Chris Bartholomew (@cdbartholomew) header
Chris Bartholomew (@cdbartholomew) profile picture

Chris Bartholomew

@cdbartholomew

Building Hindsight @Vectorizeio | Creator of @langstream_ai | Prev founder @kesquetech (acquired @DataStax) | Author @OReillyMedia

hindsight.vectorize.io
Joined August 2011
  • Tweets980
  • Following2.9K
  • Followers679
36Media
Photo by Chris Bartholomew (@cdbartholomew)Photo by Chris Bartholomew (@cdbartholomew)Photo by Chris Bartholomew (@cdbartholomew)Photo by Chris Bartholomew (@cdbartholomew)Photo by Chris Bartholomew (@cdbartholomew)Photo by Chris Bartholomew (@cdbartholomew)Photo by Chris Bartholomew (@cdbartholomew)Photo by Chris Bartholomew (@cdbartholomew)Photo by Chris Bartholomew (@cdbartholomew)Photo by Chris Bartholomew (@cdbartholomew)
Another big milestone for Hindsight! A tiny fraction of repos on GitHub every reach this level. Thanks to the @Vectorizeio team, our many contributors, and the community. A special thanks to @nicoloboschi , who has lead the way on the project and the community.
Vectorize (@Vectorizeio) profile pictureVectorize
@VectorizeioMay 29
Hindsight Hits 15,000 Stars: What's Shipped Since 10k

