# whichai

> AI tools ranked by the job you need done. Updated Oct 22, 2026. Editorial picks; sponsored slots are labeled.

Contact: hello@which-ai.app · Sponsor: https://which-ai.app/sponsor

## Best AI for…
- [Best AI agents for business (2026)](https://which-ai.app/best/business-agents): Lindy for an AI assistant that works your inbox and calendar, Manus for big research and build jobs, Relevance AI for a team of sales and ops agents, and Gumloop when non-engineers need to build and own the agents.
- [Best AI for research (2026)](https://which-ai.app/best/research): Perplexity for fast answers with sources you can click, NotebookLM when the answers have to come only from your own files.
- [Best AI coding assistant (2026)](https://which-ai.app/best/coding-assistants): GitHub Copilot if your team lives on GitHub, Gemini Code Assist for the best free solo plan, JetBrains AI if you're in IntelliJ or PyCharm, and Tabnine when code can't leave the building.
- [Best AI for vibe coding (2026)](https://which-ai.app/best/vibe-coding): Cursor if you can read code. Lovable if you can't. Claude Code or Codex if you live in the terminal.
- [Best AI for video (2026)](https://which-ai.app/best/video): Runway or Kling to generate footage, HeyGen for talking-head videos, OpusClip to turn long videos into shorts.
- [Best AI for spreadsheets (2026)](https://which-ai.app/best/spreadsheets): Use the AI built into the sheet you already use: Gemini in Google Sheets or Copilot in Excel. For one-off analysis of a CSV, use Julius.
- [Best AI for images (2026)](https://which-ai.app/best/images): Midjourney for the best-looking images, Ideogram when the words in the image have to be spelled right, Krea for fast edits and iteration.
- [Best AI for writing (2026)](https://which-ai.app/best/writing): Claude for long-form drafts that sound human, ChatGPT if you want one tool for everything, Grammarly to polish what you already wrote, and Sudowrite for fiction.
- [Best AI for automation (2026)](https://which-ai.app/best/automation): n8n if you're technical or want to self-host for free, Zapier if you want the most apps and the easiest start, Make if you think in flowcharts.

## Vibe coding
- #1 [Cursor](https://which-ai.app/tools/cursor): AI code editor with agents that work across your whole repo. Best for: Builders who read code.
- #2 [Claude Code](https://which-ai.app/tools/claude-code): Terminal-first coding agent from Anthropic. Best for: Terminal people.
- #3 [Codex](https://which-ai.app/tools/codex): OpenAI's coding agent for CLI, IDE, and cloud tasks. Best for: Parallel background tasks.
- #4 [Lovable](https://which-ai.app/tools/lovable): Prompt-to-app builder with hosting and a database baked in. Best for: Non-coders shipping MVPs.
- #5 [Bolt.new](https://which-ai.app/tools/bolt): Full-stack apps in the browser from a prompt. Best for: Quick prototypes.
- #6 [v0](https://which-ai.app/tools/v0): Vercel's app and UI builder. Best for: Frontend + Next.js.
- #7 [Replit](https://which-ai.app/tools/replit): Cloud IDE with an agent that builds and deploys. Best for: All-in-one cloud dev.

## Video
- #1 [Runway](https://which-ai.app/tools/runway): Generative video studio: text/image to video plus editing tools. Best for: Creative, cinematic clips.
- #2 [Kling AI](https://which-ai.app/tools/kling): Text and image to video with strong motion. Best for: Realistic generated motion.
- #3 [HeyGen](https://which-ai.app/tools/heygen): AI avatar videos in your face and voice. Best for: Talking-head content.
- #4 [OpusClip](https://which-ai.app/tools/opusclip): Long video in, short vertical clips out. Best for: Shorts / Reels / TikTok.
- #5 [Descript](https://which-ai.app/tools/descript): Edit video by editing the transcript. Best for: Talky edits.
- #6 [CapCut](https://which-ai.app/tools/capcut): Free-first editor with AI captions and templates. Best for: Mobile short-form.

