MentisDB retweeted
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…
mentisdb.com
Own your memories.
Don't repeat yourself.
Harness and model provider independent.
2
💬 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…
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 👇
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…
PSA: private vulnerability reporting is now enabled in our Github repository.
Please send your notes through the repository's Security → Report a vulnerability form.
github.com/CloudLLM-ai/menti…
9
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!
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.

















