{"ok":true,"source":"tensorfeed.ai","lastUpdated":"2026-11-02","categories":[{"id":"coding","name":"Coding Agents","description":"AI-powered tools that write, review, and debug code directly in your development workflow."},{"id":"research","name":"Research Agents","description":"AI agents specialized in finding, synthesizing, and analyzing information from various sources."},{"id":"general","name":"General / Personal Agents","description":"Versatile AI assistants for everyday tasks including writing, analysis, brainstorming, and conversation."},{"id":"creative","name":"Creative Agents","description":"AI tools for generating images, music, video, and other creative media."},{"id":"frameworks","name":"Frameworks & Platforms","description":"Developer tools and SDKs for building custom AI agents and multi-agent workflows."}],"agents":[{"id":"muse-code","name":"Muse Code","provider":"Meta","category":"coding","description":"A terminal coding agent released August 5, 2026 and co-trained as one unit with Muse Spark so the model and the harness share goals, compaction, and subagent recipes. It left beta on August 31, 2026. Meta's docs list muse-spark-1.2 as the Muse Code default, with Muse Spark 1.3 the latest Spark release and Muse Wonder in preview above it. Meta documents it as running on macOS, Linux, and Windows from one codebase; it runs persistent background agents across a session and keeps a replay-safe event log so it survives a crash.","url":"https://dev.meta.ai","pricing":"Flat monthly plans at $5 (Everyday Usage, 10 to 50 prompts every 5 hours), $15 (High Usage, 5x Everyday), and $50 (Power Usage, 20x Everyday), plus a Maximum Usage tier at 80x Everyday, or usage-based via the Meta Model API: $1.25/$4.25 per 1M tokens standard, or $0.10/$0.20 on the contributor tier if you let Meta train on your data","launched":2026},{"id":"deepseek-harness","name":"DeepSeek Harness","provider":"DeepSeek","category":"coding","description":"A plugin-first open-source coding agent released August 13, 2026 under MIT, aimed directly at Claude Code. Shipped the same day DeepSeek moved V4-Pro to general availability and raised API prices, pairing an open harness with a more expensive model. Still labeled a developer preview with breaking changes expected, and past 269,000 GitHub stars.","url":"https://github.com/deepseek-ai/deepseek-harness","pricing":"Free and open source under MIT; model inference billed separately","launched":2026},{"id":"grok-build","name":"Grok Build","provider":"xAI (SpaceXAI)","category":"coding","description":"xAI's official terminal coding agent, invoked as the grok command. Delegates larger tasks to parallel subagents that can each run in their own git worktree, and has shipped Grok 4.7, with a 500K context window, since the model's release on September 21, 2026.","url":"https://x.ai/build","pricing":"Free to try within limits; higher usage comes with SuperGrok ($30/mo), SuperGrok Plus ($100/mo), and SuperGrok Heavy. API use bills at model rates, currently $2/$6 per 1M tokens for Grok 4.7 on prompts under 200K tokens, doubling to $4/$12 above that","launched":2026},{"id":"openai-codex","name":"Codex","provider":"OpenAI","category":"coding","description":"OpenAI's coding agent, available in the ChatGPT desktop app, on the web, in the open-source Codex CLI, in IDE extensions, and in Codex cloud, where it completes tasks end to end, from routine pull requests to hard engineering problems. Its harness is the one OpenAI now exposes to developers through the Agents API. GPT-6.1 Terra, a cheaper computer-use and visual reasoning model, arrived in Codex and ChatGPT Work on October 26, 2026.","url":"https://openai.com/codex/","pricing":"Included with ChatGPT plans: Free, Go $8/mo, Plus $20/mo, Pro from $100/mo, plus Business and Enterprise seats","launched":2025},{"id":"google-antigravity","name":"Google Antigravity","provider":"Google","category":"coding","description":"Google's agent-first development platform, introduced November 18, 2025 alongside Gemini 3 and now generally