## Writing
- #1 [Claude](https://which-ai.app/tools/claude): Anthropic's assistant. Strong long-form writing and editing. Best for: Long-form drafts.
- #2 [ChatGPT](https://which-ai.app/tools/chatgpt): The generalist. Writing, research, files, images, all in one. Best for: Everyday everything.
- #3 [Grok](https://which-ai.app/tools/grok): xAI's assistant with live X context. Best for: Timely, X-aware posts.
- #4 [Grammarly](https://which-ai.app/tools/grammarly): Grammar, tone, and rewrite help in every app. Best for: Polishing anything.
- #5 [Hemingway Editor](https://which-ai.app/tools/hemingway): Highlights dense sentences so you cut them. Best for: Clarity edits.
- #6 [Sudowrite](https://which-ai.app/tools/sudowrite): AI built for fiction writers. Best for: Novels and fiction.

## Spreadsheets & data
- #1 [Gemini in Google Sheets](https://which-ai.app/tools/gemini-sheets): Gemini built into Sheets: formulas, tables, summaries. Best for: Google Workspace users.
- #2 [Copilot in Excel](https://which-ai.app/tools/copilot-excel): Microsoft's AI inside Excel. Best for: Excel shops.
- #3 [Julius AI](https://which-ai.app/tools/julius): Chat with your CSVs and get charts back. Best for: Quick data analysis.
- #4 [Rows](https://which-ai.app/tools/rows): Spreadsheet with built-in AI and data integrations. Best for: Live-data dashboards.

## Images & design
- #1 [Midjourney](https://which-ai.app/tools/midjourney): The look-best image generator. Best for: Beautiful visuals.
- #2 [Ideogram](https://which-ai.app/tools/ideogram): Image gen that gets text right. Best for: Text in images.
- #3 [Krea](https://which-ai.app/tools/krea): Real-time generation plus enhance/upscale in one suite. Best for: Rapid iteration.
- #4 [Adobe Firefly](https://which-ai.app/tools/firefly): Adobe's generative suite, wired into Photoshop. Best for: Adobe users.
- #5 [Canva](https://which-ai.app/tools/canva): Design anything, with AI helpers built in. Best for: Social graphics.

## Voice & music
- #1 [ElevenLabs](https://which-ai.app/tools/elevenlabs): Lifelike voices, cloning, and dubbing. Best for: Voiceovers.
- #2 [Suno](https://which-ai.app/tools/suno): Full songs from a prompt. Best for: Songs and jingles.

## Automation & agents
- #1 [n8n](https://which-ai.app/tools/n8n): Workflow automation with AI nodes. Self-host it free. Best for: Technical builders.
- #2 [Zapier](https://which-ai.app/tools/zapier): Connect thousands of apps with AI steps and agents. Best for: No-code teams.
- #3 [Make](https://which-ai.app/tools/make): Visual automation builder. Best for: Visual thinkers.

## Research & search
- #1 [Perplexity](https://which-ai.app/tools/perplexity): Answer engine with citations. Best for: Quick sourced answers.
- #2 [NotebookLM](https://which-ai.app/tools/notebooklm): Chat grounded in your own docs, plus audio overviews. Best for: Your own sources.

## Slides & docs
- #1 [Gamma](https://which-ai.app/tools/gamma): Decks, docs, and sites from an outline. Best for: Fast decks.

## Meetings & notes
- #1 [Granola](https://which-ai.app/tools/granola): AI notepad for meetings. No bot joins the call. Best for: Back-to-back calls.
- #2 [Fathom](https://which-ai.app/tools/fathom): Records, transcribes, and summarizes Zoom/Meet/Teams. Best for: Solo operators.

## Coding assistants
- #1 [GitHub Copilot](https://which-ai.app/tools/github-copilot): AI pair programmer in VS Code, JetBrains, and GitHub itself. Best for: Teams already on GitHub.
- #2 [Gemini Code Assist](https://which-ai.app/tools/gemini-code-assist): Google's coding assistant for VS Code, JetBrains, and GitHub. Best for: Free solo use.
- #3 [JetBrains AI Assistant](https://which-ai.app/tools/jetbrains-ai): AI built into IntelliJ, PyCharm, WebStorm, and the rest. Best for: JetBrains users.
- #4 [Tabnine](https://which-ai.app/tools/tabnine): Privacy-first code assistant with private and self-hosted deployment. Best for: Locked-down companies.

