semantica-agi / semantica
semantica-agi / semantica
Graph-Native Infrastructure for Context and Accountable AI Systems 用于上下文和可问责 AI 系统的图原生基础设施
The Open Source Palantir for AI Agents. Ingest your enterprise data, extract what matters, build a Context Graph and knowledge graph (KG), and run graph analytics and causal reasoning over all of it, with full decision provenance baked in. Explainable, traceable, and trustworthy by design. 这是 AI Agent 领域的开源版 Palantir。它能够摄取企业数据、提取关键信息、构建上下文图谱（Context Graph）和知识图谱（KG），并在此基础上运行图分析和因果推理，同时内置完整的决策溯源功能。其设计初衷即是可解释、可追踪且值得信赖的。
Decision Intelligence · Context Management · Deterministic Reasoning · Ontology Management · Knowledge Modeling · End-to-End Traceability 决策智能 · 上下文管理 · 确定性推理 · 本体管理 · 知识建模 · 端到端可追溯性
Open Source · Self-Hostable · Auditable · Governed · Zero Vendor Lock-In 开源 · 可自托管 · 可审计 · 受治理 · 无供应商锁定
Polyglot Graph Storage · RDF & LPG Support · W3C Standards · Interoperable 多语言图存储 · 支持 RDF 和 LPG · 符合 W3C 标准 · 可互操作
Built for High-Stakes, Regulated Domains 专为高风险、受监管领域打造
pip install semantica
Knowledge Explorer · Context Graphs · Reasoning Engine · Decision Intelligence · Ontology Hub 知识浏览器 · 上下文图谱 · 推理引擎 · 决策智能 · 本体中心
▶ Watch the full platform walkthrough ▶ 观看完整平台演示
Most AI agents act without a trail. They store embeddings, not meaning: context that can’t be explained, decisions that can’t be audited. In lending, that gap is a compliance exposure, not an inconvenience: an underwriting agent’s approval has to survive a regulator’s “why” months later. Semantica sits underneath your LLM, vector store, and agent framework as a deterministic infrastructure layer: no LLM required for graph construction, reasoning, or provenance. 大多数 AI Agent 在行动时不会留下痕迹。它们存储的是向量而非语义：这些上下文无法解释，决策也无法审计。在贷款领域，这种缺失不仅是不便，更是合规风险：承保代理人的批准必须经得起数月后监管机构对“为什么”的质询。Semantica 位于你的大模型（LLM）、向量数据库和 Agent 框架之下，作为确定性的基础设施层：在图谱构建、推理或溯源过程中无需依赖 LLM。
Who it’s for: 适用人群：
- AI/ML platform teams shipping agents that make consequential decisions and need structured, queryable context built from fragmented raw data, not just a vector index. AI/ML 平台团队：负责交付关键决策 Agent，且需要从碎片化原始数据中构建结构化、可查询的上下文，而不仅仅是向量索引。
- Data platform teams on Databricks or Snowflake who need to turn tables already sitting in Unity Catalog or a Snowflake warehouse into a governed, lineage-tracked knowledge graph, without exporting that data to a third-party SaaS first. Databricks 或 Snowflake 上的数据平台团队：需要将 Unity Catalog 或 Snowflake 仓库中现有的表转化为受治理、可追踪血缘的知识图谱，且无需先将数据导出到第三方 SaaS。
- Compliance, risk, and audit teams who need a straight answer to “why did the AI do that?” in a format a regulator will actually accept. 合规、风险和审计团队：需要以监管机构认可的格式，直接回答“AI 为什么这样做？”的问题。
- Regulated enterprises (finance, healthcare, legal, government, defense) that can’t ship a black box, and can’t send their data to someone else’s SaaS to get one. 受监管企业（金融、医疗、法律、政府、国防）：无法交付黑盒系统，也无法将数据发送到他人的 SaaS 平台。
- Platform and infra engineers who want the KG, reasoning, and provenance stack self-hosted and swappable, not locked to one vendor’s backend. 平台和基础设施工程师：希望知识图谱、推理和溯源栈可自托管且可替换，而不是被锁定在某个供应商的后端。
- Data and knowledge engineers building a KG from messy, multi-source data: entities and relationships get extracted, conflicting or contradictory facts are flagged instead of silently overwritten, and duplicates are merged before they turn into noise. 数据和知识工程师：从混乱的多源数据中构建知识图谱：提取实体和关系，标记冲突或矛盾的事实而非静默覆盖，并在重复数据变成噪音前进行合并。
What Semantica Gives You
Semantica 为你提供：