available. Pairs a familiar AI IDE with a manager surface where agents plan, code, and verify work across the editor, terminal, and browser, with model choice spanning Gemini, Claude, and gpt-oss. It now ships as five pieces: the Antigravity app, CLI, IDE, SDK, and extensions. Gemini 4 Argon landed in Antigravity on October 13, 2026, the same day Google built Antigravity into the Gemini macOS app, and a plugin marketplace followed on October 29, 2026.","url":"https://antigravity.google","pricing":"Free for individuals with weekly rate limits; higher limits with Google AI Pro ($19.99/mo) and Google AI Ultra (from $99.99/mo); business plans sold through Google Cloud start at $30 per seat per month, with a pay-as-you-go option that carries no seat fee","launched":2025},{"id":"jules","name":"Jules","provider":"Google","category":"coding","description":"Google's asynchronous coding agent. Point it at a GitHub repository and branch, or add a jules label to an issue, and it clones the repo onto a cloud VM, drafts a plan, shows you a diff to approve, and opens a pull request. It went to beta in May 2025 and generally available on August 6, 2025. The free tier runs on Gemini 2.5 Pro; paid tiers start at Gemini 3 Pro.","url":"https://jules.google","pricing":"Free tier with 15 tasks a day and 3 at once; Google AI Pro ($19.99/mo) raises that to 100 a day and 15 at once; Google AI Ultra (from $99.99/mo) to 300 a day and 60 at once","launched":2025},{"id":"claude-code","name":"Claude Code","provider":"Anthropic","category":"coding","description":"An agentic coding tool that lets Claude operate directly in your terminal, IDE, desktop app, or browser, reading files, editing code, running commands, and managing git workflows autonomously.","url":"https://code.claude.com/docs","pricing":"Included with Claude Pro ($20/mo), Max ($100/mo), Ultra ($200/mo), Team, and Enterprise plans; also usage-based via the Claude API","launched":2025},{"id":"cursor","name":"Cursor","provider":"SpaceXAI (formerly Anysphere)","category":"coding","description":"An AI-native code editor built on VS Code that provides inline code generation, multi-file editing, and codebase-aware chat powered by multiple foundation models. SpaceX closed its $60 billion all-stock acquisition of maker Anysphere on August 14, 2026, folding Cursor into the SpaceXAI unit alongside Grok Build and Grok Bot. Its consumer tiers now read Plus, Premium, Super, and Ultra, with Grok models bundled into the subscription (Plus is Grok-only) and Grok Bot included from Premium up.","url":"https://cursor.com","pricing":"Free, Plus $8/mo, Premium $30/mo, Super $100/mo, Ultra $200/mo, Teams from $30/user/mo, Enterprise custom","launched":2023},{"id":"github-copilot","name":"GitHub Copilot","provider":"GitHub / Microsoft","category":"coding","description":"An AI pair programmer integrated into popular editors that suggests code completions, generates functions from comments, and offers chat-based coding assistance.","url":"https://github.com/features/copilot","pricing":"Free tier, Pro $10/mo, Pro+ $39/mo, Max $100/mo, Business $19/seat/mo, Enterprise $39/seat/mo; usage metered in GitHub AI Credits","launched":2022},{"id":"windsurf","name":"Devin Desktop (formerly Windsurf)","provider":"Cognition","category":"coding","description":"An AI-native developer environment (rebranded from Windsurf in June 2026) that provides a unified surface for managing local and cloud coding agents, including Devin, Claude Code, Codex, and custom agents through the Agent Client Protocol.","url":"https://cognition.com","pricing":"Free tier, Pro $20/mo, Max $200/mo, Teams $80/mo plus $40/mo per full seat, Enterprise custom","launched":2024},{"id":"perplexity","name":"Perplexity","provider":"Perplexity AI","category":"research","description":"An AI-powered answer engine that searches the web in real time, synthesizes information from multiple sources, and provides cited responses to complex questions.","url":"https://www.perplexity.ai","pricing":"Free tier, Pro $17/mo and