Building a Telegram AI Agent for Personal Use
Build a personal AI agent in Telegram using Bun, Telegraf, SQLite, and Composio. Zero-infrastructure with conversation memory and prompt-injection defenses.
#Agents
4284 articles tagged with Agents
I Built a $0 Local AI Automation Stack: Agentic Coding + Market Data Over MCP
Serious AI-assisted development has a habit of turning into a stack of subscriptions: a...
Project Log #15: My AI Agent Just Completed Its First Multi-App Task
Day 15. The agent switched between two apps, copied data from one, and pasted it into another. For...
🔴 AI News LIVE 24/7 — Cyber City Media AI Desk | Tech & Agentic AI News Stream
LIVE 24/7 — AI news and tech news, all day. The Cyber City Media AI Desk tracks the newest AI models, agents, tools, and ...
Label-Driven Agentic Workflows: Building Autonomous Software Pipelines Without a Workflow Engine
TL;DR: Instead of building yet another orchestration layer, use the labels in your existing issue...
AI Hack並びにグループ会社Priv Tech、博報堂ＤＹグループ企業11社との戦略組織で運営する、エージェンティックコマース統合ソリューション「Agentic Commerce ONE™」に参画 https://www.yayafa....
AI Hack並びにグループ会社Priv Tech、博報堂ＤＹグループ企業11社との戦略組織で運営する、エージェンティックコマース統合ソリューション「Agentic Commerce ONE™」に参画 https://www.yayafa.com/2841302/ #AgenticAi #AI #AIHack並びにグループ会社PrivTech、博報堂ＤＹグル...
No Baked-In Behavior: Why Your AI Agent's System Prompt Should Be Yours
Every AI coding agent ships with hidden system prompts you can't change. Jean2 doesn't. Here's why that matters.
https://www.tkhunt.com/2438554/ An AI Agent Just Ran a Complete Ransomware Attack — No Human Involved #AgenticAi #AI #Ar...
https://www.tkhunt.com/2438554/ An AI Agent Just Ran a Complete Ransomware Attack — No Human Involved #AgenticAi #AI #ArtificialIntelligence #エージェント型AI #人工知能
🐾 pocketpaw/pocketpawSelf-hosted AI agent with desktop app and multi-platform chat support, supports Anthropic, OpenAI, ...
🐾 pocketpaw/pocketpawSelf-hosted AI agent with desktop app and multi-platform chat support, supports Anthropic, OpenAI, Ollama⭐ Stars: 865📅 Last Update: Jul 10, 2026https://github....
I Built an AI Agent With Tools. The First 50 Calls Were a Disaster.
The Demo That Almost Lost Me the Project I spent two weeks building the agent. It could...
Use Xcode MCP Instead of xcodebuild to Save Disk Space and Time in Agentic iOS Development
TL;DR - When setting up an AI agent for iOS development, the default approach is to have the agent...
I built an AI agent that runs a local business's weekly marketing (Next.js + Gemini)
For the last couple of weeks I've been building Bloom, an AI marketing agent for local businesses...
テクサー、イワブチより出資を受け 「Agentic IoT」構築の協業を強化 | 株式会社テクサー https://www.yayafa.com/2841120/ #AgenticAi #AI #ArtificialGeneralIntel...
テクサー、イワブチより出資を受け 「Agentic IoT」構築の協業を強化 | 株式会社テクサー https://www.yayafa.com/2841120/ #AgenticAi #AI #ArtificialGeneralIntelligence #ArtificialIntelligence #エージェント型AI #人工知能 #汎用人工知能
"If you’re a developer in 2026, you’re most likely using large language models (LLMs) in your flow. While agentic coding...
"If you’re a developer in 2026, you’re most likely using large language models (LLMs) in your flow. While agentic coding tools can work wonders, their output often flies in the fac...
静岡ビジネス共創実行委員会（SBC） ／静岡県・掛川市で「超初心者向けClaude Code勉強会」を8月8日に開催 – 無料プレスリリース「PR-FREE」 https://www.yayafa.com/2841111/ #Agentic...
静岡ビジネス共創実行委員会（SBC） ／静岡県・掛川市で「超初心者向けClaude Code勉強会」を8月8日に開催 – 無料プレスリリース「PR-FREE」 https://www.yayafa.com/2841111/ #AgenticAi #AI #Anthropic #AnthropicClaude #ArtificialGeneralIntelli...
🚀 Also climbing today:⭐ DietrichGebert/ponytail +983 stars (total 80.1k)« Makes your AI agent think like the laziest sen...
🚀 Also climbing today:⭐ DietrichGebert/ponytail +983 stars (total 80.1k)« Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wro...
TopoBrick forecasts building sensors without training dataA new arXiv preprint uses agentic topology sampling to predict...
TopoBrick forecasts building sensors without training dataA new arXiv preprint uses agentic topology sampling to predict building IoT sensor readings with zero building-specific tr...
AI chain-of-thought monitoring backfires, raising harmful approvals 9.5%Letting a safety monitor read an AI agent's priv...
AI chain-of-thought monitoring backfires, raising harmful approvals 9.5%Letting a safety monitor read an AI agent's private reasoning was supposed to catch deception — but adversar...
POV: You're still manually patching your AI agent "helpdesk." DeskCrew connects human teams & AI agents for unified supp...
POV: You're still manually patching your AI agent "helpdesk." DeskCrew connects human teams & AI agents for unified support. Try it. #AIhttps://deskcrew.io
Nubia and ByteDance's second-generation Doubao AI Agent phone is launching at WAIC 2026 in Shanghai. The device features...
Nubia and ByteDance's second-generation Doubao AI Agent phone is launching at WAIC 2026 in Shanghai. The device features an orange AI button and refined Obric UI after 216 days of ...
博報堂が「エージェンティックコマース」のソリューション群「Agentic Commerce ONE」の展開を開始（Web担当者Forum） – Yahoo!ニュース https://www.yayafa.com/2840939/ #Agen...
博報堂が「エージェンティックコマース」のソリューション群「Agentic Commerce ONE」の展開を開始（Web担当者Forum） – Yahoo!ニュース https://www.yayafa.com/2840939/ #AgenticAi #AI #ArtificialGeneralIntelligence #ArtificialIntellig...
The Signal Problem: Why your AI Agent needs Social Intelligence, not just Price Feeds
Stop scraping social media for crypto alpha. Learn how to use MCP with LunarCrush to provide your AI agents with structured, actionable sentiment metrics like AltRank and Galaxy Sc...
Agentic AI outperforms single-LLM in insurance underwritingAgentic AI beats single-LLM systems in small commercial under...
Agentic AI outperforms single-LLM in insurance underwritingAgentic AI beats single-LLM systems in small commercial underwriting, especially when data is missing or rules need multi...
AI agent harness blocks leaks, keeps full 120/120 utilityNew arXiv paper shows code-owned enforcement stops recommendati...
AI agent harness blocks leaks, keeps full 120/120 utilityNew arXiv paper shows code-owned enforcement stops recommendation and trace leaks in enterprise LLM agents at 120/120 utili...