7♋11

Detroit 313 to my city 😜Snap: JakeTonyy #Gaymer PSN: JakeTonyy

[Di Huang @dihuang111]

We open-sourced OhMyGame 48 hours ago. Today we have an amazing partner. 🤯

Say hi to Hyper3d 👋 Their 3D model is now built right into OhMyGame, and it's **FREE** for everyone, sponsored by @DeemosTech 🎁

This is the power of open source ❤️

https://t.co/OVFaPowG1y

[Dogxi @dogxii]

世界第一款开源游戏 Agent 工具 beta 测试版本已上线，LLM、图片生成、3D模型统统集合，游戏画布、程序、策划与美术统统搞定。官网上线地址：https://t.co/907lIVRvQS，欢迎体验！（测试阶段，可能有很多问题，还请见谅）欢迎在 GitHub 上点 star，提 issue！GitHub：https://t.co/6FxZrNhjd3

[Nano(ナノ) @Dstudio_ai]

Tripo P2.0 × Codexで1枚絵からキャラクターモデルを制作できる「きゃらくる/Charakuru」というキットを無料公開しました！
なんと、 Tripo様より正式にスポンサードしていただくことになりました！！！

Tripoだけでキャラクターモデルを制作しようとすると、顔がガビガビだったり、動きがおかしかったり、テクスチャが汚かったりしてしまいます…！
このキットはそれを解決します！

AIに丸投げするサービスではなく、エージェントをアシスタントとして共同でキャラクターモデリングをしていくタイプのローカルキットです！
GPT-6.1 Sol,GPT-6 AstraのComputer useを最大限生かしています！

丸投げしてしまうとクオリティがひどく、かといって人力でやると鬼ほどスキルが要求される問題の解決を目指しています。

自分がワークフローを共有したとしても再現性が無く、敷居も高かったので、いっそのことみんなが簡単に再現できるようなキットを作ってしまおうという感じで作りました！

僕が見つけたワークフローをローカルアプリやエージェントのSkillsに詰め込み、それをユーザーが再現できる形で配布しています。

動作にblenderを活用していますが、ユーザーが触ることはありません。
人間が行う必要のある作業は、アプリ上の簡単な操作で実現できるようにしています。

無料なのでぜひお試しください～！

※現在開発途中で足らない機能も多いですが、今後のアップデートで順次機能を追加していく予定です！

[Tech with Mak @techNmak]

AI Engineering Roadmap 2026

[rewind @rewind02]

here's how to build a game in Unreal Engine with Claude Opus 5.5...

the trick is letting Opus work inside the live editor, but there's a smart way to set it up:

- step 1: Unreal Engine 5 + the Third Person template, so you can walk and jump from minute one
- step 2: enable Unreal MCP and AllToolsets in the editor, start the server
- step 3: install Epic's plugin in Claude Code and have Opus read the project before it changes anything
- step 4: one prompt builds a playable base level: a valley, a dirt path, a town at the end, 3 glowing collectibles
- step 5: test the whole route with the default mannequin before any custom art
- step 6: bring in a rigged character on the UE5 Mannequin skeleton, Opus swaps it in and wires walk, run and jump
- step 7: import your forest and town assets, Opus places them along the route
- step 8: refine in small batches: vegetation, lighting, a minimap, the town entrance

and the rule that saves the project...

a successful tool call doesn't mean the level is right

check the editor after every batch, and never change terrain, lighting and character in one prompt

[Hermes Super-Intel @BkashJosi]

Before you build another Hermes cron job from scratch, type /blueprint.

@HermesWatcher surfaced 16 built-in automation blueprints.

The useful part isn’t the number. It’s how quickly a recurring idea becomes a real Hermes job.

My first 5 to try:

→ Morning brief
→ Important mail
→ News digest
→ Competitor watch
→ Weekly review

Run:
/blueprint

Or jump straight in:
/blueprint morning-brief

Hermes asks for the missing details, then you confirm before the job is created.

That’s the bridge from:
“I should automate this”
→ “Hermes runs it for me.”

Which blueprint should I test first?