Hindsight Hits 15,000 Stars: What's Shipped Since 10k

Article · @Vectorizeio
1
9
555
Chris Bartholomew retweeted
PixelRainbow (@PixelRainbowNFT) profile picture
PixelRainbow
@PixelRainbowNFTNov 10
Replying to @nicoloboschi
Hindsight cloud runs my entire mental Model for my 7 device fleet, 1.4m facts and counting and it's been flawless. Their infra is strong
3
1
4
201
Chris Bartholomew retweeted
Vectorize (@Vectorizeio) profile picture
Vectorize
@VectorizeioNov 10
Hindsight 1.2.1 is out today - change embedding model live, no downtime - huge improvements on big banks across many internal ops - different embeddings model for search and storage (you can use @qdrant_engine Constella models now) - knowledge pages renamed to Pages and more: hindsight.vectorize.io/blog/…
3
8
1
48
3,255
Chris Bartholomew retweeted
Nicolò Boschi (@nicoloboschi) profile picture
Nicolò Boschi
@nicoloboschiNov 9
another banger from grok
Grok (@grok) profile pictureGrok
@grokNov 9
Replying to @nicoloboschi @illiteratewithd
Hindsight is the stronger choice for production. It has a year of Cloud use, reached 1.0 with a stable API and 99.9% SLA, plus Enterprise options (BYOC, on-prem, Memlake for 100M+ memories). Security, multi-bank sharing, and the reflect step are built for real agent fleets. MemPalace excels at local verbatim recall with zero external deps and high LongMemEval scores, and some teams run it successfully in constrained setups. It is less hardened for concurrent scale or managed reliability. Pick Hindsight when stability and proven multi-agent ops matter most.
1
2
11
509
Chris Bartholomew retweeted
Vectorize (@Vectorizeio) profile picture
Vectorize
@VectorizeioNov 9
Hindsight just hit 60k stars on Github!
2
1
20
724
Chris Bartholomew retweeted
Nicolò Boschi (@nicoloboschi) profile picture
Nicolò Boschi
@nicoloboschiNov 9
best memory for Hermes, people are saying it, not me
Image from Nicolò Boschi (@nicoloboschi)
Image from Nicolò Boschi (@nicoloboschi)
27
10
3
192
28,587
Chris Bartholomew retweeted
Nicolò Boschi (@nicoloboschi) profile picture
Nicolò Boschi
@nicoloboschiNov 6
run it your own huggingface.co/hindsight-ai or use our API inference.hindsight.vectoriz…
Image from Nicolò Boschi (@nicoloboschi)
2
5
200
Chris Bartholomew retweeted
Brad Trnavsky (@bmtrnavsky) profile picture
Brad Trnavsky
@bmtrnavskyNov 5
I just upgraded my local AI memory tonight. Hindsight 1.2.0 + GPT OSS 120B + hs-decide-1-flash handling recall, consolidation, and reflect. Hs-decide-1-flash is now assisting in Recall, Reflect, and Consolidation, so the big LLM gets 31% fewer LLM calls. Who else is running a persistent agent memory layer locally? What are you using? I have been VERY happy with #Hindsight. I hope these changes were worth it.
4
3
7
201
Chris Bartholomew retweeted
Nicolò Boschi (@nicoloboschi) profile picture
Nicolò Boschi
@nicoloboschiNov 3
this is the beginning of something new in the Memory space not only Hindsight can use decision models to get better in all the axis (cost, speed, quality) but we also train our own models now and we give them away FOR FREE mark my words: other memory systems will follow this train and copy us (as usual)
Vectorize (@Vectorizeio) profile pictureVectorize
@VectorizeioNov 3
Introducing Hindsight Models Hindsight memory is now 2.5x cheaper and 2x faster, with better answers. The LLM writes, a small decision model judges. Open weights on Hugging Face, or hosted on the new Hindsight Inference API.
2
2
15
605
I believe that in the future all software will be powered by custom-trained models. Because these models are purpose-trained, they can be smaller and faster than general-purpose models. Today Hindsight takes a step in that direction with our own set of models trained specifically to improve how Hindsight works. I am also happy to report that these models also do well on industry benchmarks. The models are open source, but we are launching inference API if you don't want the hassle of self hosting them.
Vectorize (@Vectorizeio) profile pictureVectorize
@VectorizeioNov 3
Introducing Hindsight Models Hindsight memory is now 2.5x cheaper and 2x faster, with better answers. The LLM writes, a small decision model judges. Open weights on Hugging Face, or hosted on the new Hindsight Inference API.
3
1
11
519
Dear Cold Email Bots, Asking me a "Quick Question" is a dead give away. You gotta come up with something better. You are AI, I know you can do it if you try.
2
1
120
🤔
Vectorize (@Vectorizeio) profile pictureVectorize
@VectorizeioNov 2
tomorrow. 8am pt.
3
145
Chris Bartholomew retweeted
Lurul (@CyberVu2r0n) profile picture
Lurul
@CyberVu2r0nOct 27
Replying to @DaveShapi
Have you tried hindsight? On a setep like Hermes? If you haven't, your missing out on an incredible memory system.
3
5
81
Nailed it
Nicolò Boschi (@nicoloboschi) profile pictureNicolò Boschi
@nicoloboschiOct 29
i asked Claude to build the best memory system then this happened
5
136
Chris Bartholomew retweeted
Domi (@frmdomi) profile picture
Domi
@frmdomiOct 28
started using Hermes 2 days ago today i'm installing tools i didn't even know existed just to make my agent stronger @Teknium your tool turned me into a nerd and there's no going back 💀
Image from Domi (@frmdomi)
16
7
1
84
6,942
Chris Bartholomew retweeted
Vectorize (@Vectorizeio) profile picture
Vectorize
@VectorizeioOct 28
"The software agent, however, was an amnesiac." Aditya Rana on solving their agent memory issue for good: medium.com/@adityarana9268/h…
How Hindsight Fixed My Safety Agent’s Check-In Memory

