Загрузка видео...

Не удалось загрузить видео

На главную

Introducing SelfGraph. The open source framework for building agent graphs. Turn unstructured text into a graph your agents can query. Every fact keeps its source. Same framework. Any graph store. Link in comments.

28,769 просмотров • 4 дней назад •via X (Twitter)

Комментарии: 29

Фото профиля HydraDB
HydraDB4 дней назад

Repo Link :

Фото профиля aditya.
aditya.3 дней назад

AYOOOO FINALLYYYY

Фото профиля abhinav
abhinav4 дней назад

🔥 less go

Фото профиля Soham Ratnaparkhi
Soham Ratnaparkhi4 дней назад

Easiest way to graph anything Lesss gooo

Фото профиля Vyom
Vyom4 дней назад

Lessgoooo; excited for this !!!

Фото профиля Aditya Shrivastava
Aditya Shrivastava3 дней назад

Graph it out!

Фото профиля Eshwar Prasad Yaddanapudi
Eshwar Prasad Yaddanapudi3 дней назад

Been following @hydra_db from your launch video. This is a great direction. Congratulations!

Фото профиля Ani (YC F26)
Ani (YC F26)3 дней назад

its funny to see the stars on repo at 300 in the morning and now at 48. why would someone go back to unstar it?

Фото профиля Jayking♟️
Jayking♟️4 дней назад

Love these Can I build with you guys early

Фото профиля Chen
Chen4 дней назад

every fact keeping its source is such a good call. way too many agent graphs just lose all provenance.

Фото профиля Lane Henslee
Lane Henslee4 дней назад

The notes file my agents pass from one run to the next is capped at 3,000 characters, so it has room for a fact but not for where the fact came from

Фото профиля HydraDB
HydraDB4 дней назад

Use

Фото профиля Nox
Nox4 дней назад

every fact keeping its source is the whole point tbh

Фото профиля Harsh
Harsh4 дней назад

🚀🚀

Фото профиля Cole Whitman
Cole Whitman3 дней назад

Turning unstructured data into reliable, traceable knowledge is a big win for AI agents.

Фото профиля Zo
Zo4 дней назад

Can you query what the agent knew at the time, separately from when a fact was true? Thinking of a correction learned today that gets backdated to last week.

Фото профиля Yashas
Yashas3 дней назад

@SohamR_7113 Who’s the lead at hydra? (pref cto, ceo) hmu

Фото профиля FutureTechTeller
FutureTechTeller3 дней назад

Every fact keeps its source. The only feature that matters for audit-sensitive environments. I would run the same provenance checks on factory data pipelines and digital twin layers.

Фото профиля Vasu Pal
Vasu Pal4 дней назад

@graphify ?

Фото профиля Grumpy
Grumpy4 дней назад

traceability per node makes checking wrong answers trivial, merging conflicting claims is where these usually break

Фото профиля Prakalp Choubey
Prakalp Choubey3 дней назад

graph for graphs?

Фото профиля HydraDB
HydraDB3 дней назад

Graphs for “everything” that is scattered and disconnected 😉

Фото профиля Snazzie
Snazzie3 дней назад

Hasnt graphs been proven to not help? atleast it hasnt helped me

Фото профиля HydraDB
HydraDB3 дней назад

Well, give us a try. There's something waiting for you on the other side 😉

Фото профиля Smobile
Smobile3 дней назад

keeping the source on every fact is the part that matters

Фото профиля Raviv Golov
Raviv Golov4 дней назад

Every fact keeps its source" is the feature that matters. Graph RAG without provenance is just confident hallucination with extra hops. Being store-agnostic also means nobody has to migrate their graph DB just to try it.

Фото профиля 生晓bai
生晓bai3 дней назад

Keeping the source attached to every fact is the part most agent-memory demos conveniently skip.

Фото профиля Aivatar
Aivatar3 дней назад

Turning unstructured text into queryable agent graphs with source attribution attacks the exact pain point of RAG — answers without receipts. The attribution part is what makes this usable in real work: you can check where the graph got it. How does it handle conflicting sources in the same corpus?

Фото профиля Gunmay Jhingran
Gunmay Jhingran3 дней назад

Lets goo 🚀🚀

Похожие видео

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:

Andrew Ng

169,184 просмотров • 1 год назад