[Mr. Buzzoni @Mr_Buzzoni]

I'm sharing with you one of the best papers I've read on Harness Engineering

it takes apart Claude Code (Opus 5.5), Codex, Gemini CLI and more, and boils all of them down to one line:

agent = model + harness

what you walk away with:
> what a harness actually is
> how today's coding agents are built under the hood
> the patterns every one of them repeats
> where the whole category is heading
> their checklist for building your own

the model gets the headlines. the harness decides whether the agent works

loop and graph engineering on top of it - in my article below

[Skytech Gaming @skytechgaming]

Our King 95 is our highest selling PC and it comes in all kinds of specs! Get yours today at Skytech Gaming!

[Rina @irinatoxi]

3D artists won’t like the math here.

I gave Opus 5.5 about 2 minutes inside Cinema 4D and got this.

Now imagine a scene you’d normally quote at $500.

If AI removes even a few hours of production, the client still sees a $500 result - but your margin looks very different.

That’s the real conflict.

But it might destroy the economics of charging for every hour spent clicking around.

[rewind @rewind02]

i built a small playable game in Unreal Engine with Claude Opus 5.5...

no blueprints by hand, Claude worked inside the running editor

the trick is the live connection, but there's a smart way to set it up:

- step 1: Unreal Engine 5.8 + a Third Person project, under source control
- step 2: enable Unreal MCP and AllToolsets, start the server
- step 3: install Epic's free plugin for Claude Code and start Claude in the project folder
- step 4: build a greybox level first: a path, a walled village, a tower you can see from the start
- step 5: add the rules: 3 orbs, a locked gate, "You made it", R to restart
- step 6: add one enemy, then health, then your attack, one feature per prompt
- step 7: only then make it look good: your character, real assets, lighting

and every prompt follows the same 4 rules...

- say what "done" means
- say what must not change
- ask for a list of everything it touched
- no silent workarounds: if it can't do it, it stops and says so

the full course is in the article 👇🏻

[Chiro Visuals @chirovisuals]

I built 9 opensource cinematic spells that run live in your browser with @threejs that you can use in your games or demons !

Live demo & source code :👇
https://t.co/3Og6GVGENT

- hand-written GLSL, GPU particles, real ragdolls that spells pin, tear, slice and corrode (no canned death animations), cast with your bare hands through your webcam

[Hermes Release Watch @HermesWatcher]

Bookmark this Hermes command cheat sheet for your next session.🔖

The new edition has a fresh layout, updated command guidance, and badges showing where commands work across Desktop, CLI, messaging, and the shell.

It covers useful controls like:

- /goal
- /loop
- /heartbeat
- /bg
- /btw
- /plan
- /review
- /refine
- /moa
- /busy

This edition also adds hermes pause and hermes resume to Terminal Essentials, expands the CLI queue guidance, and clarifies branching and saved sessions.

The sheet is organized around what you’re trying to do:

- Sessions & context
- Active work
- Goals, loops & plans
- Models & behavior
- Skills, memory & tools
- Automation & coordination
- Inspection, recovery & troubleshooting

Messaging/Gateway commands and Terminal Essentials are included, too.

Command names, syntax, and availability checked against Hermes source.

Keep it nearby when you need to queue the next task, steer a running job, or figure out what went wrong.

[Brij Pandey @LearnWithBrij]

RAG Design Patterns You Should Know in 2026🔥

Save it for later 🔖

[Don Coderlione @doncoderlione]

oyun yapmak istiyorsunuz ma 3D ortam modellemeyi hiç bilmiyorsunuz, buraya bakın

image-blaster diye bir Claude skill'i var, bir fotoğraf veriyorsun, gezilebilir 3D ortam çıkarıyor hem de ses efektleriyle birlikte

gpt 2.5 ile görseli oluştur > at buraya oyun ortamını oluştursun

blender öğrenmek için günlerini aylarını harcayanlar için üzgünüm

repoyu aşağıda paylaşıyorum

[Mnimiy @Mnilax]

