Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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 Aufrufe • vor 4 Tagen •via X (Twitter)

29 Kommentare

Profilbild von HydraDB
HydraDBvor 4 Tagen

Repo Link :

Profilbild von aditya.
aditya.vor 3 Tagen

AYOOOO FINALLYYYY

Profilbild von abhinav
abhinavvor 4 Tagen

🔥 less go

Profilbild von Soham Ratnaparkhi
Soham Ratnaparkhivor 4 Tagen

Easiest way to graph anything Lesss gooo

Profilbild von Vyom
Vyomvor 4 Tagen

Lessgoooo; excited for this !!!

Profilbild von Aditya Shrivastava
Aditya Shrivastavavor 3 Tagen

Graph it out!

Profilbild von Eshwar Prasad Yaddanapudi
Eshwar Prasad Yaddanapudivor 3 Tagen

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

Profilbild von Ani (YC F26)
Ani (YC F26)vor 3 Tagen

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?

Profilbild von Jayking♟️
Jayking♟️vor 4 Tagen

Love these Can I build with you guys early

Profilbild von Chen
Chenvor 4 Tagen

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

Profilbild von Lane Henslee
Lane Hensleevor 4 Tagen

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

Profilbild von HydraDB
HydraDBvor 4 Tagen

Use

Profilbild von Nox
Noxvor 4 Tagen

every fact keeping its source is the whole point tbh

Profilbild von Harsh
Harshvor 4 Tagen

🚀🚀

Profilbild von Cole Whitman
Cole Whitmanvor 3 Tagen

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

Profilbild von Zo
Zovor 4 Tagen

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.

Profilbild von Yashas
Yashasvor 3 Tagen

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

Profilbild von FutureTechTeller
FutureTechTellervor 3 Tagen

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.

Profilbild von Vasu Pal
Vasu Palvor 4 Tagen

@graphify ?

Profilbild von Grumpy
Grumpyvor 4 Tagen

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

Profilbild von Prakalp Choubey
Prakalp Choubeyvor 3 Tagen

graph for graphs?

Profilbild von HydraDB
HydraDBvor 3 Tagen

Graphs for “everything” that is scattered and disconnected 😉

Profilbild von Snazzie
Snazzievor 3 Tagen

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

Profilbild von HydraDB
HydraDBvor 3 Tagen

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

Profilbild von Smobile
Smobilevor 3 Tagen

keeping the source on every fact is the part that matters

Profilbild von Raviv Golov
Raviv Golovvor 4 Tagen

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.

Profilbild von 生晓bai
生晓baivor 3 Tagen

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

Profilbild von Aivatar
Aivatarvor 3 Tagen

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?

Profilbild von Gunmay Jhingran
Gunmay Jhingranvor 3 Tagen

Lets goo 🚀🚀

Ähnliche Videos

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 Aufrufe • vor 1 Jahr