## Agents for business
- #1 [Lindy](https://which-ai.app/tools/lindy): AI employees that work your inbox, calendar, and tools. Best for: Solo founders and small teams.
- #2 [Manus](https://which-ai.app/tools/manus): General agent that browses, researches, and builds deliverables. Best for: Big research jobs.
- #3 [Relevance AI](https://which-ai.app/tools/relevance-ai): Build a team of specialist agents for sales, support, and ops. Best for: Sales and ops teams.
- #4 [Gumloop](https://which-ai.app/tools/gumloop): No-code agent and workflow builder with any model. Best for: Ops people, no code.

## New this week
- Oct 21, 2026: Claude Duet (research preview): Anthropic's new standalone agent app for iOS, Android, and claude.ai. It brings over your Claude memory, skills, and connected apps (Gmail, Calendar, Drive, Slack, QuickBooks, HubSpot, and more), checks them every few hours, and sends a morning brief with what needs you and drafted replies. Hand it bigger jobs like a financial model, a deck, or a dashboard and it works on its own cloud computer with a browser while your phone is off. It asks before it sends, pays, signs, or deletes anything. It's US-only, by waitlist, for Pro and Max plans, and it burns your normal Claude usage limits. Best for: Solo founders and small-business owners on Claude Pro or Max. (source: https://claude.com/resources/articles/claude-duet)
- Oct 21, 2026: Recursive Flint: The first model from Richard Socher's Recursive: a free, Apache 2.0 coding model that runs on a laptop. It's a mixture-of-experts with 40B parameters but only 2.5B active, so it clocked about 131 tokens a second on an M4 Pro MacBook Pro, roughly twice similar models. It beats other sub-50B models on SWE-Bench Verified, and the company says its automated research system helped build almost every part of it. Weights are on Hugging Face. Recursive admits it needs more hand-holding than the big paid agents, so break big tasks into smaller steps. Best for: Coding offline or on private code from a laptop. (source: https://techcrunch.com/2026/10/21/recursive-launches-flint-a-laptop-coding-model-it-says-was-largely-built-by-ai/)
- Oct 21, 2026: Breken: "Production before production." Breken rebuilds your whole app on its own machines, fakes the outside services inside a sealed sandbox, and fast-forwards time at 4,000x so real-looking accounts and pending jobs pile up. Then it changes one thing at a time (a retry, a lost response, a clock jump, a deploy mid-job) and only reports failures that reproduce every time, each with the state, a trace, and a draft fix PR. On its own ESCAPES benchmark it caught 76 of 235 bugs that real users later hit, about twice what Claude Code found, with fewer false alarms (vendor-run numbers). Sign in with GitHub; usage is prepaid from a $25 top-up. Best for: Teams with payments, billing, or sync logic that breaks in prod. (source: https://breken.ai/)
- Oct 21, 2026: Omnara: An open-source (Apache 2.0), self-hostable take on Claude Managed Agents and OpenAI's Agents API. Create an agent with one API call and Omnara runs the loop, gives it sandboxes for shell commands, and handles secrets, permissions, and approvals. Every step lands in a Postgres event log, so agents survive restarts and cost nothing while idle. It works with any model provider (OpenAI, Anthropic, OpenRouter, Bedrock, Ollama), has MCP, skills, memory, subagents, and scheduled triggers, and runs on one box with Docker Compose. There's also a hosted cloud. Best for: Builders running durable agents on their own servers. (source: https://news.ycombinator.com/item?id=50183892)
- Oct 21, 2026: UseIt Studio: An AI design agent for stuff you can hold: pins, stickers, gift boxes, pop-up cards, and brand kits. Describe it in one sentence, it asks the questions a designer would, and you fix any detail by pointing at it. You get a real, editable design file with true dimensions, bleed, and dielines, ready to print, cut, and fold. It runs in the browser or pops up anywhere on a Windows desktop. It was #1 on Product Hunt for Oct 21. Best for: Small brands and makers doing print, merch, and packaging. (source: https://www.producthunt.com/products/useit-studio-from-idea-to-delivery)
