THE CREATOR OF OBSIDIAN JUST TURNED YOUR NOTE VAULT INTO AN AI AGENT.
Not a plugin.
Not an integration.
A full agent skills system that teaches Claude Code, Codex, and OpenCode to READ, WRITE, and REASON inside your Obsidian vault like a power user.
27,000 GitHub stars in days.
Here is what shipped at launch:
obsidian-markdown — wikilinks, embeds, callouts, properties, the full Obsidian flavor Claude now understands natively.
obsidian-bases — Claude can create .base files with views, filters, formulas, and summaries.
json-canvas — Claude builds .canvas files with nodes, edges, groups, and connections.
obsidian-cli — Claude controls your vault, develops plugins and themes directly from the terminal.
defuddle — strips web pages into clean Markdown so you stop burning tokens on clutter.
Install the whole thing in one line:
npx skills add https://t.co/mHDEvCNOIC
Then connect it to Claude Code, Codex, or OpenCode.
That is it.
Your second brain now has an agent inside it that understands how Obsidian actually works.
Not a generic AI that pastes text into files.
An agent that knows what a wikilink is. What a callout is. What a canvas is.
Built on the open Agent Skills spec. MIT license. Free forever.
The gap between people using Obsidian as a note app and people using it as an AI operating system just got wider.
Bookmark this before you open your vault today.
Follow @cyrilXBT for every build that changes how Obsidian and Claude work together.
some new and old ways I'm exploring for how to improve AI skills:
- Peter Steinberger's Agent Scripts: https://t.co/UKznGdKm4z
- this paper https://t.co/wJSJZpTfbz
- I keep going back to autoresearch for tuning skills, having made a lot of mistakes in the past:
A 19-year old broke into India's largest high school examination system of 2M+ students a year, the CBSE, and was able to view and CHANGE any students' marks.
He responsibly wrote to the team 3 months ago, and it took them 3 days to fix only one of the issues. Today, they took the entire website down.
This is a absolute embarrassment. The futures and lives of millions rests in the hands of the utterly incompetent. There is also no mass media reporting on the matter.
This topic is close to me because not only is this the education system I went through, but 12 years ago and silently for 5yrs since, I'd written about and reported a much less severe vulnerability allowing me to scrape these results too. More than a decade later, not much has changed.
This 19yo, Nisarga Adhikary, wrote a great piece outlining each vulnerability he reverse engineered:
- the master password leak
- the client-side 2fac / OTP validation workaround
- tokenless access to the entire internal app (dashboard, evaluator details, etc) setting dummy browser values
- changing any password without knowing the old one
- an IDOR vuln allowing you to act as any user and edit exam marks
For those interested in a beautiful study in security breaches, this is a must read (link below).
If there's any light at the end of the tunnel, it's that a 19yo who never went to college can do things 99% of top engineers couldn't figure out.
🚨 CEO Anthropic Dario Amodei właśnie dostał nokaut na oczach całego świata.
Chiński founder Moonshot AI Yang Zhilin wziął i wrzucił za darmo całą rewolucyjną architekturę Kimi Agent Swarm.
Rój ponad 100 agentów działających równolegle. 1500 wywołań narzędzi jednocześnie.
Zadania, które Claude 4.5 i GPT-5.2 robią w godzinę, Kimi załatwia w 15 minut.
40-minutowy masterclass na NVIDIA GTC, w którym Yang tłumaczy wszystko krok po kroku:
• Orchestrator + parallel reinforcement learning
• MoE na bilionach parametrów
• Kimi Linear i 3D-synergia kontekstu
Efekt?
Kimi K2.5 miażdży Zachód w kluczowych benchmarkach agentycznych (HLE-Full, MathVista, OCRBench, multimodal) i robi to 4–5× taniej.
The 10 fastest growing GitHub repos this week:
1. codegraph (+14.1K stars)
Pre-indexed code knowledge graph for Claude Code, Codex, Cursor, OpenCode, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
https://t.co/PmnpMlGC3r
2. openhuman (+17.1K stars)
Your Personal AI super intelligence. Private, Simple and extremely powerful.
https://t.co/mrpvMxUFwe
3. academic-research-skills (+11.6K stars)
Academic Research Skills for Claude Code: research → write → review → revise → finalize
https://t.co/dek8R1gZIu
4. RuView (+6.8K stars)
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
https://t.co/UILhiVpLyX
5. agentmemory (+6.9K stars)
#1 Persistent memory for AI coding agents based on real-world benchmarks
https://t.co/KttGKncznV
6. supertonic (+3.6K stars)
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
https://t.co/LA0oJzR5Hf
7. CloakBrowser (+7.0K stars)
Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.
https://t.co/smRQh0wY3u
8. ViMax (+2.7K stars)
"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"
https://t.co/Jp53BzC0rK
9. 12-factor-agents (+1.9K stars)
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
https://t.co/qMqRwXa7iu
10. bun (+2.0K stars)
Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one
https://t.co/UAtNVbQlBd
The theme this week: agent memory, context efficiency, and on-device intelligence are making AI infrastructure the hottest build category.