Max $167/mo when billed annually","launched":2022},{"id":"elicit","name":"Elicit","provider":"Elicit Inc.","category":"research","description":"A research assistant that helps find and analyze academic papers, extract key claims, and summarize findings across large bodies of scientific literature.","url":"https://elicit.com","pricing":"Free Basic tier; Pro $49/user/mo ($588 billed annually) and Scale $229/user/mo ($2,748 billed annually); Enterprise custom","launched":2021},{"id":"consensus","name":"Consensus","provider":"Consensus NLP","category":"research","description":"A search engine that uses AI to find and synthesize results from peer-reviewed scientific research, providing evidence-based answers with citations.","url":"https://consensus.app","pricing":"Free tier, Pro $20/mo ($144 billed annually); a higher Deep tier and custom Team plans are also offered","launched":2022},{"id":"chatgpt","name":"ChatGPT","provider":"OpenAI","category":"general","description":"A general-purpose AI assistant that can handle conversation, writing, coding, analysis, and web browsing, with agent mode, plugins, custom GPTs, Dots, and the Codex coding agent built in on paid plans.","url":"https://chatgpt.com","pricing":"Free tier, Go $8/mo, Plus $20/mo, Pro at $100, $200, or $500/mo (the $200 tier was closed to new sign-ups from September 10, 2026 and reopened on September 29, 2026), Business $25/seat/mo ($20 billed annually), Enterprise custom","launched":2022},{"id":"gemini","name":"Gemini","provider":"Google","category":"general","description":"Google's multimodal AI assistant with deep integration into Google Workspace, Search, and Android, capable of handling text, images, code, and long documents.","url":"https://gemini.google.com","pricing":"Free tier, Google AI Plus $4.99/mo, Google AI Pro $19.99/mo, Google AI Ultra from $99.99/mo","launched":2023},{"id":"gemini-spark","name":"Gemini Spark","provider":"Google","category":"general","description":"A 24/7 personal AI agent announced at Google I/O May 2026 that works in the background even when your phone and laptop are off, taking actions across Gmail, Calendar, Drive, Docs, and other connected apps under the user's direction. Google's release notes track it as a beta for Google AI Ultra subscribers 18 and over in the United States, with the macOS app added June 30, 2026. The standalone Spark product page no longer resolves, so treat the wider rollout as unconfirmed.","url":"https://gemini.google/release-notes/","pricing":"Included with Google AI Ultra (from $99.99/mo) for users 18 and over; Google's release notes describe the beta as United States only","launched":2026},{"id":"openclaw","name":"OpenClaw","provider":"OpenClaw Foundation","category":"general","description":"Open-source personal AI agent that runs locally, keeps context across conversations, and acts on the user's own machine, driven mainly through messaging platforms rather than a chat window. Shipped in 2025 as Clawdbot, renamed Moltbot over a trademark conflict, and settled on OpenClaw in January 2026; now stewarded by the independent OpenClaw Foundation, a 501(c)(3) with no paid tier, hosted service, or token.","url":"https://github.com/openclaw/openclaw","pricing":"Free and open source; you pay only whatever model provider it calls","launched":2025},{"id":"claude-cowork","name":"Claude Cowork","provider":"Anthropic","category":"general","description":"Anthropic's agent for knowledge work beyond coding, launched January 12, 2026 as a way to bring Claude Code's agentic loop to the rest of your work. It reads local files, connected tools, and the web, then produces finished documents, spreadsheets, and decks; scheduled tasks keep running unattended after the laptop closes. A built-in browser arrived August 26, 2026. From September 16, 2026 Anthropic began folding Cowork into the main Claude experience, so one conversation sizes the work itself; the merged surface reached Pro and Max first, with Team, Free, and Enterprise to follow.","url":"https://claude.com/product/cowork","pricing":"Included