5/5 Happy animating 🥂 #animationtip #customtools #scriptingforanimators #Animatingwithselormx

🤔Ti servono utensili Speciali in modo urgente? Hai l’esigenza di risparmiare? Non esitare a contattarci, il nostro supporto al tuo servizio: speciale@sautool.it #sautool #specialtools #customtools #metalcutting #cncmachining

Most of the recent startup doing an Agent for something something can be mapped to Think(withChatSDK) Storage CustomTools

Giving it a shot; it is a rather silly precise unifying piece in my template tool template personality experiment. My influential personalities equipped with the masteries provided by Agency - organized and deployed through UI by a crew of customtools Gemini..

you need to use the gemini-3.1-pro-preview-customtools model slug

THIS IS A JOKE Introducing Gemini 3.2 Pro Exp, our latest experimental model for the 3.2 series. It comes with: - 3M token Context Window, - Improvements to our best-in-class vision capabilities, - SOTA in agentic tasks (no more failed tool calls) - Verbosity controls for users who want the model to talk longer/shorter We will be shutting down the customtools endpoint since it's rolled into the model We have also lowered the pricing for the Grounding tools (Search & Maps) 5k prompts per month then $10 / 1,000 search queries Lastly, Flex and Batch processing now passes on cost savings to cached tokens In the coming weeks, we will be rolling out a few more agents something, something managed swarm agents We are just getting started : )

For #metalworking Reach out to us for your integrated solutuion: atcarbide.com #TungstenCarbide #CementedCarbide #SolidCarbide #CarbideInserts #SolidEndMills #CarbideBurrs #CustomTools #SawBlades #CarbideReamers #CarbideDrills #CuttingTools #EXCELLEDGE #INNOVEDGE

Pi v0.63.1: one new model and nine bug fixes, mostly around compaction. Highlights: - Added gemini-3.1-pro-preview-customtools for the google-vertex provider - Fixed repeated compactions dropping messages kept by an earlier compaction - Fixed interactive compaction UI: no duplicate summary blocks; trigger-compact fires only on threshold - Fixed auto-compaction overflow recovery for Ollama on explicit context-length errors Complete details in thread ↓

How it works - - •Deployment – Self‑hosted onLinux/macOS/WSL (cheap $5 VPS orserverless like Modal/Daytona). Always‑on,hibernates when idle, reachable via CLI,Telegram, Discord, Slack, WhatsApp, or IDEback‑ends. : •Core loop – : 1User submits a natural‑language taskor scheduled cron job. 2Hermes routes the request to any LLMprovider (Anthropic/Claude,OpenAI‑compatible, Vercel AIGateway, Nous Portal, OpenRouter,custom endpoints) through a unifiedcall_llm API. 3The agent plans, then calls tools inparallel (via ThreadPoolExecutor). 4Tools run in sandboxed back‑ends(local, Docker, SSH, Singularity, Modal)with namespace isolation andhardening. 5Output streams token‑by‑token to allinterfaces (CLI   gateways). : •Persistent shell – Keeps current directory,environment variables, and aliases aliveacross tool calls. •Self‑improving loop – After completingcomplex tasks the agent automaticallycreates or refines reusable skills (Pythonmodules stored in the Skills Hub, shareablevia the open agentskills.io standard).Skills improve with use; the agent nudgesitself to persist knowledge. •Memory system – Multi‑level memory(Honcho async writes, dialectic usermodeling, session titles, multi‑user isolation)plus full‑text search and LLM summarizationbuilds a deepening model of the user andprojects across sessions. •Sub‑agents – Can spawn isolatedsub‑agents for delegation and parallelism. : Plugins & extensibility (v0.3.0) : •Drop plain Python files into~/.hermes/plugins/ → instant customtools, commands, hooks (no fork needed). •40 built‑in tools (terminal, filesystem, codeexec, web search, vision, image generation,TTS, cron, memory, task planning, sub‑agentdelegation). •Community‑contributed skills from ClawHub,LobeHub, GitHub are installable. - Key v0.3.0 additions : •Real‑time unified streaming across allplatforms. •First‑class plugin architecture. •/browser connect via Chrome DevToolsProtocol (attach to an existing Chromeinstance). •Native Anthropic provider & Vercel AIGateway with auto‑credential discovery(OAuth PKCE, no middleman). •VS Code / Zed / JetBrains integration viaACP Server (full slash‑command support). •Voice mode (push‑to‑talk CLI, voice notes inmessaging apps, Discord voice channels,local faster‑whisper transcription). •Smart approvals (learned safe commands,Codex‑style; /stop kills runs instantly). •PII redaction (privacy.redact_pii scrubsbefore sending to LLMs). •Concurrent tool execution, persistent shell,Honcho memory, 9 new skills, 50 bug fixes. •Agentic On‑Policy Distillation (new RLenvironment for distilling policies into bettermodels via Atropos). Installation – One‑line curl … | bash then hermes setup; update with hermes update. All components are local‑first but can delegate to cloud models.

