| Anda Cognitive Nexus Python | Python binding for Anda Cognitive Nexus |
| Anda Cognitive Nexus HTTP Server | An Rust-based HTTP server that exposes KIP via a small JSON-RPC API (GET /, POST /kip) |
| Anda App | AI Agent client app based on KIP |
Version History
| Version | Date | Changes |
|---|---|---|
| v1.0-RC5 | 2026-03-25 | v1.0 Release Candidate 5: Added execute_kip_readonly interface |
| v1.0-RC4 | 2026-03-09 | v1.0 Release Candidate 4: Added IN, IS_NULL, IS_NOT_NULL FILTER operators; clarified UNION variable scope semantics; defined batch response structure; added temporal and UNION query examples |
| v1.0-RC3 | 2026-01-09 | v1.0 Release Candidate 3:Optimized documentation; optimized instructions; optimized knowledge capsules |
| ... | ... | ... |
| v1.0-draft1 | 2025-06-09 | Initial Draft |
About Us
- 🔔 Products: Anda.AI | 天策 Celestian
- 💻 GitHub: LDC Labs
- 🏢 Company: Yiwen AI
License
Copyright © 2025 LDC Labs.
Licensed under the MIT License. See LICENSE for details.
常见问题
io.github.ldclabs/KIP 是什么?
基于 Knowledge Graphs 的能力组件,用于实现持久记忆、知识演化与可解释交互。
相关 Skills
前端设计
by anthropics
面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。
✎ 想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。
网页构建器
by anthropics
面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。
✎ 在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。
网页应用测试
by anthropics
用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。
✎ 借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。
相关 MCP Server
GitHub
编辑精选by GitHub
GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。
✎ 这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。
Context7 文档查询
编辑精选by Context7
Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。
✎ 它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。
by tldraw
tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。
✎ 这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。