Cavezzan Patrice retweeted
Conductor is dead. Here are 69 alternatives. What are you using?
1. @orca_build · 115k★
2. T3 Code (@t3dotgg) · 47k★
3. Paseo (@moboudra) · 23k★
4. @useOrchestrator · 14k★
5. @paradevai · 16k★
6. cmux (@manaflowai) · 29k★
7. @emdashcom · 6.2k★
8. @RunMaestroAI · 3.5k★
9. @nimbalyst · 2k★
10. Zeron · 3.5k★
11. Jean (@heyandras) · 1.4k★
12. Xum (@codermux) · 2.1k★
13. @TraycerAI · 1.7k★
14. @get_bb_app · 4.9k★
15. Ghostex (@maddada) · 1.6k★
16. Kandev · 1.1k★
17. Parallel Code · 1.1k★
18. Supacode (@khoiracle) · 2.4k★
19. Termio · 752★
20. Pane (@parsakhaz) · 602★
21. Agent Teams AI · 2.4k★
22. wmux · 449★
23. OpenHarness (@autonomous_labs) · 1.4k★
24. Hive · 474★
25. Cate · 2.2k★
26. diri (@cristicrtu) · 483★
27. @NuphosAI · 351★
28. PandaCode · 1.1k★
29. @verdent_ai · 39k installs
30. Alethe · 1.1k★
31. agentglass · 347★
32. Waku (@localhost_5173) · 1.6k★
33. Kangentic · 139★
34. @vicoaai · 531★
35. ADE · 133★
36. Termic · 326★
37. Sculptor (@imbue_ai) · 245★
38. Poracode · 121★
39. DevThrottle · 107★
40. @zuse_sh · 243★
41. CCC · 215★
42. Agentbox · 345★
43. Hermes IDE · 346★
44. Maestri (@evertjr)
45. Termany (@idoubicc) · 498★
46. Frame (@jiuv__jiuv) · 455★
47. dev-3.0 · 324★
48. @usetempest · 196★
49. Kander (@dualface) · 171★
50. Prometeu · 65★
51. Frink · 183★
52. @superdoteng · 695 Discord
53. Lanes · 277★
54. Polyscope (@marcelpociot)
55. Agetor (@alamops) · 116★
56. Antumi · 94★
57. Ouijit · 177★
58. @agentastic
59. @glueprint_ai
60. @aidorothy1 · 357★
61. ManyAgents (@stulogy)
62. MAO (@miguerdotcom)
63. KanVibe · 149★
64. @veflowai
65. CodeAgentSwarm (@Art0xDev)
66. Tegment
67. Hyperlane
68. Jaade · 1.3k downloads
69. Muster
Cavezzan Patrice retweeted
Addy Osmani has an important warning for everyone using AI coding agents.
The better the output looks, the easier it becomes to stop questioning it.
In his latest article, he discusses cognitive surrender, a concept studied by Wharton researchers Steven Shaw and Gideon Nave. It describes what happens when an AI-generated answer quietly becomes your own conclusion without sufficient scrutiny.
He describes three stages:
→ Cognitive offloading: You delegate work but retain responsibility for the result.
→ Deferral: You begin treating the AI's answer as the starting point for your next decision.
→ Cognitive surrender: You accept the output without feeling the need to verify it.
The transition can be surprisingly gradual. You review one answer carefully, skim the next, and eventually approve changes you cannot fully explain.
His practical advice is to form your own hypothesis before prompting, examine the agent's assumptions, look for evidence that could disprove its conclusions, and maintain enough understanding to defend what you ship.
A useful reminder as more engineering work moves into autonomous agent workflows.
Cavezzan Patrice retweeted
Goの並行処理教材はgoroutine・channel・selectの紹介止まりか、パターンを説明なしに示すものが多い。本書はブラウザで動く500以上の例と自動テスト付き演習50問で、Context、Data races、Semaphores、Atomicsまで13章で解説。Go 1.26対応 / Gist of Go: Concurrency
antonz.org/go-concurrency/
Cavezzan Patrice retweeted
Goodbye map[string]struct{} 👋
Go's generic set proposal was just accepted. set.Set is still a map underneath, so range just works, but you get Insert, Contains, Union, Difference and more.