- Oct 21, 2026: Needle: An outbound sales engine built for agents. From one prompt inside Claude, ChatGPT, or Grok, it finds leads that fit, enriches them, and reaches out on whichever channel they actually use, LinkedIn included. It finished #3 on Product Hunt for Oct 21. Best for: Founders and small sales teams doing their own outbound. (source: https://www.producthunt.com/products/needle-3)
- Oct 21, 2026: TwinMind for Desktop: TwinMind's note-taker is now a Mac and Windows app. It captures what you say and hear in meetings, lectures, and in-person conversations, transcribes and summarizes it, suggests tasks as you go, and lets you dictate into any app. Everything feeds a running "second brain" you can ask questions later. Best for: People who want notes and dictation in one desktop app. (source: https://www.producthunt.com/products/twinmind)
- Oct 20, 2026: Bria Fibo 2.0: Bria's 8B open-weights image model now does generation and editing in one model. Instruction, masked, and multi-reference edits keep what you didn't ask to change (identity, layout, lighting), and text, texture, and hands got better. It ships as Fibo 2.0 Dev (full base, built for fine-tuning) and Edit Turbo (4-step editing). Artificial Analysis ranked it #1 for open-weights image editing on Oct 20. It's trained only on licensed data; the weights are CC BY-NC, so commercial use goes through Bria's API or a deal with them. Best for: Product teams that need edits that don't wreck the rest of the image. (source: https://huggingface.co/briaai/Fibo-2.0-dev)
- Oct 20, 2026: FastH3-Omni: An open-weight, sped-up version of MiniMax H3 from Nuva Lab and UC San Diego's FastVideo team. Feed it text plus up to 9 images, 3 video clips, and 3 voice or music references, and it makes a 5 to 15 second, 24 fps clip with synced stereo audio in one pass. It samples in 8 steps instead of 50, which the team measured at 5.6 to 11.9x lower latency. It runs on RTX GPUs, DGX Spark, and Apple Silicon, with ComfyUI support. The license is MiniMax's H3 community license, not MIT, so check terms before client work. Best for: Creators running local video pipelines. (source: https://nuvalab.ai/fasth3/)
- Oct 20, 2026: Ornith-1.5-122B: An MIT-licensed 122B mixture-of-experts model, built on Qwen3.5 and Gemma4 and then trained with a self-improvement loop that writes its own practice tasks. It has a 262K context, serves on a single 80 GB GPU through vLLM or SGLang, and comes in FP8, GGUF, and MLX builds, plus a quantized mobile variant. Best for: Self-hosting a coding-agent model. (source: https://huggingface.co/ornith-ai/Ornith-1.5-122B)
- Oct 20, 2026: Gradium Phonon: Tiny open text-to-speech models that run on the device: a phone, a laptop CPU, a browser tab, or a small board. Phonon 31m is English-only, 64 MB, and Apache 2.0. The 40m models add French, German, Spanish, and Portuguese but are non-commercial unless you talk to sales. Audio streams while it generates, it works fully offline once downloaded, and the Rust runtime has Python, browser (npm), Swift, and an OpenAI-compatible server. Best for: Offline voice in apps and gadgets. (source: https://gradium.ai/phonon)
- Oct 20, 2026: Ampersand v0.1 (humans&): A model trained to work with groups of people over weeks, not just finish one task. You drop it into a group chat with two tools, send_message and pass, and it decides when to speak and when to stay quiet, like flagging that a teammate already said they're out Friday. It's trained from GLM 5.3 and available now through an OpenAI-compatible Agents API with no waitlist. humans& admits it sometimes coaches when people just want an answer. Best for: Builders adding an AI teammate to group chats. (source: https://ampersand.humansand.ai/blog/)
- Oct 20, 2026: Mintlify Autopilot: An always-on docs agent, in beta on Mintlify's Pro and Enterprise plans. It watches code merges, Slack, your tracker, support tickets, and feature flags, drafts the doc update, and opens a pull request for a human to review. It never publishes on its own. It learns your tone from the PRs you merge, and each PR it opens or updates costs 250 credits; runs that find nothing cost nothing. Best for: Dev teams whose docs lag behind the code. (source: https://www.mintlify.com/blog/autopilot)