China f*cked the world again

DeepSeek just dropped a killer library that saves up to 98% on tokens ur GPT Astra and Opus 5.5

it's DeepGEMM, the engine DeepSeek trains and runs its own models on

faster GPU math -> more tokens per GPU -> cheaper tokens

> plug the engine DeepSeek uses into your own models
> squeeze more tokens per second out of the GPUs you already pay for
> match or beat expert-tuned GPU libraries on speed

u will pay $1.6 instead of $50

its sitting in one public repo, link below

[Gauri Tripathi @GauriTripa94282]

8 RAG architectures you should know:

1. Naive RAG
2. Advanced RAG
3. Modular RAG
4. Graph RAG
5. Corrective RAG
6. Self-RAG
7. Adaptive RAG
8. Agentic RAG

From basic retrieval to self-correction and multi-step agents.

Know the architecture. Build better RAG systems.

#AI #RAG

[Leonard Rodman @RodmanAi]

10 GITHUB REPOS BRINGING AI INTO CYBERSECURITY

AI isn't just changing how we build software.

It's also changing how security teams find, test and fix vulnerabilities.

1. PentestGPT
AI assistant for reasoning through penetration testing workflows and findings.
https://t.co/9ZcItviCti

2. Caido
Modern toolkit for intercepting and analyzing web traffic during security research.
https://t.co/E2yv2L2Jge

3. HexStrike AI
Connect AI agents with cybersecurity tools through an MCP-based framework.
https://t.co/wVj3W9dqJ2

4. Strix
AI-powered security testing for investigating applications and finding vulnerabilities.
https://t.co/xlYhXK5975

5. Nuclei
Fast, template-based vulnerability scanner for applications and infrastructure.
https://t.co/Vr7yol06Oq

6. Semgrep
Code-aware security scanning that helps catch vulnerabilities before deployment.
https://t.co/UXshu3HJIF

7. Gitleaks
Find exposed API keys, passwords, tokens and other secrets in Git repositories.
https://t.co/gzbcvI0c3R

8. OWASP Amass
Discover domains, subdomains and infrastructure to understand external attack surfaces.
https://t.co/xpX7sLwzf2

9. Wazuh
Open-source platform for security monitoring, detection, vulnerability management and log analysis.
https://t.co/KzY46IlhYq

10. Prowler
Assess cloud environments against security best practices and compliance frameworks.
https://t.co/JYRDnoAogJ

Save these repos if you're exploring AI-powered cybersecurity.

[Promix @Promixyz]

AI security stack is getting f...cking important

10 open-source GitHub projects for letting agents use real tools without giving them the keys to EVERYTHING

01 E2B
▸ https://t.co/DrzCf9dj69
→ isolated sandboxes for agent execution

02 gVisor
▸ https://t.co/nuwxaXyQd3
→ sandbox untrusted workloads

ISOLATE THE AGENT

03 Firecracker
▸ https://t.co/M5EyDiSyPb
→ lightweight microVM isolation

04 Kata Containers
▸ https://t.co/1z6kgws9aX
→ containers with VM-level isolation

CONTROL THE TOOLS

05 Open Policy Agent
▸ https://t.co/852OIL1z5C
→ policy checks before actions execute

06 Casbin
▸ https://t.co/zjncieEueO
→ permissions + access control

PROTECT THE SECRETS

07 Infisical
▸ https://t.co/Wt9v5hKOro
→ secrets management for AI infrastructure

08 SOPS
▸ https://t.co/WDWZjquEgp
→ encrypted secrets inside repos

WATCH WHAT HAPPENS

09 Falco
▸ https://t.co/BXQUlwne2c
→ detect suspicious runtime behavior

10 Trivy
▸ https://t.co/S8LWn7YH88
→ scan code + containers + infrastructure

the security loop:

request → permission → sandbox → tool → execute → inspect → allow / block → log

3 layers I'd actually build:

agent:
E2B → OPA → Casbin
runtime:
Firecracker → Falco → Trivy
secrets:
Infisical → SOPS

and this is where it gets interesting:

giving an AI agent more tools makes it more useful
it also gives it more ways to break something

the next agent stack isn't just memory + tools + reasoning

it needs permissions ⭣

[kiosa @thegreatest_sv]

