Loading video...

Video Failed to Load

Go Home

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 views • 4 days ago •via X (Twitter)

29 Comments

HydraDB's profile picture
HydraDB4 days ago

Repo Link :

aditya.'s profile picture
aditya.3 days ago

AYOOOO FINALLYYYY

abhinav's profile picture
abhinav4 days ago

🔥 less go

Soham Ratnaparkhi's profile picture
Soham Ratnaparkhi4 days ago

Easiest way to graph anything Lesss gooo

Vyom's profile picture
Vyom4 days ago

Lessgoooo; excited for this !!!

Aditya Shrivastava's profile picture
Aditya Shrivastava3 days ago

Graph it out!

Eshwar Prasad Yaddanapudi's profile picture
Eshwar Prasad Yaddanapudi3 days ago

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

Ani (YC F26)'s profile picture
Ani (YC F26)3 days ago

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?

Jayking♟️'s profile picture
Jayking♟️4 days ago

Love these Can I build with you guys early

Chen's profile picture
Chen4 days ago

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

Lane Henslee's profile picture
Lane Henslee4 days ago

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

HydraDB's profile picture
HydraDB4 days ago

Use

Nox's profile picture
Nox4 days ago

every fact keeping its source is the whole point tbh

Harsh's profile picture
Harsh4 days ago

🚀🚀

Cole Whitman's profile picture
Cole Whitman3 days ago

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

Zo's profile picture
Zo4 days ago

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.

Yashas's profile picture
Yashas3 days ago

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

FutureTechTeller's profile picture
FutureTechTeller3 days ago

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.

Vasu Pal's profile picture
Vasu Pal4 days ago

@graphify ?

Grumpy's profile picture
Grumpy4 days ago

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

Prakalp Choubey's profile picture
Prakalp Choubey3 days ago

graph for graphs?

HydraDB's profile picture
HydraDB3 days ago

Graphs for “everything” that is scattered and disconnected 😉

Snazzie's profile picture
Snazzie3 days ago

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

HydraDB's profile picture
HydraDB3 days ago

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

Smobile's profile picture
Smobile3 days ago

keeping the source on every fact is the part that matters

Raviv Golov's profile picture
Raviv Golov4 days ago

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.

生晓bai's profile picture
生晓bai3 days ago

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

Aivatar's profile picture
Aivatar3 days ago

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?

Gunmay Jhingran's profile picture
Gunmay Jhingran3 days ago

Lets goo 🚀🚀

Related 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 views • 1 year ago