- Oct 20, 2026: Penmentor: An open-source mentor that checks your handwritten math and marks it up visually, like a teacher with a red pen, using the Claude, Codex, or Antigravity CLI you already have. The maker says it's currently tuned to his own Arch Linux and i3 setup. Best for: Students practicing math by hand. (source: https://news.ycombinator.com/item?id=50167604)
- Oct 20, 2026: Mistral Voxtral 3: Mistral's new speech family: transcription models for 50+ languages (from $0.0035 a minute, with a realtime version), Voxtral Speech 3 text-to-speech at $13 per million characters, voice cloning plus a "Pro Voice" mode for close matches, and a voice-agent SDK built on LiveKit that streams listening, reasoning, tool calls, and speech in one pipeline. It runs on Mistral's EU, US, and global API endpoints or self-deployed, and you can try it in the Studio playgrounds. Best for: Builders shipping voice agents and phone bots. (source: https://mistral.ai/news/voxtral-3/)
- Oct 20, 2026: Beacon: An open-source, local-first memory layer for coding agents. It captures full sessions from Claude Code, Cursor, Codex, OpenCode, Cline, and 20+ other harnesses, spots the fixes and workflows worth keeping, and turns the ones you approve into Agent Skills that future agents load through MCP or a skills folder. Best for: Devs who bounce between coding agents. (source: https://github.com/Asymptote-Labs/agent-beacon)
- Oct 19, 2026: Notion Agents rebuilt (Auto router): Notion rebuilt its agent harness: agents now get their own computer and browser, can work on a task for up to 24 hours, and have a "Review for me" mode with safety checks. The Auto model router picks the model per task, and Notion says it matched Opus 5.5 and Astra on 20+ common tasks at about 90% lower cost. You can connect your ChatGPT Plus, Pro, or Go plan to your personal Notion Agent, Notion MCP got an overhaul with memory sync, and all AI usage moves to a new credit system. It hit Product Hunt on Oct 21. Best for: Teams whose docs and projects live in Notion. (source: https://www.notion.com/releases/2026-10-19)
- Oct 19, 2026: Exa 3.0: Exa's search API for AI agents got its biggest upgrade: a larger embedding model, Dynamic Highlights now generally available (it uses 95% fewer tokens than full page text), and billions of new documents, including shopping listings, local businesses, flights, events, and live news, sports, and weather. There's a new Lite search type at $4 per 1,000 requests; Auto is $7. Exa says it ranks first on every benchmark it tested. Best for: Builders wiring web search into agents. (source: https://exa.ai/blog/exa-3)
- Oct 19, 2026: Cloudflare Clairic: A preview extraction model on Workers AI. You send text (plus up to four images) and a schema of typed fields, and it returns values instead of prose: exact text spans with offsets, numbers, real dates, lists, estimates with an 80% range, and basic forecasts. Every answer carries a confidence score and a "null" probability. It's $0.10 per million input tokens, and Cloudflare says open weights are coming. Best for: Pulling structured data out of emails, invoices, and receipts. (source: https://developers.cloudflare.com/changelog/post/2026-10-19-clairic-workers-ai/)
- Oct 19, 2026: Inception Mercury 3: A diffusion LLM that writes tokens in parallel instead of one at a time. Inception clocks it at 1,068 tokens per second on NVIDIA GPUs, with a 1M-token context, tool calling, and JSON outputs. It's OpenAI API compatible and live on Inception's API, OpenRouter, Baseten, and Vercel at a launch price of $0.10 in and $0.35 out per million tokens (half off), and new API keys get 100 million free tokens. Best for: Latency-sensitive agent loops. (source: https://www.inceptionlabs.ai/blog/introducing-mercury-3)
