# AI and agent tools we track

Canonical: https://theagenticweekly.com/tools · Last updated: 2026-10-26 · Author: Agentic Weekly

139 tools, each with a plain-English verdict and an evidence label (Reported = read from official sources, not run by us; Tested = we ran a small smoke test).

- [Langflow](https://theagenticweekly.com/tools/langflow) ([md](https://theagenticweekly.com/tools/langflow.md), Tested (smoke test, 2026-10-26, no LLM involved), updated 2026-10-26): MIT-licensed visual builder for AI agents and MCP servers with a very large GitHub following.
- [Amazon Q Developer](https://theagenticweekly.com/tools/amazon-q-developer) ([md](https://theagenticweekly.com/tools/amazon-q-developer.md), Reported (not run by us), updated 2026-10-25): AWS's AI coding assistant for IDEs and the CLI, with a free tier and a $19 Pro tier; IDE plugin support ends April 30, 2027.
- [AssemblyAI](https://theagenticweekly.com/tools/assemblyai) ([md](https://theagenticweekly.com/tools/assemblyai.md), Reported (not run by us), updated 2026-10-25): Speech AI APIs for transcription and understanding; start free, pay as you go.
- [Augment Code](https://theagenticweekly.com/tools/augment-code) ([md](https://theagenticweekly.com/tools/augment-code.md), Reported (not run by us), updated 2026-10-25): Coding agent and 'Cosmos' platform with a Context Engine, CLI and cloud agents; plans are flat team prices with usage included.
- [Base44](https://theagenticweekly.com/tools/base44) ([md](https://theagenticweekly.com/tools/base44.md), Reported (not run by us), updated 2026-10-25): No-code AI platform that builds apps and websites from your words, with backend, authentication, payments and hosting built in.
- [Beautiful.ai](https://theagenticweekly.com/tools/beautiful-ai) ([md](https://theagenticweekly.com/tools/beautiful-ai.md), Reported (not run by us), updated 2026-10-25): AI presentation platform with 300+ Smart Slide layouts; 14-day free trial.
- [Bolt](https://theagenticweekly.com/tools/bolt-new) ([md](https://theagenticweekly.com/tools/bolt-new.md), Reported (not run by us), updated 2026-10-25): Browser-based AI builder that turns a chat prompt into a hosted website or app, with a free plan and token-based tiers.
- [Botpress](https://theagenticweekly.com/tools/botpress) ([md](https://theagenticweekly.com/tools/botpress.md), Reported (not run by us), updated 2026-10-25): Customer-support AI agent platform with a free plan and conversation-based paid plans.
- [Canva AI](https://theagenticweekly.com/tools/canva-ai) ([md](https://theagenticweekly.com/tools/canva-ai.md), Reported (not run by us), updated 2026-10-25): Canva's AI image generator inside its design editor; free to try with plans for Pro, Business and Enterprise.
- [Cartesia](https://theagenticweekly.com/tools/cartesia) ([md](https://theagenticweekly.com/tools/cartesia.md), Reported (not run by us), updated 2026-10-25): Realtime voice AI: text-to-speech, speech-to-text in 44 languages and voice agents, with a free plan and credit tiers.
- [Cohere](https://theagenticweekly.com/tools/cohere) ([md](https://theagenticweekly.com/tools/cohere.md), Reported (not run by us), updated 2026-10-25): Enterprise AI company: Command models, Rerank and the North platform.
- [Copy.ai](https://theagenticweekly.com/tools/copy-ai) ([md](https://theagenticweekly.com/tools/copy-ai.md), Reported (not run by us), updated 2026-10-25): Go-to-market AI platform now priced by workflow credits.
- [Deepgram](https://theagenticweekly.com/tools/deepgram) ([md](https://theagenticweekly.com/tools/deepgram.md), Reported (not run by us), updated 2026-10-25): Voice AI APIs for speech-to-text, text-to-speech and agents with $200 in free credit.
- [DeepSeek](https://theagenticweekly.com/tools/deepseek) ([md](https://theagenticweekly.com/tools/deepseek.md), Reported (not run by us), updated 2026-10-25): Model API that works with the OpenAI and Anthropic SDK formats and can back agent tools such as Claude Code, GitHub Copilot and OpenCode.
