feature
为免费层引入按使用量计费和月度上限，而非硬限制
免费层用户现在对超出其层级限制的超额部分有灵活的按使用量计费，用户可自行设置月度花费上限，而非被硬性限制在层级限制。
证据
−10,000 add requests/ month
1,000 retrieval requests/ month
+Usage-based billing past your limits, with a monthly cap you set
Mem0
记忆与上下文mem0.ai9 条已发布变化
2 个来源在监控
变化时间线
positioning
Shifted from "simple and affordable" fixed pricing to "free and custom plans" flexible model
Company repositioned as offering flexible, negotiated pricing rather than transparent, self-serve pricing tiers, requiring sales outreach for production use cases.
证据
−Simple and Affordable
+Free and custom plans
Start free with your own LLM key. Talk to us when you need higher limits or a contract.
pricinghigh
Mem0 completely restructured pricing from tiered plans (Hobby/Starter/Pro/Enterprise) to Free + Custom model
All customers must migrate from named tier subscriptions (Hobby, Starter, Pro, Enterprise) to either a free tier with usage-based overages or a custom plan negotiated with the company. No more fixed-price Pro plan at $249/month.
证据
−Hobby
For individuals exploring and building side projects.
10,000 add requests/ month
1,000 retrieval requests/ month
1 project
Starter
For solo builders shipping their first AI agent.
$19
/ month
Pro
Popular
For production apps with real scale.
$249
/ month
Enterprise
For teams that need compliance, control & SLAs.
Contact Us
+For developers building and testing with Mem0.
Free
First 30 days: 10,000 adds and 1,000 retrievals a month, model calls on us
With your own LLM key: 50,000 adds and 10,000 retrievals a month
Usage-based billing past your limits, with a monthly cap you set
For production apps that need higher limits, advanced features or a contract.
Custom
Talk to us
featurehigh
用户资料功能已添加到 Mem0 Python SDK (v2.2.0)，附带资料管理方法
Python SDK 用户现在可以创建、检索和管理用户资料，这些资料是由可配置架构构成的结构化 JSON 摘要，支持异步生成和幂等作业重试。
证据
+Add User Profiles to MemoryClient and AsyncMemoryClient: get_profile(), generate_profile(), get_profile_settings(), update_profile_settings(), sample_profiles(), and get_profile_job(). A profile is a structured, always-current JSON summary of one user, shaped by a JSON Schema you configure per project and filled by an LLM from that user's memories. Generation is asynchronous. Every job POST carries an Idempotency-Key; to retry a lost request without starting a second job, pass the same idempotency_key on each attempt
apihigh
Mem0 Pi Agent Plugin v0.3.0：移除了 Dream 合并和 pin 命令
使用 Dream 合并、pin 命令和相关技能进行集成的开发者必须更新代码；仅保留 remember、search、forget、tour、scope 和 status 命令。
证据
+Removed Dream consolidation and pin commands, skills, configuration, types, and exports. The remaining commands are remember, search, forget, tour, scope, and status. Update integrations that import removed APIs or invoke removed commands.
apihigh
Mem0 Python SDK：delete_all() 现在以 1000 为单位对向量存储进行分页处理
拥有超过单页内存数量的账户现在将正确删除所有内存，而不是静默留下剩余部分。
证据
+delete_all() now paginates through the vector store in batches of 1000 instead of listing once, so accounts with more memories than a single page (most vector stores default to ~100) had the remainder silently left behind
featurehigh
Mem0 Node SDK：添加了 Qdrant 服务器端 BM25 keywordSearch()
Qdrant 向量存储现在支持服务器端 BM25 关键词搜索（需要 Qdrant >= 1.15.2），无需在客户端依赖 BM25。
证据
+Add Qdrant server-side BM25 keywordSearch() (requires Qdrant >= 1.15.2) plus payload filter indexes, so keyword search runs without a client-side BM25 dependency
github.com · 另有 1 个来源报告了同一变化
featurehigh
修复关键安全问题，防止元数据覆盖身份字段 (user_id, agent_id, run_id, actor_id)
防止恶意元数据将内存移动到不同租户的未授权租户范围升级攻击
证据
+Stop `update()` metadata from overwriting or injecting `user_id`, `agent_id`, `run_id`, or `actor_id`. These identity fields are immutable after creation, so passing them in `metadata` can no longer move a memory into a different tenant's scope (#6278)
api
OpenAIStructuredLLM 现在读取 OPENAI_BASE_URL 而不是 OPENAI_API_BASE
配置现在与官方 OpenAI SDK 和其他 OpenAI 兼容提供商保持一致；用户可能需要更新环境变量
证据
+Read `OPENAI_BASE_URL` (was `OPENAI_API_BASE`) in `OpenAIStructuredLLM`, matching the official OpenAI SDK's environment variable and the rest of the OpenAI-compatible providers (#6322)