Holy sh*t, I wish I’d found this earlier.

someone put 300+ AI agent projects into one free GitHub repo

because half the time you think you need to build something new…

someone already built it.

agent memory? there.

browser control? there.

coding agents, sandboxes, evals, voice, multi-agent teams, local models?

all there.

so I went through the list and started connecting the pieces:

> RUN - Ollama runs the model locally
> BUILD - LangChain connects everything
> CODE - Aider + Continue work inside your codebase
> ORCHESTRATE - CrewAI + AutoGen manage the agent team
> ACT - E2B + Composio give agents tools and somewhere safe to run
> REMEMBER - Mem0 keeps memory between sessions
> WATCH - AgentOps shows what your agents actually did
> SHIP - Vercel AI SDK helps turn it into a real product

but here’s what clicked for me:

the list isn’t really a list. it’s a build-your-own-agent menu.

model -> framework -> tools -> sandbox -> memory -> evals -> product

missing something?

don’t spend the weekend rebuilding it.

find the category -> see what already exists -> grab 3 options -> check which one’s still alive -> start there.

and if you want to build on top of the list itself, they even give you the ecosystem data in JSON + YAML.

> no signup.
> no paywall.
> MIT licensed.
> 300+ projects in one place.

basically, before I build anything agent-related now, I’d check this repo first.

I pulled out the projects I’d actually start with + the best stuff from each category below

[kiosa @thegreatest_sv]

this is ultimate f*cking treasure.

20 open-source projects that basically give you the entire AI agent stack for free.

not just another “top AI tools” list.

together they cover the whole agentic loop:

BUILD

01 Ollama - run models locally ▸ ⁠https://t.co/bbPvy1btKB
02 LangChain - wire LLM workflows ▸ ⁠https://t.co/w2AdRxxPGg
03 Open Interpreter - let AI use your computer ▸ ⁠https://t.co/m42rPX3UMB
04 AutoGen - build multi-agent systems ▸ ⁠https://t.co/5leQUbSdBE
05 Aider - code with AI ▸ ⁠https://t.co/UjLV3aq4YZ

ORCHESTRATE

06 AutoGPT - autonomous workflows ▸ ⁠https://t.co/mK2fbGHB6Q
07 MetaGPT - software teams made of agents ▸ ⁠https://t.co/FEvhxdjPjN
08 CrewAI - coordinate specialized agents ▸ ⁠https://t.co/tVukPP8BMm
09 DSPy - optimize LLM pipelines ▸ ⁠https://t.co/yTxej7HI5Z
10 CAMEL - multi-agent collaboration ▸ ⁠https://t.co/15vpxKBpjy

ACT

11 Flowise - visual agent workflows ▸ ⁠https://t.co/yHqz6eKPoP
12 Continue - AI inside your IDE ▸ ⁠https://t.co/nPVsDDOJiE
13 Vercel AI SDK - ship AI apps ▸ ⁠https://t.co/ngeqtPP3jE
14 E2B - give agents a sandbox ▸ ⁠https://t.co/peIqKgWyKg
15 Composio - connect agents to real tools ▸ ⁠https://t.co/z0WxBpwlXN

REMEMBER · TEST · SHIP

16 PrivateGPT - private knowledge ▸ ⁠https://t.co/jQeb6RcggL
17 Mem0 - agent memory ▸ ⁠https://t.co/2AzDvOZElw
18 AgentOps - monitor agents ▸ ⁠https://t.co/seBG6fCh5C
19 AgentBench - evaluate them ▸ ⁠https://t.co/BfSngb42sG
20 ElevenLabs + Deepgram - voice in + voice out ▸ ⁠https://t.co/v1ZqYu3PEE▸ ⁠https://t.co/DsGanIwElC

the interesting part isn’t any single repo.

it’s what happens when you connect them:

model -> agent -> crew -> tools -> sandbox -> memory -> eval -> product

you don’t need to build an AI employee from zero anymore.

the pieces are already open source. you just have to assemble them.

save this before you build your next agent.