Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
🚨 STOP BURNING YOUR TOKENS!
If you use Claude Code, you are probably wasting 80% of your context window.
I found 10 ace tools that will completely rescue your API bill.
1. Caveman Claude
- Literally makes Claude talk like a caveman
- Slashes 75% of output tokens with zero loss in accuracy
Repo → github.com/juliusbrussee/cav…
2. RTK (Rust Token Killer)
- A blazing fast proxy that filters terminal output
- 60-90% reduction and completely dependency-free
Repo → github.com/rtk-ai/rtk
3. Code Review Graph
- Claude reads only what matters using a Tree-sitter graph
- An unbelievable 49x token reduction on huge monorepos
Repo → github.com/tirth8205/code-re…
4. Context Mode
- Sandboxes raw output into SQLite instead of your context
- A staggering 98% context reduction on logs & GitHub
Repo → github.com/mksglu/context-mo…
5. Claude Token Optimizer
- Brilliant setup prompts that optimize any project
- 90% token savings, taking docs from 11K to 1.3K
Repo → github.com/nadimtuhin/claude…
6. Token Optimizer
- Hunts down the invisible ghost tokens eating your context
- Fully restores and protects your context quality
Repo → github.com/alexgreensh/token…
7. Token Optimizer MCP
- Adds aggressive caching and compression to your MCP tools
- 95%+ token reduction through pure intelligence
Repo → github.com/ooples/token-opti…
8. Claude Context
- Zilliz’s hybrid vector search MCP
- Makes your entire codebase the context for 40% less cost
Repo → github.com/zilliztech/claude…
9. Claude Token Efficient
- Just drop one CLAUDE.md file into your repo
- Enforces strict terseness with zero code changes
Repo → github.com/drona23/claude-to…
10. Token Savior
- Navigates your code by symbols, not giant files
- 97% reduction on code navigation with persistent memory
Repo → github.com/mibayy/token-savi…
----
[ The god-tier stack ]
Pick 2-3 based on what’s draining you:
> Massive repo? Code Review Graph + Token Savior
> Heavy terminal output? RTK
> MCP data dumps? Context Mode
> Need an instant fix? Caveman + Claude Token Efficient
Most devs are bleeding tokens.
Run `/context` in a fresh session and watch the savings roll in 👀
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
Relations got most of our attention this summer.
Publishing warns you when a relation is still a draft. required on a relation is finally enforced at publish. And reordering holds, in the seven places it did not.
More from the summer releases 👉 strapi.link/4AdofQE
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
48 HOURS AFTER KARPATHY POSTED HIS LLM WIKI IDEA, A 26-YEAR-OLD BIRMINGHAM GRAD SHIPPED THE ONE COMMAND THAT MAKES IT WORK. IT NOW HAS 76,000 GITHUB STARS
1 command. 71.5x fewer tokens per query. 0 vector databases
points graphify at any folder - codebase, docs, PDFs, screenshots, video. Tree-sitter parses the code, Claude reads the prose, the whole thing lands as a knowledge graph in graphify-out/
one flag - --obsidian - writes the entire graph as a fully-linked Obsidian vault: one markdown note per concept, every relationship a wikilink, every node linked back to its source. Drop the vault into Claude Code as a skill. Claude queries the graph instead of grepping through raw files, forever
Safi Shamsi finished his MSc at Birmingham with Distinction in 2025. His thesis was a knowledge-graph RAG system for academic search. He shipped Graphify 48 hours after Karpathy's post, iterates every week, and has already been forked by Rootly AI Labs for incident data. Hacker News, Analytics Vidhya, Towards AI - all organic.76,000 stars. Three months old
no neo4j server. no vector db. no embedding pipeline. no cloud. no monthly fee
you're reading this on a device that could clone the repo, run one command, and have a Claude-native knowledge graph of your entire codebase in Obsidian before your next standup
This quoted post is unavailable.
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
Google acaba de soltar un curso de solo 1 hora sobre Ingeniería Agentiva que destroza a la mayoría de cursos de pago 🔥
Timestamps:
00:00 → Cómo construir tu primer agente de IA
08:24 → Memoria de agente (corta, persistente y larga)
28:34 → Bucles agentivos y agentes de larga duración
40:04 → MCP vs API (esto solo ya vale la pena)
1:00:22 → Sistemas multiagentivos
En 60 minutos aprendes más que en 10 cursos pagos. Míralo hoy. Luego lee el artículo y construye un sistema agentivo que se auto-mejora solo.
¿Lo vas a ver ahora o lo guardas para “después”? 👀
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
InfraLens is a zero-instrumentation observability tool that uses eBPF to automatically discover and visualize service-to-service communication in Kubernetes clusters without requiring code changes or sidecars
➜ ku.bz/FljwMJsXy
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
Intro to Machine Learning Systems book for FREE!
This book covers ML Systems, AI Workflows, Data Engineering and more.
To get your copy, do the following.
- Like and Repost
- Comment ML
- Follow me so that I can DM you.
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
Streaming-first language for model-generated UI
github.com/thesysdev/openui
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
Enhancing RAG with Application-Aware Reasoning
Neat trick to improve RAG systems: give it the relevant knowledge and show it how to apply it.
Very simple and effective!
This approach also works well with AI agents.
Pay attention, AI devs.
Here are my notes:
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
A RAG engine for deep document understanding!
RAGFlow lets you build enterprise-grade RAG workflows on complex docs with well-founded citations.
Supports multimodal data understanding, web search, deep research, etc.
100% local & open-source with 55k+ stars!
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
OpenAI, Google, and Anthropic just dropped the guides on:
- Prompt Engineering
- Building effective Agents
- AI in Business
- 601 AI use cases
and so much more...
9 best guides you don’t want to miss:
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
BREAKING: Email platforms are officially obsolete.
Mailchimp charges $300+ for what this open-source tool gives you free.
BillionMail gives you unlimited sending, full control, & no monthly fees.
Here’s how to set it up in 5 minutes:
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
SQLite-Vec: a tiny, portable vectorDB built on SQLite!
It's lightning fast & lightweight, perfect for on-device RAG solutions!
🔥 Key features:
- Matryoshka embedding slicing
- 32x storage reduction with binary quantization
- L2, cosine, and Hamming distance support
- Works with Python Lists and NumPy Arrays
🌐 Universal Integration:
SDKs for Python, JavaScript, Go, Rust, Wasm and more...
Best part? It's MIT/Apache-2.0 dual licensed. Use it, modify it, make it yours.
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
🚨BREAKING: A new Python library for algorithmic trading.
Introducing TensorTrade: An open-source Python framework for trading using Reinforcement Learning (AI)
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
Crazy what you can do on Hugging Face in 40 seconds
rejoiced by the rebirth of the skeuomorphic isomorphic 3D icons on @Airbnb I've trained a FLUX LoRA to generate 3D icons in that style
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
LETS GOO: Hugging Face just dropped the MCP Course everything you need to know about Model Context Protocol AND how to use it!! 💥
Sign up today - totally free and open source course!
From understanding what MCP is to connecting LLMs, to deploying your own MCP servers - we've got you covered! 🤗
Pierre-Eric Marchandet 🇫🇷🇪🇺 retweeted
LangChain just dropped the Figma of AI agents — fully open-source, no code, and insanely powerful.
This could be the game-changer for building custom AI workflows without touching a line of code. 🧠⚡
