What each one has. With the source of every cell.

• yesthe vendor’s documentation describes the whole capability
• partialit describes part of it; the note says which
• nothe documentation says it works another way
• not documentedthe page read says nothing about it, which does not mean it does not exist

Every mark is a link to the page read, on 2026-10-01. Documentation changes: a cell only changes after a new reading, with a new date.

Capability	Niadra	Mem0 (open source)	Mem0 Platform	Zep	Letta	Supermemory	Hindsight	Honcho	Cognee	Amazon Bedrock AgentCore Memory	Twilio Conversation Memory
Identity across channelsThe memory works out that the phone, the WhatsApp number, the e-mail and each system’s ID belong to the same person. The application does not hand over a ready-made ID.	yes	no	no	no	no	no	no	no	no	no	yes
One memory for agents from different vendorsAgents from different vendors read and feed the same customer memory, each with its own permission, and cutting one vendor off erases nothing.	yes	partial	partial	partial	partial	partial	partial	partial	partial	partial	partial
Events from the CRM and the ERPOrders, bills and tickets enter the memory through the events the system already emits, tied to the right customer by that system’s ID.	yes	not documented	not documented	partial	not documented	not documented	not documented	not documented	not documented	not documented	partial
Typed business state with freshnessAn order, a bill, a quote: every value reaches the agent with its type, the date it was last updated, the source and what may not be stated with it.	yes	no	partial	partial	no	partial	no	no	partial	no	partial
The claim checkBefore the answer goes out, every price, date and number the agent is about to say is checked against what it consulted. What has no source is flagged.	yes	not documented	not documented	not documented	not documented	not documented	not documented	not documented	not documented	not documented	not documented
Coordination between agentsBefore acting, the agent asks who holds the customer and what was already done. One business fact causes one effect.	yes	not documented	not documented	not documented	not documented	not documented	not documented	not documented	not documented	not documented	not documented
Turn records and replayWhat the agent read, called, showed and stated on every turn, with the build pinned, and the replay of a real conversation in your CI.	yes	not documented	not documented	not documented	partial	not documented	not documented	not documented	not documented	partial	not documented
Per-agent permissions and field accessEach agent reads only what its purpose allows, item by item, and a sensitive field reaches only who may see it.	yes	partial	partial	partial	partial	partial	partial	partial	partial	partial	not documented
Receipts of who read whatEvery read, the refused one included, leaves a record of which agent read what, for what and when, tamper-evident.	yes	partial	partial	partial	not documented	not documented	not documented	not documented	not documented	partial	partial
Erasure with a receiptErasing a customer walks through everything derived from their data and returns a receipt of what was erased.	yes	partial	partial	partial	partial	partial	yes	partial	partial	partial	partial
Prompt-ready compact contextThe agent receives text ready for the prompt, assembled before the request, with no AI on the read.	yes	partial	partial	yes	partial	yes	partial	yes	partial	partial	partial
Voice integrationsA documented adapter for voice platforms: LiveKit, Pipecat, Vapi, Retell, ElevenLabs, Twilio.	yes	yes	yes	yes	yes	yes	yes	not documented	not documented	not documented	yes
MCP serverThe memory as MCP tools, for any agent that speaks the protocol.	yes	yes	yes	yes	partial	yes	yes	yes	yes	partial	not documented
A published benchmarkThe vendor publishes measured results of its own memory, with the method.	yes	yes	yes	yes	yes	partial	yes	yes	yes	not documented	not documented
Open source and self-hostingThe memory engine is open and can run on the customer’s own infrastructure.	no	yes	no	partial	yes	yes	yes	yes	yes	no	no
Published priceThe list price as the vendor’s page states it, with no conversion. The cost per thousand conversations, measured by the same method for every system, is on the benchmark.	US$ 2 to 3 per thousand conversations or tasks, models included; US$ 500 a month minimumsource · 2026-10-01	Free software; you pay for the model and the serverssource · 2026-10-01	Hobby free; Starter US$ 19 a month; Pro US$ 249 a month (500,000 adds and 50,000 retrievals); Enterprise on requestsource · 2026-10-01	Flex US$ 125 a month with 50,000 credits (1 credit per episode of up to 350 bytes); Flex Plus US$ 375; Enterprise on requestsource · 2026-10-01	API US$ 20 a month, plus US$ 0.10 per active agent a month and US$ 0.00015 per second of tool execution; the model apartsource · 2026-10-01	Pro US$ 19, Max US$ 100 and Scale US$ 399 a month; rate card of US$ 5 per million SM tokens and US$ 5 per million searchessource · 2026-10-01	Usage-based: retain US$ 10 per million tokens, recall US$ 0.75 per million, reflect US$ 0.05 per call, storage US$ 0.25 per million a monthsource · 2026-10-01	Ingestion US$ 2 per million tokens; context() unlimited; reasoning from US$ 0.001 to 0.50 per questionsource · 2026-10-01	Free up to 1 million tokens; Standard US$ 1 per million tokens plus US$ 5 per extra workspace; Enterprise on requestsource · 2026-10-01	US$ 0.25 per 1,000 events; US$ 0.75 per 1,000 records stored a month (US$ 0.25 with your own strategy); US$ 0.50 per 1,000 retrievalssource · 2026-10-01	US$ 0.005 per profile used per day; US$ 0.0028 per 1,000 characters generated; US$ 0.007 per recallsource · 2026-10-01

Names and logos belong to their owners and appear here only to identify the systems compared.