CongVC

545 posts

CongVC

CongVC

@cong_vc

Katılım Şubat 2020
146 Takip Edilen25 Takipçiler
CongVC retweetledi
priyanshu.sol
priyanshu.sol@priyanshudotsol·
someone wrote a 680 page interactive book on cs algorithms
English
83
1.3K
13K
700.2K
CongVC retweetledi
そう|Claude Codeで始めるAI自動化
セッションをまたいで記憶を保ち、経験から自分でスキルを作って育つAIエージェント Hermes Agent。ガチで使い倒すためのGitHubレポ10選: 21 Hermes Agent 本体 Nous Research公式のコアリポジトリ。MITライセンスで自由に使える。 github.com/NousResearch/h… 2. Hermes-Wiki Hermes Agentのソースコードを解説するコミュニティWiki。実装理解に効く。 github.com/cclank/Hermes-… 3. Atlas エコシステム地図。100+のツール・スキルを俯瞰でき、RAG検索にも対応。 github.com/ksimback/herme… 4. Control Interface セルフホスト型ダッシュボード。複数エージェント・長時間タスク・記憶を一画面で管理。 github.com/xaspx/hermes-c… 5. Skill Factory タスクを振り返って新スキルを自動生成・追加。エージェントが自分の武器を自製。 github.com/Romanescu11/he… 6. Maestro ローカル動作のマルチエージェント協調ツール。Codex・Claude Code・Geminiを横断して構造化記憶と引き継ぎを管理。 github.com/ReinaMacCredy/… 7. Hermes Agent Camel 信頼境界(CaMeL)を組み込んだフォーク版。本番運用の防護に向く。 github.com/nativ3ai/herme… 8. Hermes HUD TextualベースのTUI監視ターミナル。意識の流れとメモリ状態をリアルタイム可視化。 github.com/joeynyc/hermes… 9. Hermes Alpha クラウド環境向けのHermes Agentデプロイ用テンプレート。Makefileと設定例同梱。 github.com/kaminocorp/her… 10. Awesome Hermes Agent コミュニティ厳選のプラグイン・プロンプト・教材まとめリスト。 github.com/0xNyk/awesome-… 保存して順に試してみて。
そう|Claude Codeで始めるAI自動化 tweet mediaそう|Claude Codeで始めるAI自動化 tweet mediaそう|Claude Codeで始めるAI自動化 tweet mediaそう|Claude Codeで始めるAI自動化 tweet media
日本語
20
208
1.5K
72.8K
CongVC retweetledi
Jaewoong Eum
Jaewoong Eum@github_skydoves·
Published a new open-source project, Compose Performance Skills. ⚡️ This is a curated library of Agent Skills focused on Jetpack Compose performance. Every skill is grounded in primary sources. github.com/skydoves/compo…
English
1
21
157
4.5K
CongVC retweetledi
Dami-Defi
Dami-Defi@DamiDefi·
Claude Code cannot read 300 files at once. So someone built a system that lets it control NotebookLM from the terminal instead. The results are wild. Here is the full workflow nobody is talking about: The Setup → Claude Code connects to NotebookLM via a command line interface → Claude searches YouTube, finds relevant videos, uploads them as sources automatically → NotebookLM processes up to 300 sources simultaneously and returns cited, grounded answers → Everything syncs back into your Obsidian vault with passage-level citations you can click to verify Why This Changes Research Forever → No more 20 browser tabs you never close → No more copy-pasting outputs into random notes → No more hallucinated answers with no sources to back them up → 60% of citations verified as strong matches in accuracy audits - answers are grounded in real data What Claude Can Do From the Terminal → Search YouTube for relevant videos on any topic and rank by relevance → Create a new NotebookLM notebook and add 20 sources in parallel automatically → Ask questions and export cited answers directly into Obsidian with wikilinks → Set custom personas per notebook - concise, no filler, no preamble → Generate audio overviews and save them as MP3 files into your vault → Build mind maps, flashcard decks, and research dashboards from your sources → Search arXiv for academic papers and feed them directly into NotebookLM → Upload competitor blog posts, podcast episodes, PDFs, and your own vault notes The Obsidian Output → Every answer arrives with clickable citations that link to the exact passage in the source video or article → Graph view shows connections between all 20 sources and the topics they share → Q&A log tracks every question asked and the grounded response received → Source dashboard shows citation frequency, topics extracted, and which questions each source answered Use Cases Worth Building Today → Academic research with arXiv papers, full citation traceability → Competitor analysis from their YouTube channels and blog posts → Company knowledge base for onboarding, new employees ask NotebookLM instead of interrupting teammates → Podcast research, feed 4-hour Lex Fridman episodes and ask what's new in AI this week → Personal second brain, 300 daily notes uploaded and queryable in one notebook Before this system existed you needed 20 tabs, hours of manual reading, and no guarantee the answers were real. Now you type one prompt in the terminal and Claude does all of it for you. The research stack of 2026 is not a browser. It is a terminal connected to everything
English
41
156
1.4K
100K
CongVC retweetledi
Ivan Morgillo
Ivan Morgillo@hamen·
Good Monday, beautiful people. Jetpack Compose Audit Skill 1.5 is out. New compose-agent Flow reference: - StateFlow vs SharedFlow vs cold Flow - correct stateIn/shareIn usage - flatMap/combine/zip choices - durable UI state vs ephemeral events - no hallucinated Flow APIs
English
3
8
37
1.5K
CongVC retweetledi
Rahul
Rahul@sairahul1·
Karpathy didn't make a course. He made THE course. 3 hours. Free. Tokenization. Attention. Hallucinations. Tool use. RLHF. DeepSeek. AlphaGo. Every behavior you've ever wondered about in an LLM - where it comes from, why it exists, how it was engineered. The gap between engineers who understand this and engineers who don't isn't technical depth. It's the ability to conceive of entirely different things.
English
73
949
7.4K
616K
CongVC retweetledi
Khairallah AL-Awady
Khairallah AL-Awady@eng_khairallah1·
🚨 INSTEAD OF WATCHING NETFLIX TONIGHT. Spend 1 hour with this. Obsidian + Claude Code = 24/7 personal operating system. Works while you sleep. The people who build this tonight will never work the same way again. Watch it and Bookmark it now.
CyrilXBT@cyrilXBT