Nods and takes notes 📝 Are you aware of the gemini-3.1-pro-preview-customtools endpoint? ai.google.dev/gemini-api/doc…

Struggling with bad entries, fakeouts, or no clear direction? QuantRx fixes that fast: Free daily liquidity signals (like the BTC & SOL wins you just saw) Free bias market structure breakdowns every day Invite-only premium indicators (Harmonics, PVSR Suite, MTF Matrix, Kill Zones, SMC Dashboard, Oscillator more) Education-first community – no hype, just real setups And the best part: premium members get to request their own indicator builds & dashboard upgrades Join in under 1 min – free tier gets you signals bias today. Premium unlocks everything your custom ideas get built. Link in bio. Spots move quick. #QuantRx #FreeSignals #LiquidityTrading #CryptoDiscord #TradingCommunity #PremiumIndicators #CustomTools #Bitcoin #Solana #JoinNow

google/gemini-3.1-pro-preview-customtools こういうモデルがあるのね。

I think this is probably also the reason why Gemini 3.1 Pro is bad at coding. It's probably not using tools well. Gotta try it with the customtools version now in pi

figured out why google launched a special "customtools" version for Gemini 3.1 Pro. It's not that it's "better" at tool calling. It's that the base 3.1 pro model is utter shit at it. What works even with 3-flash does not work with 3.1 pro base but works with customtools

4️⃣ El Secreto para Agentes: Si usas Gemini en tu terminal, NO uses el modelo base. Cambia al endpoint: gemini-3.1-pro-preview-customtools. Está optimizado para tus propias herramientas y evita bucles infinitos. 🚀 #TechTips #Software #WebDev #Coding #jokioki

Sveza lista dostupnih Google/Gemini API modela - ------------------------------------------------------------ Available Models: - models/gemini-2.5-flash (Gemini 2.5 Flash) - models/gemini-2.5-pro (Gemini 2.5 Pro) - models/gemini-2.0-flash (Gemini 2.0 Flash) - models/gemini-2.0-flash-001 (Gemini 2.0 Flash 001) - models/gemini-2.0-flash-exp-image-generation (Gemini 2.0 Flash (Image Generation) Experimental) - models/gemini-2.0-flash-lite-001 (Gemini 2.0 Flash-Lite 001) - models/gemini-2.0-flash-lite (Gemini 2.0 Flash-Lite) - models/gemini-2.5-flash-preview-tts (Gemini 2.5 Flash Preview TTS) - models/gemini-2.5-pro-preview-tts (Gemini 2.5 Pro Preview TTS) - models/gemma-3-1b-it (Gemma 3 1B) - models/gemma-3-4b-it (Gemma 3 4B) - models/gemma-3-12b-it (Gemma 3 12B) - models/gemma-3-27b-it (Gemma 3 27B) - models/gemma-3n-e4b-it (Gemma 3n E4B) - models/gemma-3n-e2b-it (Gemma 3n E2B) - models/gemini-flash-latest (Gemini Flash Latest) - models/gemini-flash-lite-latest (Gemini Flash-Lite Latest) - models/gemini-pro-latest (Gemini Pro Latest) - models/gemini-2.5-flash-lite (Gemini 2.5 Flash-Lite) - models/gemini-2.5-flash-image (Nano Banana) - models/gemini-2.5-flash-lite-preview-09-2025 (Gemini 2.5 Flash-Lite Preview Sep 2025) - models/gemini-3-pro-preview (Gemini 3 Pro Preview) - models/gemini-3-flash-preview (Gemini 3 Flash Preview) - models/gemini-3.1-pro-preview (Gemini 3.1 Pro Preview) - models/gemini-3.1-pro-preview-customtools (Gemini 3.1 Pro Preview Custom Tools) - models/gemini-3-pro-image-preview (Nano Banana Pro) - models/nano-banana-pro-preview (Nano Banana Pro) - models/gemini-3.1-flash-image-preview (Nano Banana 2) - models/gemini-robotics-er-1.5-preview (Gemini Robotics-ER 1.5 Preview) - models/gemini-2.5-computer-use-preview-10-2025 (Gemini 2.5 Computer Use Preview 10-2025) - models/deep-research-pro-preview-12-2025 (Deep Research Pro Preview (Dec-12-2025)) - models/gemini-embedding-001 (Gemini Embedding 001) - models/aqa (Model that performs Attributed Question Answering.) - models/imagen-4.0-generate-001 (Imagen 4) - models/imagen-4.0-ultra-generate-001 (Imagen 4 Ultra) - models/imagen-4.0-fast-generate-001 (Imagen 4 Fast) - models/veo-2.0-generate-001 (Veo 2) - models/veo-3.0-generate-001 (Veo 3) - models/veo-3.0-fast-generate-001 (Veo 3 fast) - models/veo-3.1-generate-preview (Veo 3.1) - models/veo-3.1-fast-generate-preview (Veo 3.1 fast) - models/gemini-2.5-flash-native-audio-latest (Gemini 2.5 Flash Native Audio Latest) - models/gemini-2.5-flash-native-audio-preview-09-2025 (Gemini 2.5 Flash Native Audio Preview 09-2025) - models/gemini-2.5-flash-native-audio-preview-12-2025 (Gemini 2.5 Flash Native Audio Preview 12-2025)