with Claude Pro ($20/mo), Max ($100/mo), Ultra ($200/mo), Team (from $20/seat/mo), and Enterprise plans","launched":2026},{"id":"claude-duet","name":"Claude Duet","provider":"Anthropic","category":"general","description":"A proactive standalone agent announced October 21, 2026 and aimed at professionals and small business owners. Built on Opus 5.5, it runs on a cloud virtual machine with its own browser, so it keeps working while your device is off, sends a morning brief, and asks for approval before it sends messages, makes payments, signs documents, or deletes anything. It reaches more than 6,000 connectors and plugins, including Gmail, Slack, Google Drive, Shopify, and QuickBooks. Anthropic cautions that it may misread a thread or misjudge urgency.","url":"https://claude.com/product/claude-duet","pricing":"No separate price. A waitlisted research preview included at no extra cost for Claude Pro, Max, and Ultra subscribers in the United States, drawing on the same plan usage limits; Team and Enterprise are not included yet","launched":2026},{"id":"grok-bot","name":"Grok Bot","provider":"xAI (SpaceXAI)","category":"general","description":"Always-on agents that each get their own cloud computer, sign into a customer's existing tools, and finish multi-step jobs unsupervised, including inside apps and sites that expose no clean API or MCP integration. Bots run in parallel around the clock after the user closes the laptop, run routines on a schedule, and come back when they need approval rather than direction at every step. A macOS desktop app is available.","url":"https://x.ai/bot","pricing":"No standalone plan. Included with weekly usage on SuperGrok ($30/mo) and higher xAI plans, and on Cursor Premium ($30/mo), Super, Ultra, Teams (from $30/seat/mo), and Enterprise","launched":2026},{"id":"manus","name":"Manus","provider":"Butterfly Effect","category":"general","description":"An autonomous general agent that plans and runs multi-step work on its own cloud computer, covering research, data analysis, slides, sites, and spreadsheets, and launched in invite-only beta on March 6, 2025. Meta bought maker Butterfly Effect for a reported $2 billion in December 2025, China's NDRC ordered the deal unwound in April 2026, and Manus resumed independent operations on September 1, 2026.","url":"https://manus.im","pricing":"Free tier with 300 daily refresh credits; Pro $20/mo (from 4,000 monthly credits) or $40/mo (from 8,000); Team $20/seat/mo; 17 percent off with annual billing","launched":2025},{"id":"claude","name":"Claude","provider":"Anthropic","category":"general","description":"A helpful AI assistant known for nuanced instruction-following, long-context understanding, and careful reasoning across writing, analysis, coding, and research tasks.","url":"https://claude.ai","pricing":"Free tier, Pro $20/mo ($17/mo billed annually), Max $100/mo, Ultra $200/mo (the former Max 20x tier, renamed from October 30, 2026), Team standard seats $25/seat/mo ($20 billed annually) and premium seats $125/seat/mo ($100 billed annually), Enterprise $20/seat plus usage at API rates","launched":2023},{"id":"openai-dots","name":"Dots","provider":"OpenAI","category":"general","description":"Always-on personal agents unveiled at OpenAI DevDay on September 29, 2026. A dot runs in the cloud on its own computer and browser, powered by GPT-6 Astra, and keeps working between conversations and after your machine is off. You reach it through ChatGPT, Slack, Microsoft Teams, or a voice call, with the same memory on every channel; it runs background agents in parallel, files Work and Codex tasks, and can hand you its cloud browser when a step needs you to sign in.","url":"https://learn.chatgpt.com/docs/dots","pricing":"No standalone plan. Included on ChatGPT Pro ($100, $200, or $500/mo) for users 18 and over outside the European Economic Area, the UK, and Switzerland, and rolling out worldwide on Business Premium and on Enterprise, where an admin has to switch it