Bookmark this. Next week's list will look completely different.
Boris Cherny, the creator of Claude Code at Anthropic, just explained why single-agent workflows are already dead
in this talk he breaks down exactly how the future is teams of agents, not better prompts:
- the 14% you lose to CLAUDE.md before typing a word
- one agent researching. one building. one reviewing. one orchestrating
- the architecture that separates hobbyists from real builders
- the 3 properties every agent team needs to actually survive
if you've been using Claude for more than a month and never left the chat window, you've been using one agent when you could be running a team of them
instead of another show tonight, watch this
make sure to bookmark it before it gets lost in your feed
the guide is in the article below
Anthropic engineer showed how one person can run 5 AI agents, that code, test, review, and deploy at the same time.
In 30 minutes they built the whole thing live in one session.
Here's what they cover:
> when to use one agent vs a full team
> how to split work so agents don't step on each other > the exact framework for deciding what each agent handles
that's exactly why, I put together a guide on building agent teams that actually work.
full guide in the article below 👇
Six months ago my Obsidian vault had 2,000 notes and I could not find anything.
I rebuilt the entire structure in one afternoon using this exact system.
I have not lost a single idea since.
The people who set this up today will wonder how they ever worked without it.
“design a RAG pipeline for 10M docs with zero hallucination”
apparently this was asked in a Google L5 interview round. came across it somewhere on the internet and honestly it’s a way more interesting system design problem than most classic distributed systems questions
1. ingest + normalize docs
- remove duplicates, standardize formats, extract metadata, maintain version history
2. hybrid retrieval (BM25 + embeddings)
- BM25 handles exact keyword matching while embeddings capture semantic meaning
- semantic search alone usually struggles with precision at massive scale
3. ANN retrieval + reranking
- ANN (Approximate nearest neighbor ) quickly pulls top candidate chunks from millions of docs
- then a reranker rescoring step improves relevance by deeply comparing query vs retrieved chunks
4. source confidence scoring
- every retrieved chunk gets scored based on freshness, trust level, overlap and retrieval consistency
- low-confidence context should never heavily influence generation
5. constrained generation
- the model is only allowed to answer using retrieved context (nothing new to be invented outside of the retrieved context)
6. citation-backed responses
- every major claim links back to exact chunks, documents or timestamps
7. hallucination fallback layer
- if retrieval confidence drops below a threshold: “insufficient evidence found”
8. continuous evals
- run adversarial queries, retrieval recall benchmarks and hallucination tests continuously
9. caching + memory layer
- cache high-frequency enterprise queries and retrieval paths (improves latency and output)
10. observability everywhere
- trace retrieval paths, chunk rankings, token attribution and failure points
Also at 10M docs, retrieval quality matters more than the frontier model itself.
Stop telling Claude, “write the function.”
Stop telling Claude, “fix this error.”
Stop telling Claude, “make the tests pass.”
You’re treating a billion-dollar AI engineer like Stack Overflow with autocomplete.
Here are 11 insane coding prompts you can copy-paste right now:
The "Explain Like I Ship This Tomorrow" prompt:
"Explain [concept/library/pattern] to me in 3 layers:
Layer 1: The 30-second version a PM would understand
Layer 2: The 5-minute version with code examples
Layer 3: The deep dive with trade-offs, gotchas, and when NOT to use it
Skip the textbook stuff. Give me what I need to ship."
The fastest way to actually learn.
The "Rubber Duck on Steroids" prompt:
"I'm going to explain my approach to [problem]. Don't write code yet.
Your job:
→ Ask me 5 clarifying questions about my assumptions
→ Point out flaws in my reasoning
→ Suggest 2 alternative approaches I haven't considered
→ Tell me what I'm overcomplicating
→ Tell me what I'm underestimating
Be a senior engineer mentoring a junior. Be honest."
Better than any pair programmer.
The "Refactor Without Breaking Shit" prompt:
"Refactor this code with surgical precision:
1. List every function that calls this code
2. Identify all side effects and dependencies
3. Show me a before/after diff
4. Explain what could break in production
5. Write the migration path
Treat this like a deployed system, not a toy project."
This is how senior engineers actually refactor.