It lands first in golang.org/x/exp/collection/…
go.dev/issue/69230
Cavezzan Patrice retweeted
The many beat the money. The people beat the corporations and special interests. Hope beat hate and fear.
Michigan, we won.
Cavezzan Patrice retweeted
This is pure gold!
Abdul El-Sayed trolling Trump and JD Vance after winning Michigan’s Senate race:
“JD, habibi, there is this delicious irony in the fact that you’re constitutionally obligated to swear me in, in January.”
“Donald, look, I know you struggle with my name, so after JD swears me in, you can just go on and call me Senator.”
Cavezzan Patrice retweeted
Democrats will now control the House and Senate and be able to hold Trump accountable. That's great.
At a time of massive income and wealth inequality, we must do more. We must aggressively fight for working families.
No more excuses.
Cavezzan Patrice retweeted
PentAGI est un projet open-source sous licence MIT, permettant d’automatiser des tests d’intrusion avec des agents IA autonomes : orchestration de Nmap, Metasploit et sqlmap dans Docker, mémorisation des résultats et rapports de vulnérabilités ⬇️
github.com/vxcontrol/pentagi
Cavezzan Patrice retweeted
GraalVM 25.5 is here! 🎉
In this release:
— New compiler optimizations 🚀
— Improved observability and developer experience for Native Image 🛠️
— New capabilities powered by GraalPy and GraalWasm! 🐍🧩
Learn more: medium.com/graalvm/graalvm-2…
Download: graalvm.org/downloads/
Cavezzan Patrice retweeted
Our AI agent turned one ticket into a team of nine agents. A coordinator, a coder, reviewers and QA, each in its own Kubernetes pod, talking to each other until the work is done.
Full write-up on the @deel blog:
🔗 deel.com/blog/ai-agents-turn…
Cavezzan Patrice retweeted
Accéder à votre homelab depuis n'importe où, sans ouvrir de port sur votre box : je vous montre #NetBird, un VPN maillé WireGuard open source, serveur compris, auto-hébergé avec Docker.
▶️ Vidéo : youtube.com/watch?v=xh34amWw…
👉 Article : it-connect.fr/tuto-netbird-v…
#homelab #vpn
Cavezzan Patrice retweeted
a very good watch on LSM based storage engines and all the discussion around it like the tradeoffs, compaction strategies and performance
youtube.com/watch?v=hkMkBZn2…
Cavezzan Patrice retweeted
We benchmarked DeepSeek-V4.1-Flash-1017 GGUFs on Terminal Bench, DeepSWE & more on 512K context. Unsloth ranks highest overall.
1-bit Unsloth GGUF scores 68.1 on DeepSWE, 72.2 on Terminal-Bench, 52.7 on AutomationBench. >10% ahead of other quants.
GGUF: huggingface.co/unsloth/DeepS…
We’re releasing new DeepSeek-V4.1-Flash-1017 GGUFs, ranking highest across benchmarks.
Dynamic V3.1 leads across nearly all benchmarks: GPQA Diamond, AIME25, LiveCodeBench v6, MMLU-Pro, Aider & more.
Run on 64GB+ RAM.
GGUF: huggingface.co/unsloth/DeepS…
Blog: unsloth.ai/docs/models/deeps…
Cavezzan Patrice retweeted
I (or Claude actually) made an infinite canvas in MyGo under 1 hour, for absolutely no reason at all, it's like tldraw but in pure Go
github.com/egoist/godraw
Cavezzan Patrice retweeted
OpenObserve : une alternative open source à Datadog, Splunk et Elasticsearch, qui centralise vos logs, metrics, traces et RUM dans une seule plateforme.
Jusqu'à 140x moins cher en stockage grâce à Parquet sur S3.
Un seul binaire en Rust, lancé avec Docker. ⬇️