- [Descript](https://theagenticweekly.com/tools/descript) ([md](https://theagenticweekly.com/tools/descript.md), Reported (not run by us), updated 2026-10-25): AI video and audio editor where you edit by editing text; Free plan, paid plans measured in media hours and AI credits.
- [Devin](https://theagenticweekly.com/tools/devin) ([md](https://theagenticweekly.com/tools/devin.md), Reported (not run by us), updated 2026-10-25): Cognition's autonomous software engineer: a cloud coding agent that tests in its own browser and aims to hand back a mergeable pull request.
- [Elicit](https://theagenticweekly.com/tools/elicit) ([md](https://theagenticweekly.com/tools/elicit.md), Reported (not run by us), updated 2026-10-25): AI research assistant that searches academic papers, extracts data and drafts reports; free Basic tier with paid per-user plans.
- [Fathom](https://theagenticweekly.com/tools/fathom) ([md](https://theagenticweekly.com/tools/fathom.md), Reported (not run by us), updated 2026-10-25): AI notetaker for Zoom, Google Meet and Microsoft Teams that is free for individuals.
- [Figma MCP server](https://theagenticweekly.com/tools/figma-mcp) ([md](https://theagenticweekly.com/tools/figma-mcp.md), Reported (not run by us), updated 2026-10-25): Figma's own MCP server that gives coding agents access to design files.
- [Firebase Studio](https://theagenticweekly.com/tools/firebase-studio) ([md](https://theagenticweekly.com/tools/firebase-studio.md), Reported (not run by us), updated 2026-10-25): Google's web-based AI workspace for full-stack apps; Google says it is sunsetting Firebase Studio on March 22, 2027 and new workspaces can no longer be created.
- [Firecrawl](https://theagenticweekly.com/tools/firecrawl) ([md](https://theagenticweekly.com/tools/firecrawl.md), Reported (not run by us), updated 2026-10-25): Web data API: search, scrape and crawl for AI agents.
- [Fireflies.ai](https://theagenticweekly.com/tools/fireflies) ([md](https://theagenticweekly.com/tools/fireflies.md), Reported (not run by us), updated 2026-10-25): AI meeting assistant with a free plan; paid plans $10 to $39 per seat per month billed annually.
- [FLUX (Black Forest Labs)](https://theagenticweekly.com/tools/black-forest-labs) ([md](https://theagenticweekly.com/tools/black-forest-labs.md), Reported (not run by us), updated 2026-10-25): Black Forest Labs' FLUX image models, available through an API with per-image pricing; the flux GitHub repository is Apache-2.0.
- [Freepik AI](https://theagenticweekly.com/tools/freepik) ([md](https://theagenticweekly.com/tools/freepik.md), Reported (not run by us), updated 2026-10-25): Stock library with AI suite and credit plans; credits valid for 1 year.
- [Goodcall](https://theagenticweekly.com/tools/goodcall) ([md](https://theagenticweekly.com/tools/goodcall.md), Reported (not run by us), updated 2026-10-25): A sensible first AI receptionist for a one-person shop; the per-customer pricing is simple, but test call quality yourself.
- [Grammarly](https://theagenticweekly.com/tools/grammarly) ([md](https://theagenticweekly.com/tools/grammarly.md), Reported (not run by us), updated 2026-10-25): AI writing assistant that works across apps; Free $0, Pro $12 per month, Enterprise custom.
- [Granola](https://theagenticweekly.com/tools/granola) ([md](https://theagenticweekly.com/tools/granola.md), Reported (not run by us), updated 2026-10-25): AI notepad for back-to-back meetings that captures device audio without a meeting bot.
- [Grok](https://theagenticweekly.com/tools/grok) ([md](https://theagenticweekly.com/tools/grok.md), Reported (not run by us), updated 2026-10-25): Grok is SpaceXAI's chat assistant, free to try on web and in apps, with a SuperGrok upgrade.
- [Gumloop](https://theagenticweekly.com/tools/gumloop) ([md](https://theagenticweekly.com/tools/gumloop.md), Reported (not run by us), updated 2026-10-25): Agent builder for teams; plans start at $37 per month with 20k included credits.
- [HeyGen](https://theagenticweekly.com/tools/heygen) ([md](https://theagenticweekly.com/tools/heygen.md), Reported (not run by us), updated 2026-10-25): AI avatar video with a Free plan and paid tiers at $29, $49 and $149 a month.
