RetainDB

context and memory infrastructure for AI

[RetainDB @retaindb]

@MaksimXBT @vasuman That’s why you should use retaindb 😸

[RetainDB @retaindb]

@a_levitator https://t.co/WjIA3q6VPS

[RetainDB @retaindb]

GitHub: https://t.co/WjIA3q6VPS

[RetainDB @retaindb]

Announcing RetainDB Local persistent memory for coding agents, on your machine🚨

One command:

npx -y @retaindb/local

Remembers decisions, conventions, failed approaches, corrections, and session context across every conversation

Works with Claude Code, Codex, OpenCode etc

[RetainDB @retaindb]

@jonathanbylos @Teknium @callebtc @plastic_lab @mem0ai @openvikingai @Vectorizeio @ByteroverDev Neat

[RetainDB @retaindb]

@Teknium @jonathanbylos @callebtc @plastic_lab @mem0ai @openvikingai @Vectorizeio @ByteroverDev Yeah i personally used Hermes and didn’t feel the need for external memory tbvh . Except it’s local version of each (which is also not necessary). Also every agent I build now is literally modeled after Hermes . Crazy stuff you built there

[RetainDB @retaindb]

@jonathanbylos @callebtc @Teknium @plastic_lab @mem0ai @openvikingai @Vectorizeio @ByteroverDev I wonder if anyone from Hermes ever tried retaindb . Got signups infact lots but I hear almost nothing

[RetainDB @retaindb]

@allen119269629 @Teknium @plastic_lab @mem0ai @openvikingai @Vectorizeio @ByteroverDev @retaindb installation is easy just copy the prompt on the landing page to your Hermes agent

[Al-ameen @alameenpd]

I’m getting a lot of inbound from investors lately and idk what’s happening .

If you see my posts or you’ve heard about @retaindb and you are considering investing here’s our investor brief to save you some time

https://t.co/5NslayHpyG

[RetainDB @retaindb]

Check out our investor brief

https://t.co/WqmYDu6ZpP

[Al-ameen @alameenpd]

I’m getting a lot of inbound from investors lately and idk what’s happening .

If you see my posts or you’ve heard about @retaindb and you are considering investing here’s our investor brief to save you some time

https://t.co/5NslayHpyG

[RetainDB @retaindb]

@TalosIsDead Yes please let us know so we can offer you a month or two free of the pro plan . Sorry for the inconvenience

[RetainDB @retaindb]

Hermes agent now supports retaindb

Excited to see who tried us out

[Teknium 🪽 @Teknium]

Hermes Agent now supports @plastic_lab's Honcho, @mem0ai, @openvikingai, @Vectorizeio's Hindsight, @retaindb, and @ByteroverDev memory systems!

Try them now with `hermes update` then `hermes memory setup`

We have rehauled our memory system to be much more maintainable and pluggable, so anyone can make their own memory system to build on top of Hermes easily and cleanly with a special class of plugin!

Which memory system is your favorite?

[RetainDB @retaindb]

@TalosIsDead @TalosIsDead I couldn’t reach out to you via DMs . But I just wanted to update you on this situation. The Hermes team wired retaindb wrong and the APIs were not working cause it was reaching 404 routes . We fixed this today and retaindb is very functional. We apologize

[Al-ameen @alameenpd]

We just shipped something big at RetainDB.

Until now, AI agents had memory, but they still worked in silos. One agent processes a document, another agent has no idea it exists. Everything has to be re-uploaded, re-parsed, re-prompted. Context keeps getting lost.

We fixed that.

RetainDB now gives agents a shared workspace.

You can upload a file once, ingest it, and it becomes part of memory. Not just stored somewhere, but actually understood. It gets parsed, chunked, embedded, and turned into structured memory your agents can search and use.

So instead of forcing context into prompts, agents can just query memory and already know what’s inside your documents.

And because files live at stable URIs like rdb://files/…, they’re not temporary links or blobs that disappear. They’re first-class references agents can pass around, reuse, and build on.

One agent can process a report, another can pick it up later, extract insights, and continue the workflow. No duplication, no context loss.
(this is only available on the cloud version the oss version doesnt have this ...yet)

[RetainDB @retaindb]

We just shipped a big update at retaindb .

[Al-ameen @alameenpd]

We just shipped something big at RetainDB.

Until now, AI agents had memory, but they still worked in silos. One agent processes a document, another agent has no idea it exists. Everything has to be re-uploaded, re-parsed, re-prompted. Context keeps getting lost.

We fixed that.

RetainDB now gives agents a shared workspace.

You can upload a file once, ingest it, and it becomes part of memory. Not just stored somewhere, but actually understood. It gets parsed, chunked, embedded, and turned into structured memory your agents can search and use.

So instead of forcing context into prompts, agents can just query memory and already know what’s inside your documents.

And because files live at stable URIs like rdb://files/…, they’re not temporary links or blobs that disappear. They’re first-class references agents can pass around, reuse, and build on.

One agent can process a report, another can pick it up later, extract insights, and continue the workflow. No duplication, no context loss.
(this is only available on the cloud version the oss version doesnt have this ...yet)

[Al-ameen @alameenpd]

@retaindb is now live in Hermes Agent memory update @NousResearch

Literally a one-minute setup: just run "hermes memory setup", add your API key, and your agent gets memory.

We handle storage, retrieval, and context across sessions.

Also it’s open source

[RetainDB @retaindb]

@btc_hans @Rigario Fixed

[Al-ameen @alameenpd]

https://t.co/PpklPkCHbD

[RetainDB @retaindb]

@btc_hans @Rigario Also I added a way for users without docker to run it . Please any issue you encounter share with me so I fix

[RetainDB @retaindb]

@btc_hans @Rigario Thank you . Please send me any errors or issues you encounter so I can get to fixing them asap