on","launched":2026},{"id":"midjourney","name":"Midjourney","provider":"Midjourney Inc.","category":"creative","description":"A leading AI image generation tool that creates high-quality, artistic images from text prompts, known for its distinctive aesthetic style and photorealistic output.","url":"https://www.midjourney.com","pricing":"Basic $10/mo, Standard $30/mo, Pro $60/mo, Mega $120/mo","launched":2022},{"id":"gpt-image","name":"GPT Image","provider":"OpenAI","category":"creative","description":"OpenAI's natively multimodal image generation and editing models, built into ChatGPT and served through the Image and Responses APIs. GPT-Image-2.5 Sunburst is the flagship for precise edits and GPT-Image-2.5 Flare the fast everyday tier; they succeed DALL-E 3, which OpenAI removed from the API on May 12, 2026.","url":"https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst","pricing":"Included in ChatGPT plans; API GPT-Image-2.5 Sunburst at $5 per 1M text input tokens, $8 per 1M image input tokens, and $30 per 1M image output tokens","launched":2025},{"id":"suno","name":"Suno","provider":"Suno Inc.","category":"creative","description":"An AI music generation platform that creates full songs with vocals, instruments, and lyrics from text prompts or custom lyrics input.","url":"https://suno.com","pricing":"Free tier, Pro $10/mo, Premier $30/mo","launched":2023},{"id":"langchain","name":"LangChain","provider":"LangChain Inc.","category":"frameworks","description":"An open-source framework for building LLM-powered applications with chains, agents, retrieval-augmented generation, and memory, supporting multiple model providers.","url":"https://www.langchain.com","pricing":"Open source (LangSmith platform has paid tiers)","launched":2022},{"id":"crewai","name":"CrewAI","provider":"CrewAI Inc.","category":"frameworks","description":"A framework for orchestrating role-playing AI agents that collaborate on complex tasks, allowing developers to define agent roles, goals, and delegation patterns.","url":"https://www.crewai.com","pricing":"Open source, Enterprise cloud plans available","launched":2024},{"id":"microsoft-agent-framework","name":"Microsoft Agent Framework","provider":"Microsoft","category":"frameworks","description":"Microsoft's open-source framework for building agents and graph-based multi-agent workflows in Python and .NET, with a Go SDK in a separate repo. Microsoft calls it the enterprise-ready successor to AutoGen and Semantic Kernel, both of which ship migration guides to it; 1.0 shipped in April 2026 and AutoGen is now in maintenance mode.","url":"https://learn.microsoft.com/en-us/agent-framework/","pricing":"Open source (MIT)","launched":2025},{"id":"openai-agents-api","name":"OpenAI Agents API","provider":"OpenAI","category":"frameworks","description":"A hosted API, in public beta since September 10, 2026, that runs cloud agents on the same open-source harness behind Codex. One call sets the task, model, tools, MCP servers, and environment; OpenAI handles context compaction, tool search, and parallel subagents, with sandboxes hosted by OpenAI, on your own infrastructure, or with partners such as Cloudflare, Daytona, E2B, Modal, and Vercel. It supersedes the Assistants API, which OpenAI sunset on August 26, 2026.","url":"https://openai.com/index/introducing-the-agents-api/","pricing":"No additional fee for the API; pay for model tokens and built-in tools at standard API rates, plus standard container rates for OpenAI-hosted sandboxes","launched":2026},{"id":"claude-mcp","name":"Model Context Protocol (MCP)","provider":"Agentic AI Foundation (created by Anthropic)","category":"frameworks","description":"An open protocol that standardizes how AI applications connect to external data sources and tools, enabling plug-and-play integrations for any MCP-compatible client. Created at Anthropic and now hosted as a project of the Linux Foundation's Agentic AI Foundation; the current spec revision is 2026-07-28.","url":"https://modelcontextprotocol.io","pricing":"Open source protocol","launched":2024}]}