AI Devtools Radar

Mem0

Memory & contextmem0.ai9 published changes

2 sources under watch

Change timeline

feature

Usage-based billing with monthly cap introduced to Free tier instead of hard limits

Free tier users now have flexible overage pricing beyond their tier limits, with a monthly spending cap they can set themselves, rather than being hard-capped at tier limits.

Evidence
−10,000 add requests/ month 1,000 retrieval requests/ month
+Usage-based billing past your limits, with a monthly cap you set

mem0.ai

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.

Evidence
−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.

mem0.ai

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.

Evidence
−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

mem0.ai

featurehigh

User Profiles feature added to Mem0 Python SDK (v2.2.0) with profile management methods

Python SDK users can now create, retrieve, and manage user profiles as structured JSON summaries shaped by configurable schemas, with asynchronous generation and idempotent job retries.

Evidence
+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

github.com

apihigh

Mem0 Pi Agent Plugin v0.3.0: Removed Dream consolidation and pin commands

Developers using Dream consolidation, pin commands, and related skills in integrations must update code; only remember, search, forget, tour, scope, and status commands remain.

Evidence
+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.

github.com

apihigh

Mem0 Python SDK: delete_all() now paginates through vector store in batches of 1000

Accounts with more memories than a single page will now have all memories deleted correctly instead of silently leaving the remainder behind.

Evidence
+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

github.com

featurehigh

Mem0 Node SDK: Added Qdrant server-side BM25 keywordSearch()

Qdrant vector store now supports server-side BM25 keyword search (requires Qdrant >= 1.15.2) without requiring a client-side BM25 dependency.

Evidence
+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 · also seen at 1 more source

featurehigh

Fix critical security issue preventing metadata from overwriting identity fields (user_id, agent_id, run_id, actor_id)

Prevents unauthorized tenant scope escalation attacks where malicious metadata could move memories to different tenants

Evidence
+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)

github.com

api

OpenAIStructuredLLM now reads OPENAI_BASE_URL instead of OPENAI_API_BASE

Configuration now matches official OpenAI SDK and other OpenAI-compatible providers; users may need to update environment variables

Evidence
+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)

github.com