- Context Graphs: A structured, queryable graph of everything your agent knows, decides, and reasons about. 上下文图谱：一个结构化、可查询的图谱，涵盖了 Agent 所知、所决策和所推理的一切。
- Decision Intelligence: Every decision is a first-class object: traceable, searchable by precedent, and causally linked. 决策智能：每个决策都是一等对象：可追溯、可按先例搜索，并具有因果关联。
- AI Governance & Ontology: SHACL constraints, conflict detection, compliance rules, OWL generation, and SKOS vocabulary management with a visual editor. AI 治理与本体：SHACL 约束、冲突检测、合规规则、OWL 生成以及带有可视化编辑器的 SKOS 词汇管理。
- Full Auditability: W3C PROV-O provenance on every fact, with audit trails exportable to JSON, CSV, or RDF. 完全可审计性：每个事实都带有 W3C PROV-O 溯源信息，审计追踪可导出为 JSON、CSV 或 RDF。
- Deterministic Reasoning: Forward chaining, Rete network, Datalog, and SPARQL with fully explainable paths, not black boxes. 确定性推理：前向链、Rete 网络、Datalog 和 SPARQL，提供完全可解释的路径，而非黑盒。
- Knowledge Pipeline: Multi-source ingestion, entity-aware chunking, NER/relation/event extraction, and knowledge graph construction, with semantic deduplication and provenance-preserving merges throughout. 知识流水线：多源摄取、实体感知分块、NER/关系/事件提取以及知识图谱构建，全程包含语义去重和溯源保留合并。
- Enterprise Data Platforms: Native connectors for Databricks and Snowflake, so tables become graph nodes with provenance. 企业数据平台：提供 Databricks 和 Snowflake 的原生连接器，使数据表转化为带有溯源信息的图节点。
- Graph Analytics: Centrality, community detection, link prediction, and shortest-path queries. 图分析：中心性、社区检测、链路预测和最短路径查询。
- Polyglot Graph Storage: Native RDF and Labeled Property Graphs (Neo4j, FalkorDB, etc.), all swappable. 多语言图存储：原生 RDF 和标签属性图（Neo4j, FalkorDB 等），均可互换。
Why Semantica
为什么选择 Semantica
| Feature | Vector DB + RAG | Plain LLM Memory | Semantica |
|---|---|---|---|
| Recall method | Embedding similarity | Token window | Graph traversal + semantic search |
| Decision history | Not stored | Not stored | First-class queryable objects |
| Provenance | None | None | W3C PROV-O, source-linked |
| Reasoning | None | Black box | Forward chain, Rete, Datalog, SPARQL |
| Conflict detection | Silent overwrite | Silent overwrite | Detected, flagged, resolved |
| Time travel | No | No | Point-in-time graph snapshots |
| Compliance export | None | None | PROV-O, SHACL, OWL, RDF |
| Policy enforcement | None | None | Built-in rule engine + SHACL |
| Entity resolution | No | No | Blocking + semantic deduplication |
| Multi-agent context | Separate per agent | Separate per agent | Single shared intelligence layer |
Semantica complements your existing stack rather than replacing it. Keep your LLM, vector store, and agent framework exactly as they are; Semantica adds the decision records, causal reasoning, provenance, ontology governance, conflict detection, and audit trails on top. The reasoning engines, KG construction, and provenance layer are fully deterministic; no LLM is required to use them. Semantica 是对现有技术栈的补充而非替代。你可以保留原有的 LLM、向量数据库和 Agent 框架；Semantica 在其之上增加了决策记录、因果推理、溯源、本体治理、冲突检测和审计追踪。推理引擎、知识图谱构建和溯源层是完全确定性的；使用它们无需 LLM。
Quick Start
快速开始
pip install semantica
from semantica.context import ContextGraph
graph = ContextGraph(advanced_analytics=True)
# Every agent decision becomes a queryable, auditable knowledge node
# 每个 Agent 决策都成为一个可查询、可审计的知识节点
decision_id = graph.record_decision(
category="vendor_selection",
scenario="Choose cloud provider for HIPAA workload",
reasoning="AWS offers BAA, mature HIPAA tooling, and existing team expertise",
outcome="selected_aws",
confidence=0.93,
)
# Ask "why did this happen?" and get a real, structured answer
# 询问“为什么会发生这种情况？”并获得真实的结构化答案
chain = graph.trace_decision_chain(decision_id)