- Oct 19, 2026: Sunra MCP: One MCP connector that puts image, video, audio, and 3D models inside Claude, ChatGPT, Claude Code, Codex, Cursor, and other agents: GPT Image 2.5, Nano Banana Pro, Seedance 2.5, Kling 3.0, Veo 3.1, ElevenLabs, Meshy, and more. You sign in with OAuth (no API key), and each model is billed at its maker's own API price with no markup. Best for: Making visuals and audio from inside your AI assistant. (source: https://sunra.ai/blog/introducing-sunra-mcp)
- Oct 19, 2026: Wabi 2.0: Replika founder Eugenia Kuyda relaunched Wabi as a multiplayer personal assistant shaped like a messenger. Each task or goal gets its own thread, the agent builds small apps inside them (a weight-loss tracker, a kid's schedule), and you can share a thread as a group chat. Data access is scoped per chat, and everyone sees when someone's info is requested. It's free for now. Best for: Coordinating plans with a partner, family, or small crew. (source: https://techcrunch.com/2026/10/19/replikas-founder-built-the-ai-assistant-she-pitched-at-disrupt-12-years-ago/)
- Oct 19, 2026: Wally by Willow: A new Scribe agent inside the Willow voice-dictation app. Talk or type to draft an email, Slack message, or prompt, then keep refining it in the same conversation. Highlight text in any app to get a rewrite. It learns your style from your edits, even the ones you make after pasting. Best for: People who'd rather talk their emails than type them. (source: https://www.producthunt.com/products/willow-voice)
- Oct 19, 2026: buddylist: A free desktop app for Mac (Apple Silicon), Windows, and Linux that puts Claude Code, Codex, Gemini, and OpenCode in an MSN-style buddy list. Give each agent its own Git worktree, or drop several into one group chat on a shared folder so they take turns or hand off unfinished work. Diffs, terminals, app preview, and PR checks sit beside the chat. Bring your own agent accounts. Best for: Vibe coders running several agents at once. (source: https://www.producthunt.com/products/buddylist-2)
- Oct 19, 2026: MiniMax M3.1 Flash: MiniMax unmasked "Space Bunny," the stealth model that sat at the top of OpenRouter, as an early build of M3.1 Flash. It's a fast, cheap agent and coding model with a 1M-token context that reads text, images, and video. It's $0.15 in and $0.60 out per million tokens, free on OpenRouter for the first 72 hours, and open weights are promised for Oct 23. Best for: Budget agent and coding loops. (source: https://www.minimax.io/blog/minimax-m31f)
- Oct 19, 2026: Viggle JST-2: Viggle's new world model builds everything in 3D instead of pixels. It spins up an explorable 3D scene in about a second, turns one image into an animated 3D character without a rigging step, and generates full-body motion from text or a video clip. Scenes export as Gaussian splats, and there's a free trial in the browser. Best for: Indie game devs and 3D animators. (source: https://viggle.ai/jst2)
- Oct 19, 2026: qwen3-4b-deslop: A free 4B open model fine-tuned on a MacBook Air to drop the usual AI writing tics: em dashes, "it's not X, it's Y," lists of three. It's a 2.5 GB download and runs locally with one Ollama command, no system prompt needed. The maker says the voice comes out plain to the point of flat, and it still invents names and places. Best for: Local drafts that don't sound like a bot. (source: https://news.ycombinator.com/item?id=50151928)
- Oct 19, 2026: Beam.win: A Mac app that pulls individual windows (terminal, browser, any app) off one Mac and onto another as real windows, each with its own Dock icon and a spot in ⌘Tab. It handles headless Mac minis, it's encrypted Mac to Mac, and it works across cities with Tailscale. Sharing is free, and all-day use is a paid plan. Best for: Builders with an always-on agent Mac. (source: https://www.producthunt.com/products/beam-win)
- Oct 19, 2026: readywhen: A personal assistant that lives in WhatsApp with its own phone number, its own computer, and a project board. Call it, text it, or voice-note it. It tracks what you promised to whom and by when, and it drafts the follow-ups. Nothing goes out until you approve it. Best for: Solo operators running clients over WhatsApp. (source: https://www.producthunt.com/products/readywhen)
