john owlmann 🦉

🔎 Crypto gem hunter🦉💎 Helping you uncover hidden gems in the crypto world 🌐🚀 Shit Coin Maxi 10-1000x | Memecoin degen | Not financial advice, always DYOR!

[Tom Dörr @tom_doerr]

Auto-Deep-Research is an open-source alternative to OpenAI's Deep Research for fully automated personal AI assistance

https://t.co/1OKrvwv7qr

[Tom Dörr @tom_doerr]

PwnPad teaches hardware hacking through affordable PCB challenges covering UART analysis, firmware extraction, and side-channel attacks.

https://t.co/H0bgZUPeNQ

[Open-source Projects @the_osps]

This curated list provides training, resources, and tools for Android reverse engineering.

[elune @elune0x]

10 agent evals every AI engineer should know

1) golden set

a frozen set of cases you run after every prompt model or tool change

use it as your baseline to see whether the system improved or quietly broke

OpenAI Evals helps you build repeatable benchmark sets and compare model changes

→ https://t.co/dr1GZlC75R

2) llm as judge

a second model scores open ended answers against a written rubric

use it when there is no exact output to compare against

OpenEvals provides ready made evaluators for LLM applications

→ https://t.co/S2yhnByFIP

3) rubric scoring

score correctness tone safety and cost separately

one quality number hides the problem

DeepEval helps you create custom metrics and score every dimension independently

→ https://t.co/q9Z6Xmixia

4) trajectory eval

grade the path the agent took

not only the final answer

AgentEvals checks agent actions decisions and tool calls across the full trajectory

→ https://t.co/0oziAl54az

5) tool unit tests

test every tool with fixed inputs and outputs

no model in the loop

MCP Inspector helps you inspect and test MCP servers tools and responses separately

→ https://t.co/IVmt5qpWIN

6) regression suite

replay previous runs against every new prompt model or toolset

then compare the results

Promptfoo helps you run repeatable eval suites catch regressions and add checks to CI

→ https://t.co/zxi2PuWuhe

7) a b in prod

split real traffic between two versions and compare actual outcomes

GrowthBook provides feature flags controlled experiments and product analytics

→ https://t.co/DGlE3JjDD3

8) human review

sample real runs and let a person grade them honestly

use it to calibrate your automated judge

Argilla helps teams collect human feedback review outputs and build better datasets

→ https://t.co/QHWb7skWjr

9) shadow run

let the candidate run on real traffic while its output is shown to nobody

use it before a risky rollout

Langfuse helps you trace production runs compare candidates and monitor eval results

→ https://t.co/IrhDf38tRn

10) red team

attack the system before somebody else does

jailbreaks prompt injection data leaks and tool abuse

Garak scans LLM systems for vulnerabilities and unsafe behavior

→ https://t.co/w8ObyW4ZKv

offline evals tell you it works

online evals tell you it still works

you probably do not need all ten today

start with the two that would have caught your last outage

bookmark this

[Tom Dörr @tom_doerr]

Awesome Android Root provides a comprehensive collection of over 500 root applications and modules for Magisk, KernelSU, and LSPosed, alongside step-by-step guides to root various Android devices.

https://t.co/W4l24Nk74R

[Superman @thesupermanmx]

someone open-sourced a tool that turns any phone video into a full 3D world in real time.

you record a walk around your house, drop the mp4 in, and the entire scene comes back as a walkable 996k-point world at 60fps on your local GPU.

no cloud. no subscription. runs 100% locally.

100% open source.

[Fleece AI @fleeceai]

Forget Make.
Forget Zapier.
Forget n8n.

Meet AI-native automation.

Autonomous AI Agents.
3,000+ integrations.
Deploy your fist agent in 60 seconds.

🚀 Free to start.

[Simplifying AI @simplifyinAI]

ANTHROPIC AND OPENAI BOTH MISSED THIS.

Someone just open-sourced one SDK that gives AI agents a mouse, keyboard, and screen across macOS, Linux, and Windows.

It's called CUA.

Same code drives a local VM or a cloud sandbox regardless of the OS. Your agent sees the screen, clicks, types, and runs shell commands like a real user.

> Benchmark against OSWorld and ScreenSpot
> Export trajectories for model training
> Near-native performance on Apple Silicon

No separate SDK per OS. No infrastructure headache.

100% Free. Open Source.

[john owlmann 🦉 @JohnOwlmann]

🧐

[mousepotato @iluciddreaming]

AI Agent 终于可以免费上网搜索了。

wigolo：本地优先的 MCP 服务器，给 AI agent 完整的网络搜索和抓取能力，零 API 费用。

- 18 个搜索引擎同时跑
- 自动抓取和解析网页
- 本地 ML 重排序
- 结果自动缓存
- 遇到反爬网站自动切换无头浏览器

$0/次查询，不需要任何 API key。

[Tom Dörr @tom_doerr]

Built for agencies and solopreneurs, ai-marketing-claude brings 15 specialized skills to Claude Code. Users can run full marketing audits, generate copy, create content calendars, and produce client-ready PDF reports entirely through terminal commands.

https://t.co/ASlBCBir7O

[Sandeep @Sandeepg33k]

we kept rebuilding the same playwright wrapper for every customer.

open-sourced it so you don't have to.

[Tom Dörr @tom_doerr]

Family Trip Command Center is an open-source dashboard that manages group travel logistics through a command-center interface. The tool replaces standard planning methods by tracking convoy routes, simulating arrival times, and coordinating meals and activities for multiple families traveling together.

https://t.co/iU28zCJotH

[Tom Dörr @tom_doerr]

Generates 96,000 high-quality deep research trajectories and provides a fully open-source recipe for training agentic language models on long-horizon web research tasks without external API dependencies.

https://t.co/zUo5XOpZBb

[GitHub Projects Community @GithubProjects]

NeuTTS is an open-source collection of TTS models that run locally on-device with instant voice cloning from as little as three seconds of audio.

[Tom Dörr @tom_doerr]

A list of open source tools for deploying your own VPN, music streaming service, photo hosting, and more on personal infrastructure.

https://t.co/oebhnTGo47

[Charly Wargnier @DataChaz]

ANOTHER MASSIVE WIN FOR LOCAL AI 🚀

ICYMI @kyutai_labs quietly dropped a super lightweight Text-to-Speech application designed to run efficiently on CPUs.

Only 100M parameters. No GPU needed. Zero API fees 🤯

It completely bypasses the usual token-transformer bottlenecks to deliver wildly fast performance:

→ 6x faster than real-time on a Mac
→ ~200ms latency to the first audio chunk
→ Voice cloning from just 5 seconds of audio
→ 6 languages out of the box

Best of all?

It's 100% free and open-source.

MIT licensed and trained exclusively on public data.

Repo in 🧵↓

[‏ًً @selenarc_]

Alguien creó un Simulador de Diseño de Sistemas basado en web.

Copias y pegas (API gateways, bases de datos, cachés) y simula tráfico en tiempo real.

Puedes ver la latencia, los puntos de saturacion y los fallos mientras ocurren en directo...