🚨 BREAKING: A developer on GitHub just built a tool that turns any GitHub repo into an interactive knowledge graph and open sourced it for free.
It's called GitNexus. Think of it as a visual X-ray of your codebase but with an AI agent you can actually talk to.
No server. No subscription. No enterprise sales call.
Here's what it does inside your browser:
→ Parses your entire GitHub repo or ZIP file in seconds
→ Builds a live interactive knowledge graph with D3.js
→ Maps every function, class, import, and call relationship
→ Runs a 4-pass AST pipeline: structure → parsing → imports → call graph
→ Stores everything in an embedded KuzuDB graph database
→ Lets you query your codebase in plain English with an AI agent
Here's the wildest part:
It uses Web Workers to parallelize parsing across threads so a massive monorepo doesn't freeze your tab.
The Graph RAG agent traverses real graph relationships using Cypher queries not embeddings, not vector search. Actual graph logic.
Ask it things like "What functions call this module?" or "Find all classes that inherit from X" and it traces the answer through the graph.
This is the kind of code intelligence tool enterprise teams pay thousands per month for.
It runs entirely in your browser.
Works with TypeScript, JavaScript, and Python.
100% Open Source. MIT License.
Repo: https://t.co/RzIoLR2vAe
my @virtuals_io 60 day build in public challenge officially begins! 🙌🏾
excited to show you the process of building gymbot
an ai fitness agent that coaches you in real time!
i'm building an ai fitness coach agent as a total beginner
gymbot is an openclaw agent/skill that actually coaches you
updates so far - github repo set up , app working + photo is streaming the data live to the backend
tomorrow my @virtuals_io 60 day founders challenge officially starts let's go
Hiring for AI talent should start with a candidates projects.
It’s easier than ever to make hobby projects that showcase your understanding of a job role or business challenge.
I vibe coded a website that allows users to talk to Steam data to analyse the gaming market.
Data utilisation is a series of strategic questions that ultimately lead you to make better decisions - dashboards and excel are outdated!
Check out my MVP - https://t.co/RedKaBo6UX
I’d like to see Arteta be brave and try Lewis-Skelly in midfield, similar to how Pep has reshaped O’Reilly. I actually think MLS might be the in-house solution to our midfield issues. I’m not saying he has to start every week at 6, but give him a proper run there.
His ball retention is excellent, almost Saka-level secure in tight spaces. He can carry through pressure, break lines with passes, and create space for others. We’ve already seen glimpses of that in both the premier league and UCL. Pairing MLS with Rice in a double pivot could genuinely improve our ball progression from deep.
🚨 Prompt engineering is officially outdated.
Anthropic just released the real playbook for building AI agents that actually work.
It’s a 30+ page deep dive called The Complete Guide to Building Skills for Claude and it quietly shifts the conversation from “prompt engineering” to real execution design.
Here’s the big idea:
A Skill isn’t just a prompt.
It’s a structured system.
You package instructions inside a https://t.co/aldvvbZeVI file, optionally add scripts, references, and assets, and teach Claude a repeatable workflow once instead of re-explaining it every chat.
But the real unlock is something they call progressive disclosure.
Instead of dumping everything into context:
• A lightweight YAML frontmatter tells Claude when to use the skill
• Full instructions load only when relevant
• Extra files are accessed only if needed
Less context bloat. More precision.
They also introduce a powerful analogy:
MCP gives Claude the kitchen.
Skills give it the recipe.
Without skills: users connect tools and don’t know what to do next.
With skills: workflows trigger automatically, best practices are embedded, API calls become consistent.
They outline 3 major patterns:
1) Document & asset creation
2) Workflow automation
3) MCP enhancement
And they emphasize something most builders ignore: testing.
Trigger accuracy.
Tool call efficiency.
Failure rate.
Token usage.
This isn’t about clever wording.
It’s about designing an execution layer on top of LLMs.
Skills work across https://t.co/taoTr8bSkU, Claude Code, and the API. Build once, deploy everywhere.
The era of “just write a better prompt” is ending.
Anthropic just handed everyone a blueprint for turning chat into infrastructure.
Download the guide here: https://t.co/0SgDRAMhSg
Uber drivers with electric cars pulling up with their coat on, INSIDE their car??
These drivers refuse to use the heating to save electricity and we are suffering because of it 😫
City fans 💙
Please help me reach @ManCity.
My friend Khaleed Oladipo, a lifelong City fan, lost his life on 3rd Feb in Leicester. He was 20 years old kind and dedicated to his studies.
I’m hoping to organise an applause in the 20th minute at a match in his memory.
R.I.P💔
What a great day! Thank you to everyone who came out yesterday to celebrate with me, I wanna thank my old teammates for sharing a pitch with me one last time @DulwichHamletFC
🌟🏆BAFC AWARDS
The award voted for by the lads themselves, it’s the Player of the Season Award. This year it goes to our midfield general, @DejiOshilaja for his outstanding all round contributions to the team 💪
Award sponsored by @RaygarSupplies#BAFCAwards