Go try axonDb!!
Memory that understands connections.
AxonDb stores memories as a graph and traverses it to recall connected facts, showing the path to the answer.
axondb.vercel.app
bro really said ‘let me see your homework’ 😭
Introducing supermemory's graph engine
yes. I did a graph. and yes, im against graphs. guess what
It's built ground-up from first principles (its not a real graph)
ALL you need for memory is:
- Keeping track of changing knowledge
- Forgetfulness on specific information
- Connections between information
We boiled the entire logic down into a single data structure. it can be represented as a filesystem, facts system, pages, or anything your agent / setup needs
This also allows us to magically find and inject tokens into the model harness without the model having to come looking for that information. Because
memory should be magical
and super intelligence needs @supermemory
AxonDB retweeted
hi guys! actively looking for 6M + PPO / FTE opportunities
if you come across an opening where you think i could be a good fit, or if you’re able to refer me, i’d genuinely appreciate it.
any leads, guidance, suggestions, or referrals would mean a lot. thank you :)
AxonDB retweeted
Launched free Java notes site 6 days ago, 54 visitors. Covers Core Java, Spring Boot, JUnit 5, Mockito, Microservices, Concurrency, JPA, Security, REST APIs. Free, no signup.
jvdocs.pages.dev
#Java #LearnJava #CodeNewbie
The entire memory layer runs locally.
Memories → embeddings → entities → relationships → graph → recall
Stored in a local SQLite database.
No login.
No API key.
No hosted memory service.
Your agent's memory stays on your machine.
And you don't have to interact with AxonDb in one specific way.
Use it through:
→ CLI
→ Local UI
→ MCP
→ Your agent environment
Plug it into agents like Claude Code, Codex, Claude Desktop and others.
The same memory layer sits underneath them.
axondb.vercel.app
And you don't have to interact with AxonDb in one specific way.
Use it through:
→ CLI
→ Local UI
→ MCP
→ Your agent environment
Plug it into agents like Claude Code, Codex, Claude Desktop and others.
The same memory layer sits underneath them.
axondb.vercel.app
So how does AxonDb work?
Instead of returning just the most relevant memory, AxonDb follows the connections around it.
→ relevant memories
→ connected memories
→ relationships between them
→ the path to the answer
More context. Better memory. Smarter agents.
Launching AxonDb : local memory for AI agents.
Memory that understands connections.
AxonDb stores memories as a graph and traverses it to recall connected facts, showing the path to the answer.
axondb.vercel.app
Launching AxonDb : local memory for AI agents.
Memory that understands connections.
AxonDb stores memories as a graph and traverses it to recall connected facts, showing the path to the answer.
axondb.vercel.app