How Hindsight Fixed My Safety Agent’s Check-In Memory

Building an autonomous personal safety system quickly disabuses you of the idea that LLMs are ready for mission-critical tasks out of the…

medium.com
3
7
683
Hindsight: big name in memory for Hermes
Hermes Release Watch (@HermesWatcher) profile pictureHermes Release Watch
@HermesWatcherOct 28
Memory is the one Hermes setup everyone argues about. So here are 24 ways to give Hermes a memory, all in the official plugin catalog. Cloud, fully offline, plain notes or shared across every AI you use. Pick yours. The big names ▸ Hindsight github.com/vectorize-io/hind… ▸ Honcho github.com/plastic-labs/honc… ▸ mem0 github.com/mem0ai/mem0 ▸ OpenViking github.com/volcengine/OpenVi… ▸ Supermemory github.com/supermemoryai/her… ▸ Cognee github.com/topoteretes/cogne… Local and private ▸ Mnemosyne github.com/mnemosyne-oss/mne… ▸ Holographic github.com/itpartypattaya/he… ▸ Compartment github.com/MaxFreedomPollard… ▸ SuperLocalMemory github.com/qualixar/superloc… ▸ ReMe github.com/agentscope-ai/ReM… ▸ HyAtlas github.com/tuancookiez-hub/H… Notes, logs and wikis ▸ hwiki github.com/ottosulin/hwiki ▸ Memory Wiki (official) github.com/NousResearch/herm… ▸ GBrain github.com/kerrz2020/hermes-… ▸ OptMem github.com/rarf/optmem-herme… ▸ LCM-X github.com/electricsheephq/l… ▸ hermes-dreaming github.com/itpartypattaya/he… Cloud, shared and coding ▸ Memanto github.com/moorcheh-ai/meman… ▸ BetterDB github.com/BetterDB-inc/moni… ▸ Memoria github.com/matrixorigin/memo… ▸ Membase github.com/unibaseio/membase ▸ deja-memory github.com/vshulcz/deja-vu ▸ Sugar github.com/roboticforce/suga… Save this for the next time someone asks which memory to use.
Image from Hermes Release Watch (@HermesWatcher)
1
12
722
Chris Bartholomew retweeted
Vectorize (@Vectorizeio) profile picture
Vectorize
@VectorizeioOct 27
View article
X. It’s what’s happening

X. It’s what’s happening

From breaking news and entertainment to sports and politics, get the full story with all the live commentary.

x.com
2
6
446
Chris Bartholomew retweeted
Hermes Release Watch (@HermesWatcher) profile picture
Hermes Release Watch
@HermesWatcherOct 25
The #1 long-term memory for Hermes? A folder of notes. 138 Hermes users answered: ▸ Obsidian / Markdown vault: 27 ▸ Hindsight: 25 ▸ Honcho: 22 ▸ Built their own: 18 25+ tools named. Local beat cloud 28 to 2. Memory is still anyone's game. Every system ranked below.
Image from Hermes Release Watch (@HermesWatcher)
Hermes Release Watch (@HermesWatcher) profile pictureHermes Release Watch
@HermesWatcherOct 20
What are you using for long-term memory in your Hermes setup right now? Built-in memory, Honcho, Mem0, Hindsight, something else? What made you choose it?
26
29
1
462
29,571
Chris Bartholomew retweeted
Vectorize (@Vectorizeio) profile picture
Vectorize
@VectorizeioOct 21
Replying to @nvidia
@nvidia Nemotron 3.5 Embed is the new top embedding model on the Hindsight leaderboard. 93.8% recall@10 on LoCoMo, 65.9% on BEAM 100K, and the highest MRR of anything we have run end to end. Thanks to the @nvidia Nemotron team for the early access:
We Got Early Access to NVIDIA Nemotron 3.5 Embed. It's Hindsight's New Top Embedding Model.

We Got Early Access to NVIDIA Nemotron 3.5 Embed. It's Hindsight's New Top Embedding Model.

Article · @Vectorizeio
2
9
428
Chris Bartholomew retweeted
Nicolò Boschi (@nicoloboschi) profile picture
Nicolò Boschi
@nicoloboschiOct 21
toktok is the first library to have a @typesafeai jev tokenizer github.com/vectorize-io/tokt…
Image from Nicolò Boschi (@nicoloboschi)
3
5
288
Load more