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)
Your agents are smarter than ever. They still forget everything when the session ends. Switch harness, device or model, and you're explaining yourself all over again.
1
2
2
4
222
I pointed Muse at @gubatron's MentisDB & analyzed 8 months of Rust history, symbol by symbol 52 releases. 3,620 library symbols. 5 evolution stories. 9 potentially breaking patch releases Architecture, hotspots, release history & visualizations Report: musehub.ai/gabriel/mists/JDH…
2
2
1
5
522
MentisDB + Muse VCS, a proposal. "The future of software development needs more than faster code generation. It needs a better way to understand, version, and merge what we create." -@cgcardona creator of Muse and MuseHub
3
1
5
232
The planet is a single point of failure. Agentic Memory shouldn't have one.
1
2
4
155
mentisdb.com Own your memories. Don't repeat yourself. Harness and model provider independent.
2
MentisDB moves memory out of the agent and into a database you own: 🧠 Typed memories on an append-only chain 🔁 Same memory across Claude Code, Codex, Gemini, Grok… 🔑 Private chains: only agents with allowed keys can write
1
17
💬 Setup is one sentence: "use mentisdb as your memory system" Your memory. Your data. 👇 mentisdb.com
5
Visualize your MentisDB Memory Chains with Mentis Graph by @FaulknerPearce github.com/faulknerpearce/me…
2
2
107
MentisDB retweeted
Replying to @NotionHQ
or you could use @mentisdb
1
2
5
it never gets old seeing Claude using MentisDB memory without you telling it to
11
MentisDB retweeted
Your agents shouldn’t forget the decisions that make the next run better. MentisDB is a durable semantic memory engine and versioned skill registry for AI agents that need persistent context across tools and sessions. It helps you carry decisions, lessons, and instruction bundles forward by storing typed thoughts in an append-only, hash-chained memory log and keeping skill updates as immutable versions. Key features: • Shared memory across tools – connect MCP-capable coding environments to the same MentisDB daemon • Context checkpoints – agents can write a Summary checkpoint, compact, and reload recent context • Semantic memory – the optional local-embeddings feature enables semantic vector search with FastEmbed • Versioned skills – uploads to an existing skill ID create immutable versions stored as unified diffs • Verifiable provenance – agents with registered Ed25519 keys must sign their skill uploads It’s open-source (MIT license). Link in the reply 👇
5
9
21
1,810
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
149
Durable memory, invisible, your way. Built for agents that learn. Don't get locked in by any vendor, own your agent's memories.
2
3
4
363
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
91
MentisDB retweeted
Your OpenClaw's Memory system sucks? Ask it to use MentisDB for its memory system. Problem solved. – at Denver, CO
1
2
3
220
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
MentisDB retweeted
Forked @mentisdb to play with letting my memory chains dream using a local ollama instance on a scheduled interval (to make it easier to wall off any unintended runaway token consumption). Got the basic hooks in place but I want to adjust temperature and generation params so it frequently has "working through a problem" dreams but occasionally it can have the equivalent of a "whoa is that from our meds?" dream.
2
3
165
Put the brain where your team can reach it. mentisdb.com
16