Utopia开源企业世界模型

[开源分享] Utopia：开源 “企业世界模型” Utopia 把知识图谱、向量检索、本体管理和 AI 推理整合成一个可私有部署的完整产品，让企业把散落的文档沉淀成一张可审计、可回溯、可治理的知识...

[开源分享] Utopia：开源 “企业世界模型” Utopia 把知识图谱、向量检索、本体管理和 AI 推理整合成一个可私有部署的完整产品，让企业把散落的文档沉淀成一张可审计、可回溯、可治理的知识底座，供 AI Agent 和人来共同信任与使用。 开源地址： github.com/deeplethe/utop… 核心理念：双时态知识图谱 这是整个项目最区别于普通 RAG 系统和向量库的地方。传统系统只记录“当前知识是什么”；Utopia 记录两条时间线： · 世界时间（world time）：这件事在现实中何时为真； · 信念时间（belief time）：系统何时开始相信它。 当新证据修正旧认知时，旧版本事实不会被覆盖，只是被“关闭”并链接到新版本——每次修正都保留出处。落到企业场景就是：一个决策当时是基于什么证据、什么版本的认知做出的，可以完整回放。这直接指向合规审计和决策智能两个高价值场景。 核心流水线：从文档到知识图谱 1. 解析与分块（1200 字符、150 重叠），嵌入后文档立即可搜索； 2. 抽取：每个 chunk 一次 LLM 调用，产出实体提及和事实；关系写入前做签名检查，方向反了会自动纠正并标记 direction_corrected，纠正失败则丢弃并记录 11 种丢弃原因码； 3. 实体消歧：三阶段（精确名称/别名 → 嵌入相似度 → 模型裁决），两个阈值（0.55 归并、0.35 新建），偏向“宁可拆分不误合并”，合并可逆，进入人工审核队列； 4. 类型解析：由抽取线索 + 画像相似度 + 邻居投票两条路线取并集，自动改类型只允许在原子类树内，跨分类轴的纠正交给人； 5. 本体生长闭环：词表外（OOV）的术语保留原文成为“提案”，被确认后进入本体，再反馈给下一轮抽取； 6. 一致性检查与推理：公理检查只“报告不写入”；物化推理（传递性、对称性、逆关系等前向链）默认关闭，派生事实写入独立的 derived_facts 表，每个谓词上限 2 万条，断言事实永远优先于派生事实。 设计决策记录：这个项目最“成熟”的部分 docs/decisions/ 里有 26 篇架构决策记录，标题本身就反映了团队的思考深度，比如： · “没有类型”本身是一种类型（0009）、“没有关系”就是没有关系（0010）——拒绝为了图好看而填占位值； · 记录一句话不等于断言一个事实（0015）——记录待确认，防止抽取噪音直接污染图谱； · 矛盾指向上游（0017）——矛盾被视为数据质量信号而非简单报错； · 映射不是事实（0011）、本体是契约而非建议（0012）； · 审计员无需我们就能读懂（0020）——支持 RDF 导出，避免被供应商锁定。 Sumanth @Sumanth_077 Build AI agents on a time-aware knowledge graph! Utopia is an open-source knowledge system that turns documents, databases, and connected sources into a temporal graph your agents can reason over. Most RAG systems are optimized for one question: what is relevant right now? That works until the underlying knowledge changes. A customer contract gets updated. A project owner changes. A policy is revised. A previous fact may no longer be true, but simply overwriting it means the system loses the history behind that change. Utopia handles this with a bitemporal knowledge graph. Each fact can track both when it was true in the real world and when the system learned about it. When something changes, the old fact is preserved instead of silently disappearing. That means an agent can reason about questions like: • What is true now? • What was true three months ago? • When did this information change? • What evidence was the conclusion based on? The graph is also ontology-aware, so documents are represented as entities, facts, and relationships instead of only chunks and embeddings. That gives the system more structure for reasoning across relationships, resolving entities, detecting conflicting facts, and deriving new information through explicit rules. Key capabilities: • Bitemporal knowledge graph for tracking how facts change over time • Provenance on facts so agents can trace where information came from • Conflict detection instead of silently overwriting contradictory information • Ontology-based reasoning across entities, relationships, and derived facts • Hybrid retrieval across full-text search, vector search, and graph traversal • MCP and agentic RAG support for exposing the knowledge layer directly to agents The interesting part is that this turns the knowledge base into more than a retrieval system. Instead of only finding relevant information, an agent can reason over what changed, what is still valid, how facts are connected, and where each conclusion came from. 100% open source. I've shared the GitHub repo in the comments! Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 1 👀 384 📊 1 ⚡