Colin Francis

39 posts

Colin Francis banner
Colin Francis

Colin Francis

@colifran_

software engineer @LangChain, prev @awscloud

San Francisco Bay Area Katılım Şubat 2026
62 Takip Edilen74 Takipçiler
Colin Francis retweetledi
Harrison Chase
Harrison Chase@hwchase17·
📕LLM Wiki Webinar with @BraceSproul @devstein64 @jeffreyhuber is now on YouTube! Two of my favorite insights from this webinar: "Wiki as a cache" - @devstein64: basically, the purpose of a wiki is to keep things that are commonly looked up or accessed more top of mind/readily available. What goes in the wiki should be updated and organized with that in mind "Wiki is a set of hyperlinked pages" - @jeffreyhuber. The evolution of memory (in my view) has gone from: 1. single string 2. file 3. set of files in a directory (wiki) as you think about scaling up - as files grow, the file structure matters less, and you need links between pages. The internet is a set of hyperlinked pages - so that definitely scales! Watch it here: youtube.com/watch?v=Lsut4T…
YouTube video
YouTube
Harrison Chase tweet media
English
10
5
49
5K
Colin Francis retweetledi
Brace
Brace@BraceSproul·
OpenWiki now supports ChatGPT login!! Use your subscription instead of API credits when running OpenWiki Thank you @Topzsixx for the contribution to add support! Try it out today 👇
English
6
6
56
4.1K
Colin Francis
Colin Francis@colifran_·
in case you missed it OpenWiki v0.1.1 hit yesterday with some great new features and quality of life improvements shout out to @TopZSix1 for adding ChatGPT account sign-in so your model usage can now pull from your existing ChatGPT Plus/Pro/Team Codex allowance!! we love building this with our community!
Colin Francis tweet media
English
1
2
7
1.4K
Colin Francis retweetledi
LangChain
LangChain@LangChain·
LangChain is hiring. ✅ Engineering ✅ GTM ✅ People + Finance ✅ Product Check out our open roles + apply today ⤵️ langchain.com/careers
English
6
9
65
10.1K
Colin Francis
Colin Francis@colifran_·
langchain cooking again this week with launches 🔥
Harrison Chase@hwchase17

🚀langchain launches this week: all about open source models and memory! First: open source models. We partnered with @NVIDIAAI to launch a NemoClaw DeepAgents blueprint. This pairs Deep Agents (our open source, model agnostic harness) with Nemotron 3 ultra (powerful OSS model) and OpenShell (enterprise ready run time). Blog: langchain.com/blog/langchain… Second: memory. LLM wikis continue to intrigue us. @BraceSproul @colifran_ released a new version of OpenWiki focused on "personal brains" - creating wikis from gmail, internet, etc: github.com/langchain-ai/o… open models and memory pair well together as well. They both contribute towards companies and enterprises owning their whole stack - from the model level all the way up to the context level

English
0
1
6
897
Colin Francis
Colin Francis@colifran_·
great viz by @BraceSproul to put this in perspective. the really important part of this is that OpenWiki is additive!
Brace@BraceSproul

OpenWiki general purpose memory is meant to be complementary to codex/claude code memory: it's proactive & ambient, meaning it'll automatically go out into your world (via connections like gmail, x, notion, etc), discover what you're working on or interested in, and remember it for future reference this paired with reactive memory (codex/claude memory) leads to an incredibly powerful agent that knows everything about you to have truly comprehensive memory, you can't stick with one or the other since both types are useful and important

English
1
2
9
2.8K
Colin Francis
Colin Francis@colifran_·
@HxHasNoMemory right now we have code brain and personal brain but we're thinking a lot about what's next - org brains? remote brains? love all these ideas
English
0
0
0
13
Colin Francis
Colin Francis@colifran_·
OpenWiki Brains v0.1.0 is out 🎉 personally really excited about personal brains! these maintain context about you and what you're working on, interested in, etc. webinar for all things wiki happening now: events.langchain.com/webinar/llm-wi…
Brace@BraceSproul

OpenWiki Brains 0.1.0 is officially released! We added a general-purpose memory brain to OpenWiki, in addition to the existing code brain. You can now use it to seamlessly setup a personal brain to track everything you do and are interested in. OpenWiki brains are the easiest way to setup automatic memory agents for both codebases and general-purpose memory. Try it out today 👇

English
1
2
9
2.9K
Colin Francis
Colin Francis@colifran_·
@eggbaby totally agree and part of the reason we're thinking hard about things like evals for this. i think forgetting is actually a feature for any memory system. i've seen issues memory drift, memory poisoning, etc. in other memory systems i've helped build
English
0
0
0
13
Eggb4by
Eggb4by@eggbaby·
@colifran_ The part I'd want to test is forgetting. When a source changes, does OpenWiki know what to update or remove? Proactive memory gets messy fast if old context keeps winning.
English
1
0
0
29
Colin Francis
Colin Francis@colifran_·
agent memory has always been reactive. OpenWiki makes it proactive. connect to sources, tell it what you care about, and your agent hits the ground running . what we're building is really exciting! try it out and get involved, it's open source! 👇 github.com/langchain-ai/o…
English
1
5
34
22.1K
Colin Francis retweetledi
Alex Olsen
Alex Olsen@its_ao·
This is like a front row pass to some of the best minds in the industry Don’t miss @sydneyrunkle and @masondrxy in Boston on the 27th!!
Mason Daugherty@masondrxy

If you're in Boston, come hang out with us! @sydneyrunkle and I are hosting two talks on what it takes to make agents reliable in production: "The Art of Loop Engineering" — Sydney "Why Open Models Have Crossed a Threshold" — yours truly Harvard Square, July 27, 6 PM RSVP: luma.com/iaie4h2x

English
1
2
5
537
Colin Francis retweetledi
Viv
Viv@Vtrivedy10·
should agent memory be a map? 🗺️ would love to hear ppl’s take on this, basically: - models are exceptional at search and we should leverage this a ton when we think about organizing memory - wiki memory is like a map of important info that agents can search more deeply through. it is not really a collection of facts - maps align with inference time scaling and help agents reduce the search space by up front organizing where to look - the human brain memory retrieval is much more akin to mapping through concepts than it is storing a bunch of facts (not universally but predominantly) - i’m pretty bullish on markdown being able to encode a lot of hierarchies but see the allure of graphs, I think it’s unclear what the underlying data structure should be and how much traversal gives you would love to hear how ppl think about this, what optionality they want in open memory systems
Brace@BraceSproul

x.com/i/article/2075…

English
13
4
74
10.6K
Colin Francis retweetledi
LangChain
LangChain@LangChain·
OpenWiki now supports general-purpose memory, in addition to code via the new "brains" mode. We believe both codebase and personal wikis are incredibly important for providing your agent memory, but have distinct workflows for configuring and running them. Checkout our blog on the "brains" launch to see how we think about these two problems!
Brace@BraceSproul

x.com/i/article/2075…

English
3
4
45
8.7K
Colin Francis retweetledi
Viv
Viv@Vtrivedy10·
love what Brace is doing with open memory - fully transparent how it’s generated, can use open models too - integrates into your existing systems of work - complements memory systems like in Claude and ChatGPT - markdown first, take it wherever you want - updates with you over time
Brace@BraceSproul

x.com/i/article/2075…

English
2
8
37
8K

Keşfet

@BraceSproul @devstein64 @jeffreyhuber @Topzsixx @TopZSix1 @HxHasNoMemory @eggbaby @DavidROliver