Dwarves Foundation

Dwarves build and ship top-notch software for tech-focused companies across the globe since 2015.

Discord: 💻🎧☕

[Dwarves Foundation @dwarvesf]

📚Built on @0xPolygon, by our own engineers, $ICY takes co-creation within @dwarvesf Network to the next level. Join us, engage with us, learn with us, build with us, nurture the community with us, and get $ICY in return.

📌About ICY: https://t.co/tmO9Vq0iCr

[Dwarves Foundation @dwarvesf]

People run into this curve all the time. At some point you add scripts, helpers and small agents around it because it feels like progress. Then you realise you spend more time keeping that stack alive than shipping.

Image credit goes to @thorstenball

[Dwarves Foundation @dwarvesf]

Stagehand nails the middle ground: Playwright for deterministic steps + intent-based actions when UI shifts. A11y-tree targets > CSS. observe→preview, then act; extract(schema) for typed data; cache & replay.

Full breakdown by Chinh Le: https://t.co/erKCHBuLPz

[Stagehand @Stagehanddev]

We've built the best in house observability for Stagehand 🔭

Get inference time, token usage, LLM output, and more on the new dashboard.

No more black box, see everything behind the scenes.

See for yourself, get started with npx create-browser-app 🤘

[Dwarves Foundation @dwarvesf]

By Lap Nguyen (Frontend @ Dwarves): E2B explained. Firecracker microVMs run untrusted agent code with VM-level isolation and fast cold starts. Covers architecture, lifecycle, snapshots, quotas, scaling.

Check out: https://t.co/4Nfc0oXyTI

[kodk2807 @kodk2807]

Taking a shot at understading @e2b: https://t.co/rNC0AkxGSp

[Dwarves Foundation @dwarvesf]

Breakdown by Quang Huy (Backend @ Dwarves): Maybe Finance for self-hosted personal finance. Keys: Family as tenant root, delegated Account types, append-only Entry + anchor balances for correctness; 3-tier cache; SQL-level LOCF.

Details: https://t.co/V4UPO32Wqs

[huydtt.sol @huynq_sol]

I have a breakdown for Maybe
https://t.co/l2GgsiCmUp

[Dwarves Foundation @dwarvesf]

Agentic build on @dify_ai: tools with schemas (HTTP/DB). Loop: React or function calling + HITL checkpoints. RAG: hybrid + parent-child; chunk600, overlap100, top-k~8. Streaming on; retry with backoff. SSRF-safe proxy. DifySandbox.

https://t.co/s5RwRppGuP by @_zlatanpham

[Dify @dify_ai]

📚 Build Deep Research Agent: From Question to Insight

Complex research rarely fits in one search box. The Deep Research workflow built with Dify Iterates, reasons, and sources until the answer is complete.

💡 Key workflow nodes include:

1) Start: capture the research topic and the loop budget
2) Exa Answer: gather background terminology
3) Intent LLM: clarify the real research goal
4) Loop: drive the iterative cycles
5) Reasoning LLM: frame better follow-up questions
6) Agent: execute searches, extract content, and reflect
7) Variable Assigner: update the state after each pass
8) Final Summary: synthesize a Markdown report with citations

Teams using this template cut research time dramatically and surface insights competitors miss.

Learn to implement this workflow: https://t.co/M0liVPesWW

[Dwarves Foundation @dwarvesf]

Track traffic without GA4 or cookie banners and keep data ownership. Umami is a self-hosted, privacy-first alternative focused on minimal setup and end-to-end control.

Breakdown by Chinh Le (our frontend engineer): https://t.co/Toyk1E6ETP

[umami @umami_software]

Umami is now the most starred open source analytics project! And we launched later than everyone else 😎

A huge thanks to our community for making it happen. More great things to come! 🥳

#opensource #Analytics #GitHub

[Dwarves Foundation @dwarvesf]

MEM0: Modular memory for agentic AI

Decouples memory from inference. Graph-based reasoning, implicit forgetting, multi-backend storage.

+26% acc, -91% latency, -90% tokens vs OpenAI Memory.

Mem0 breakdown was composed by @minhlq96. Check out the link below.