- Oct 18, 2026: WhatsApp MCP (free on Cloudflare): A free, open-source, read-only MCP server that lets Claude or any agent search and read your own personal WhatsApp messages. It runs on Cloudflare Workers, so there's no server to babysit, and it pulls contact names from Google so search isn't just phone numbers. It's single-user by design. Best for: Agent users whose life runs on WhatsApp. (source: https://news.ycombinator.com/item?id=50145715)
- Oct 18, 2026: Yila: A research agent that searches scholarly databases, reads 50+ full papers, compares methods and how strong the evidence is, then drafts a citation-backed review you keep editing. It can also reformat a manuscript to a journal's or thesis office's template. Best for: Grad students and researchers doing lit reviews. (source: https://news.ycombinator.com/item?id=50148356)
- Oct 17, 2026: Sphinx: A free, open-source Git hook that pauses your push and quizzes you on what the agent-written diff actually does, like what happens when a webhook retries. Answer right and the push goes through. Works with Codex, Claude Code, Cursor, OpenCode, or plain Git. Best for: Solo devs shipping agent code to prod. (source: https://news.ycombinator.com/item?id=50137950)
- Oct 17, 2026: Craft Agents: An open-source desktop app for running agents locally with your own model: Claude, ChatGPT, OpenRouter, or Ollama. Tell it "add Linear as a source" and it wires up the API or MCP server itself, and a built-in browser covers sites with no API. Best for: Builders who want local, bring-your-own-model agents. (source: https://www.producthunt.com/products/craft-agents)
- Oct 17, 2026: DeepSeek V4.1 Flash (1017 update): DeepSeek pushed a fresh snapshot of its cheap, fast open model and swapped it into its app, site, and API. Open weights, MIT license, with better coding and agent benchmark scores than the last Flash. (source: https://x.com/i/trending/2111316973992788359)
- Oct 17, 2026: FLUX 3 Image Klein (workflow update): Black Forest Labs shipped updated ComfyUI workflows for its small open-weights image model. It runs on consumer GPUs with about 8 GB of VRAM and takes up to 10 reference images. (source: https://x.com/i/trending/2111497603305394265)
- Oct 16, 2026: Llmspeed: A free, open-source site that shows how fast a local model would actually type on a given Mac or GPU, using community benchmarks where they exist and estimates where they don't. Best for: Anyone pricing a local-LLM rig. (source: https://news.ycombinator.com/item?id=50127979)
- Oct 16, 2026: GPT-6 Astra Pro upgrade (parallel agents): OpenAI upgraded GPT-6 Astra Pro in ChatGPT with faster replies and better plugin and tool use. It can now split a task across multiple agents running in parallel, and you can watch each one and review its finished work. Pro users first. Best for: ChatGPT Pro users with multi-part jobs. (source: https://x.com/OpenAI/status/2111192259073094035)
- Oct 16, 2026: Perplexity pplx-decider v1.2: Perplexity shipped new open-weight decision models in two sizes (27B and a 4B Flash) that answer with structured calls on text and images. It says they're up to 5x faster, Flash is the top 4B model on the Decision Index, and both are on OpenRouter. Best for: Agent pipelines that need fast, structured decisions. (source: https://x.com/perplexitydevs/status/2111166029539758120)
- Oct 16, 2026: Reflection AI Beam: A big open-weight model aimed at coding and long agent runs, with a 1M-token context window and day-one support in Ollama and vLLM. It ships alongside Mirror, an open-source agent harness. (source: https://x.com/i/trending/2111084244533489807)
- Oct 16, 2026: Elorian Glimpse: A visual reasoning model from ex-DeepMind folks. It zooms into image regions and rewatches video frames to check its own work before answering. Available now by API. (source: https://x.com/i/trending/2111144487468831169)
- Oct 16, 2026: Liquid AI d1-ultra: A multimodal model built to say "I don't know" instead of making things up. It now tops the Artificial Analysis Decision Index. (source: https://x.com/i/trending/2111102726482657736)