"sem" : un outil CLI qui comprend votre code Git au niveau sémantique, diff, blame, impact et log par fonction plutôt que par ligne. 26 langages supportés, zéro config.
Herdr : un multiplexeur de terminal pensé pour les agents IA. Persistance des sessions, panes cliquables, attach SSH, et une API socket pour laisser les agents piloter leur propre workspace sans intervention manuelle.
Stumbled on "envio", a secure CLI for managing environment variables, built in Rust. 🦀
Instead of scattered .env files per project, envio lets you create named encrypted profiles and load them into any shell session or program.
Key features:
→ Encrypted profiles : multiple encryption methods supported
→ Load profiles into shell sessions
→ Run programs with specific profiles injected
→ Works on Linux, macOS, and Windows
Install via cargo, Homebrew, AUR, or Windows installer.
🔗 https://t.co/030mqeM0XE
#Rust #RustLang #CLI #DevTools
Claude Code feels completely different once you install this.
Anthropic quietly released an official plugin called claude-code-setup and it basically turns Claude Code from “pretty good” into an actual AI dev environment.
It scans your project and recommends:
→ hooks
→ skills
→ MCP servers
→ subagents
→ automations
Then sets everything up step-by-step for you.
Most people are using Claude Code completely vanilla…
which is why their experience feels messy.
The real power comes from the ecosystem around it.
Install:
/plugin install claude-code-setup@claude-plugins-official
Bookmark this before you forget it.
Loop programming has been SOLVED 👇
Use @herdrdev terminal + AgentBox on @E2B
Single prompt:
/goal work on the backlog md file, use several parallel agentboxes. Each one opening a PR and doing live browser tests. You will merge the ones ready at the end.
With Agentbox claude will spin a sandbox with all your files, dev server, db, env files, a browser and run a claude subagent inside, and babysits any plan questions, simple permissions prompts, and merging his PR at the end solving any conflicts.
If you try this workflow you'll never go back!
$ npm -g i @madarco/agentbox
$ agentbox install
$ agentbox e2b claude
# or
$ agentbox e2b codex
PostgreSQL 19 is getting graph queries.
With SQL/PGQ, you can query relationships directly in SQL:
→ social networks
→ recommendations
→ fraud detection
→ dependency graphs
Postgres is not just a relational database anymore.
It’s becoming the database for everything.
https://t.co/glzueH8NYf
Introducing Takumi v2 beta, the Rust engine that renders JSX to images without a headless browser.
- renderSvg() for SVG output
- On-demand Google Fonts: load only the subsets your content uses, as it uses them
- Language-aware text (ja/zh/ko Han unification)
- Redesigned font caching, no more race conditions
- New documentation
Try it today: bun i takumi-js@beta
Release day: Clapet est en ligne!
https://t.co/YzGBpQGd8j
J'ai construit le tool de System Design que j'aurais aimé avoir pour préparer mes entretiens.
Clapet te guide pas à pas pour construire une archi au lieu de te laisser seul devant un canvas vide a la Excalidraw.
Three skills I use every day in Claude Code and Codex to solve my hardest problems:
1️⃣ /agent-watchdog
When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread.
You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed.
It can also test the work of the other agent end-to-end.
Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one.
2️⃣ /plan-arbiter
Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute.
I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them.
Then I usually have Claude Code watchdog the Codex work and fix anything that was missed.
3️⃣ /read-the-damn-docs
One thing that drives me crazy with coding agents is they're so reluctant to look up docs.
They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things.
Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem.
So I made the /read-the-damn-docs skill.
Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for.
All of these are totally open source over on my GitHub. If you try them, let me know your feedback.
Will link to them below:
Introducing Clips - 100% free, open source, agent-native alternative to Loom
Unlike Loom, agent's can fully understand Clips just from a URL. Every Clip comes with APIs and metadata for agents to explore their contents.
Agents can "see and hear" anything in a Clip - not just transcripts, but everything visually in the video at any timestamp.
Easily share bug reports, feedback, analyses, or anything else in a way that you can easily pass to agents to use to improve products, reports, or more.
Also unlike Loom, you own the software, so no one can jack up prices on you suddenly like Loom did to us.
Clips is made to be customized. The built-in agent can customize its own code, so you can personalize the app to your needs and workflows.
This, in my opinion, is the future of software. Open-source, forkable, customizable with agents, to make your own personal version of anything.
You can also import Looms just from a URL and upload videos as well.
I got so sick of telling people "don't send me feedback as looms, I can't pass those to agents, I need text and images" that I had to just solve this once and for all.
There's a free hosted version you can use too, or fork and self host yourself. Will link to both in the replies.
In the next version of Bun
`bun build --react-compiler` runs the React Compiler in Rust
On a large React codebase, it's 19x faster than the Babel plugin
React Aria Components v1.19.0 is out! ✨
Autocomplete now supports inline completions (e.g. mentions), and a new Popover API enables positioning relative to the cursor.
Also, text inputs can now be nested inside GridList and Tree without interfering with arrow key navigation!
`sem` : un outil CLI qui remplace `git diff` par une vue sémantique — fonctions ajoutées, modifiées, supprimées — plutôt que des lignes brutes. Blame, impact, historique et contexte pour LLM inclus. 26 langages, zéro config. ⬇️
https://t.co/4jA6ist69G
How fast is Rust React Compiler?
On our benchmark, Rust React Compiler was 7x to 13x faster than Babel React Compiler in Rspack, comparing only the extra time added by React Compiler.