概览
主要功能
- 基于知识图谱的智能体记忆
- 语义化和结构化数据摄入
- 用于智能体集成的Python SDK
- 可插拔的LLM和存储提供商
- 跨会话和文档查询
- 自主托管或托管部署选项
价格
- 模型
- Free
- 分类
- 服务配缩器
- 评分
- 4.8 / 5 (5)
使用场景
AI智能体的长期记忆
通过将交互存储在知识图谱中并按需检索相关上下文，为对话式智能体提供跨会话的持久回忆。
基于上下文的文档RAG
摄入文档和结构化数据，然后结合图关系和语义搜索，提供比仅限向量的RAG更丰富、更准确的检索。
减少LLM应用中的幻觉
将LLM响应建立在先前捕获的事实和关系之上，减少重复提示并随着时间的推移提高答案的可靠性。
用于自定义堆栈的自主托管记忆层
使用Python SDK将Cognee插入首选的LLM、向量存储和图数据库，提供自主托管或托管部署以实现完全控制。
优点 & 缺点
优点
- 结合图和向量检索，提供更丰富的上下文
- 开源且具有灵活的Python SDK
- 适用于多种LLM和数据库后端
- 有助于减少重复提示和幻觉
缺点
- 需要技术设置和基础设施知识
- 基于图的记忆与纯向量数据库相比增加了复杂性
- 最佳结果需要针对每个用例进行调优
评测
5 个评分的平均值。
登录以留下评测。
Does the job
Pretty happy overall. Pluggable LLM and storage providers just works and helps reduce repetitive prompting and hallucinations. but no dealbreakers — I'd recommend it to a friend without hesitating.
Does the job
Pretty happy overall. Querying across past sessions and documents just works and combines graph and vector retrieval for richer context. but no dealbreakers — I'd recommend it to a friend without hesitating.
Years in this space
I've evaluated a lot of these over the years. What stands out here is self-hosted or managed deployment options — handled better than most — and combines graph and vector retrieval for richer context. Worth the time if this is your use case.
Skeptical, then convinced
I went in skeptical — most tools in this space overpromise. It actually delivers on knowledge graph based agent memory, and combines graph and vector retrieval for richer context caught me off guard. still, I'd recommend giving it a real trial.
Skeptical, then convinced
I went in skeptical — most tools in this space overpromise. It actually delivers on knowledge graph based agent memory, and open-source with a flexible Python SDK caught me off guard. Requires technical setup and infrastructure knowledge is why this isn't a perfect score, still, I'd recommend giving it a real trial.
问答
是否支持多个用户、租户或工作区?
是。Cognee Cloud是多租户的，具有隔离的工作区和每会话的内存，因此您可以在一键部署中为很多用户或客户提供服务。
Asked by Quentin Lefevre · Mar 15, 2026
如何准确度的Cognee?
Cognee在 BEAM（agent memory benchmark）中是当前最先进的，它在长期、多会话回忆上超越了之前最先进的版本（79%比73.4%高，100k tokens 时 67%比64.1%高，10M 时）。但不必为此建立一个定制的架构。
Asked by Mei-Ling Wong · Mar 9, 2026
Is cognee cost-effective at scale?
Yes. cognee is built to keep memory costs flat as data grows — in our benchmarks it processes the same workloads at a fraction of a baseline LLM approach's cost.
Asked by Henrik Dahl · Mar 5, 2026
Which databases and data sources does cognee support?
cognee connects to the data sources your team already uses — Slack, Notion, Google Drive, GitHub, Confluence, Jira, Dropbox, Amazon S3, Salesforce, and more. Under the hood it works with graph and vector backends including Kuzu, NetworkX, Neo4j, FalkorDB, LanceDB, Qdrant, Milvus, Weaviate, pgvector, and Redis, so you can match your existing infrastructure.
Asked by Celia Ramirez · Feb 28, 2026
能否在我现有的 PostgreSQL 数据库上运行 cognee?
是的，cognee 可以在 PostgreSQL 中使用 pgvector。所以你可以在现有的基础设施上添加 agent 内存，而不是另外创建一个数据库。
Asked by Amos Fältskog · Feb 27, 2026
提问
服务配缩器 的替代品
Playwright MCP服务配缩器开源MCP服务器，利用_playwright让LLM控制真实的浏览器以及可访问性快照
Python agent 框架由 Pydantic 团队开发，用于构建类型安全的 GenAI 应用。
Inbox Zero服务配缩器AI 邮箱助手，帮助您更快地达到 inbox zero。
Screenpipe服务配缩器开源式24小时设备屏幕和音频录制，适合构建依赖实况人工智能（AI）应用
AgentKit服务配缩器用于构建和编排带有工具、内存和多智能体工作流的AI智能体的TypeScript库。
onchain-mcp服务配缩器把无银行的 onchain API 带入 MCP
markitdown服务配缩器带少分享系兿司上字詰級下合存号来皅
mcp-clickhouse服务配缩器mcp-clickhouse MCP 服务