x.com/i/article/2046…

English
94
626
5K
777.8K
CongVC retweetledi
0xMarioNawfal
0xMarioNawfal@RoundtableSpace·
Anthropic's Head of Coding Agents research explains vibe coding in 30 minutes better than 100 paid courses. WATCH THIS NOW. THIS WILL CHANGE HOW YOU USE AI.
English
25
170
1.4K
163.5K
CongVC retweetledi
Geek Lite
Geek Lite@QingQ77·
基于 Karpathy 的 LLM Wiki 模式,将个人文档自动转化为结构化、相互关联的知识库桌面应用 github.com/nashsu/llm_wiki 这个应用基于 Karpathy 的 LLM Wiki 模式,用两步链式思考来处理文档:第一步 LLM 分析内容提取实体和关联,第二步生成 wiki 页面并更新索引。跟传统 RAG 每次从头检索不同,它的知识是增量构建、持久化保存的。
Geek Lite tweet media
中文
14
127
694
36K
CongVC retweetledi
Movez
Movez@0xMovez·
This 30-minute speech by the Head of Anthropic "Coding Agents" researcher will teach you more about vibe coding than 100 paid courses. Bookmark it & give it 30 minutes today. This video will change the way you use AI forever,
Movez@0xMovez

This weather bot turned $300 → $122K on Polymarket weather markets in 3 months I fully decoded algo and built a self-learning Hermes weather trading agent using weather APIs + Opus 4.7, the bot runs 5-min scans & searches mispricings on Polymarket run your agent in 5 steps: • set up a VPS server on Hetzner - $6 • create a weather API on {visualcrossing} - free • set up Hermes agent using one-liner code - free • connect Telegram bot + Opus 4.7 • send {weather trading logic} from article to agent started my agent 2 days ago with a test sum and already having 40% profit agent already caught 2 traders with +400% ROI on Seoul & Chicago weather markets bot used for logic: @coldmath?via=following" target="_blank" rel="nofollow noopener">polymarket.com/@coldmath?via=… my bot test wallet: @hermesweather?via=following" target="_blank" rel="nofollow noopener">polymarket.com/@hermesweather… Hermes bot is a self-learning agent so give him enought trades {100+}, to build his own logic. start small

English
89
1K
9.8K
1.6M
CongVC retweetledi
阿川 | AI thinking
阿川 | AI thinking@AI_jacksaku·
这个仓库今天爆了, 单日新增5700+星。 它是什么? 一个单独的CLAUDE.md文件, 整理了Andrej Karpathy关于LLM编程的观察和建议。 Andrej是谁? 前Tesla AI总监, OpenAI创始成员, AI领域最会写代码的人之一。 这个skill文件里有什么? LLM编程的常见陷阱 如何与AI结对编程 提示词工程的最佳实践 代码审查的AI辅助策略 简单说,就是AI大神的编程心法。 更狠的是, 这个文件可以直接丢给Claude Code, 让Claude按照Andrej的方式帮你写代码。 不是泛泛的"AI辅助编程", 是顶级工程师的思维模式注入。 为什么今天突然爆火? 因为大家发现, 用AI写代码和用好AI写代码, 完全是两回事。 这个skill就是 bridging the gap。 建议所有的开发者收藏 github.com/forrestchang/a…
中文
34
548
3.4K
330.6K