MentisDB (@mentisdb) header
MentisDB (@mentisdb) profile picture

The Infinite Memory Solution for Agents. Own your memories, use any harness, don't fear context collapse. No more .md file hell for agents, memories or skills.

Colorado
Joined March 2026
Photo by MentisDB (@mentisdb)Photo by MentisDB (@mentisdb)Photo by MentisDB (@mentisdb)Photo by MentisDB (@mentisdb)Photo by MentisDB (@mentisdb)Photo by MentisDB (@mentisdb)Photo by MentisDB (@mentisdb)Photo by MentisDB (@mentisdb)Photo by MentisDB (@mentisdb)Photo by MentisDB (@mentisdb)
Durable memory, invisible, your way. Built for agents that learn. Don't get locked in by any vendor, own your agent's memories.
2
2
4
319
Visualize your MentisDB Memory Chains with Mentis Graph by @FaulknerPearce github.com/faulknerpearce/me…
2
2
92
it never gets old seeing Claude using MentisDB memory without you telling it to
10
MentisDB 0.10.10 is out 🧠 🐳 Official Docker image: docker run ghcr.io/cloudllm-ai/mentisdb 🐧 Linux binaries now run on Ubuntu 22.04 & Debian 12 🔒 Webhooks to your private network (Tailscale/WireGuard) Durable, self-hosted memory for your AI agents. github.com/CloudLLM-ai/menti…
1
1
3
148
New MentisDB 0.10.9.54 out Good morning Gang, new MentisDB out with Security vulnerabilities fixes, memory blow up bug fixed, search reranking bug fixed, improved search retrieval. Also memory appends improved dramatically Per-append cost dropped from 6.3–7.8 ms to 1.4 ms!
1
90
MentisDB solves this. The memory graph can invalidate and point back at previously wrong assumptions or things that are no longer true, however, nothing is forgotten. Memories are stored the same was as a blockchain, tamper proof.
AI memory sounds impressive until it remembers one wrong thing you said it once 6 weeks ago the model treats it like law and every new answer builds around that old assumption it still knows the files the old name the joke you made in passing it does not know you changed your mind the hard part isn’t storing 10,000 things it’s knowing which 10 should still matter tomorrow
1
22
Put the brain where your team can reach it. mentisdb.com
16
Durable memory, invisible, your way. Built for agents that learn. Don't get locked in by any vendor, own your agent's memories.
219
Don't repeat yourself. Let intelligence compound with experience. Try it today, free and open mentisdb.com
7
6
285
New MentisDB This is a technical-debt release. It closes the two open bug reports filed against the 0.10.x line - a vector sidecar bug that could make a chain stop opening (@FaulknerPearce Thanks) - a CLI flag that was documented but not wired
3
4
31
Just pasted to Muse our opencode's MCP mentisdb configuration JSON as an example and told it, connect yourself to it!
1
1
107
New MentisDB 0.10.6 build 51 release github.com/CloudLLM-ai/menti… cargo install mentisdb --locked --force Powered by Grok 4.6
2
23
Just saw a video of 38 Grok 4.6 agents working, all connected to MentisDB. Mind melding Borg.
2
180
What if you could visualize the mind, the memories of your agents?
We made a tool to visualise the brain we have built for our agents while using @mentisdb .
1
28
The folks at Aseryx build a MentisDB Brain visualization for all the memories their agents have built the past few months
This is the Aseryx Brain. A knowledge base that we have built using @mentisdb
1
1
2
75
MentisDB works well as a local daemon, but the more interesting deployment is a remote memory server: one EC2 instance, many coding agents, shared durable chains, and MCP clients connecting from laptops or other hosts.
1
2
24
"from now on speak and think in Simplified Technical English (STE), save user preference to mentisdb"
2
32
You can do this with EVERY harness with MCP support. Just have your sessions plugged to MentisDB memory on a server in the cloud, they will share their state of mind. Free and opensource, written in rust for enterprise performance mentisdb.com
New in Claude Code: your sessions can now message each other. Instead of having to re-explain yourself in another session, you can now tell Claude to do it. It sends a summary (not your history or files), and the other session picks it up mid-task.
1
1
54
The whole point of MentisDB has always been not having to explain yourself repeatedly to any model. Your models can be seamlessly orchestrated thanks to our memory chains.
4