[0xm @minhlq96]

Just making a breakdown about this great memory layer here https://t.co/k8YFbGr5cY

[Dwarves Foundation @dwarvesf]

Crawl4AI: clean Markdown (variants + citations) + typed JSON for RAG/agents. Pick speed (CSS/XPath/Regex) or accuracy (LLM schema). Anti-bot ready with Playwright + proxies; scales with browser pools + cache.

Our takes in the breakdown series: https://t.co/BUQUXl8n41

[Unclecode (Hossein) @unclecode]

Crawl4ai crossed 50K start 🌟 (~5k forks). Thanks to all who shared their love and support. A project I started to build a tool for my company turned into a lovable open-source project at this scale. It's so rewarding to be part of an authentic change. I like to believe Crawl4ai made a positive change in the life of many developers and shared success in many projects.

We already released new features such as adaptive crawling, link preview, web page change observer, URL seeders and a few more, which I will talk about them soon. Also another project of mine, an agentic crawler , which I have been working on for a while based on Crawl4ai, will be out.

I also announce the official account of Crawl4ai @crawl4ai please follow, and continue your support, definitely it motivates me and my collaborators.

https://t.co/VhN3NtRlen
https://t.co/6apdISAYzn
https://t.co/waAsHDjXaQ

I appreciate all the new friends I found on this journey for their support in spreading the word, and collaboration: @aravind_karnam @nasrintohidi @engineerrprompt @Sam_Witteveen @tom_doerr @MervinPraison @ozenhati @jasonzhou1993 @GithubProjects @omarsar0 @Saboo_Shubham_ @ai_for_success and many more.

Live Long and import Crawl4ai

[Dwarves Foundation @dwarvesf]

Cline brings structured tool calls, streaming diffs, and shadow commits to VS Code. We put together a developer-first breakdown, how it works, where it shines.

Written by Chinh Le (frontend @ Dwarves): https://t.co/hBWEoKLLmb

[Cline @cline]

👋 How to start using Cline in 2 minutes

(step-by-step thread 🧵)

[Dwarves Foundation @dwarvesf]

ax framework is a TypeScript port of @DSPyOSS. Instead of writing prompts directly, you can pass arguments to the framework and it will generate the prompts, which makes managing the semantics of the codebase a bit easier.

This piece is a part of the team’s breakdown series.

[P @vincentzepanda]

https://t.co/kORIQedGAq one of my favorite tool when building agentic apps. Read this if you're still on the fence about adopting DSPy.

[Dwarves Foundation @dwarvesf]

Why care?
- No more manual state management.
- Context sticks around, no matter how many tools you use.
- Workflows stay sharp and efficient.

[Dwarves Foundation @dwarvesf]

Most AI tools just stack models, but context and collaboration still get lost. zen-mcp-server by
@BusyMac gives Claude real multi-model memory, so your AI team actually works together, not in silos.

Here’s how we break it down at Dwarves: https://t.co/oGpqUUohwH

[Ian Nuttall @iannuttall]

Somebody hooked up Claude Code to pair program with o3 and Gemini 2.5 via MCP for an all-star coding lineup 🤯

- Claude controls the work
- Can call out to Gemini and o3 for tasks and input
- Works around MCP limit by using prompt files

Check out Zen MCP (link below)

[Dwarves Foundation @dwarvesf]

Use Cases
- Seamless cross-tool investigations.
- Reviving context after a reset.
- Getting consensus from different models.

[Dwarves Foundation @dwarvesf]

Meanwhile, I’m out here hitting Claude’s usage cap 3 times a day… and still not on the leaderboard.

We are, indeed, absolutely r̵i̵g̵h̵t̵ cooked. 👍

[Anthropic @AnthropicAI]

Some of the biggest Claude Code fans are running it continuously in the background, 24/7.

These uses are remarkable and we want to enable them. But a few outlying cases are very costly to support. For example, one user consumed tens of thousands in model usage on a $200 plan.

[Dwarves Foundation @dwarvesf]

Claude: I converted all 106 models flawlessly.
Reality: Literally none of them work.
AI delusion speedrun (any%) complete.

#devlife #techmemes #AIart

[Dwarves Foundation @dwarvesf]

Bro really took the MBTI test and said ‘I’m not like other browsers’.

#comet #Perplexity

[tom @monotykamary]

lol apparently comet is INFJ

[Dwarves Foundation @dwarvesf]

Me: I don’t need Claude Opus 4.
Also me after one code review session:
"$200/month is actually a steal."

#devlife #AIAgents