- [Hugging Face](https://theagenticweekly.com/tools/hugging-face) ([md](https://theagenticweekly.com/tools/hugging-face.md), Tested (smoke test, 2026-10-26, SmolLM2-135M from the Hub), updated 2026-10-26): The hub where the ML community shares models, datasets and apps, with PRO, Team and Enterprise tiers.
- [Ideogram](https://theagenticweekly.com/tools/ideogram) ([md](https://theagenticweekly.com/tools/ideogram.md), Reported (not run by us), updated 2026-10-25): AI image generator with Plus, Pro and Team plans, pay-as-you-go credits at 1 cent each, and an API.
- [invideo](https://theagenticweekly.com/tools/invideo) ([md](https://theagenticweekly.com/tools/invideo.md), Reported (not run by us), updated 2026-10-25): AI video editor with agents; plans at $10, $30 and $75 per seat a month billed annually.
- [Jasper](https://theagenticweekly.com/tools/jasper) ([md](https://theagenticweekly.com/tools/jasper.md), Reported (not run by us), updated 2026-10-25): AI platform for marketing teams with brand governance and AI visibility tracking; 7-day free trial.
- [Jobber Receptionist](https://theagenticweekly.com/tools/jobber) ([md](https://theagenticweekly.com/tools/jobber.md), Reported (not run by us), updated 2026-10-25): Best if you already use or plan to use Jobber for scheduling and invoicing; the receptionist works with your Jobber data.
- [Kiro](https://theagenticweekly.com/tools/kiro) ([md](https://theagenticweekly.com/tools/kiro.md), Reported (not run by us), updated 2026-10-25): AWS's agentic coding tool that turns prompts into requirements, designs and tasks (spec mode), with an IDE and a CLI.
- [Krea](https://theagenticweekly.com/tools/krea) ([md](https://theagenticweekly.com/tools/krea.md), Reported (not run by us), updated 2026-10-25): Creative AI suite for images, videos and upscaling; Free plan with 5,000 units a month.
- [Leonardo.Ai](https://theagenticweekly.com/tools/leonardo-ai) ([md](https://theagenticweekly.com/tools/leonardo-ai.md), Reported (not run by us), updated 2026-10-25): Image and video creation platform with a free tier, four individual plans, team seats and API pay-as-you-go.
- [Lindy](https://theagenticweekly.com/tools/lindy) ([md](https://theagenticweekly.com/tools/lindy.md), Reported (not run by us), updated 2026-10-25): AI 'employee' builder that connects to your tools; Free plan with $50 in credits that last 7 days, then credit-based plans.
- [LiteLLM](https://theagenticweekly.com/tools/litellm) ([md](https://theagenticweekly.com/tools/litellm.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): Useful as a single interface in front of local and hosted models; check the license files and pin the version because it releases daily.
- [llama.cpp](https://theagenticweekly.com/tools/llama-cpp) ([md](https://theagenticweekly.com/tools/llama-cpp.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): LLM inference in C/C++: the open-source engine many local-model tools build on; MIT-licensed with near-daily build tags.
- [LM Studio](https://theagenticweekly.com/tools/lm-studio) ([md](https://theagenticweekly.com/tools/lm-studio.md), Reported (not run by us), updated 2026-10-25): Desktop app for running open models locally; the homepage now leads with Bionic, an agent for work and code.
- [Make](https://theagenticweekly.com/tools/make) ([md](https://theagenticweekly.com/tools/make.md), Reported (not run by us), updated 2026-10-25): Visual automation platform: build scenarios by prompt or drag and drop, credits-based billing, a free plan with no time limit.
- [MCP reference servers](https://theagenticweekly.com/tools/mcp-servers) ([md](https://theagenticweekly.com/tools/mcp-servers.md), Tested (smoke test, 2026-10-25, no LLM involved), updated 2026-10-25): The MCP project's collection of reference servers.
- [Microsoft Copilot](https://theagenticweekly.com/tools/microsoft-copilot) ([md](https://theagenticweekly.com/tools/microsoft-copilot.md), Reported (not run by us), updated 2026-10-25): Microsoft's AI assistant for chat, creating and getting work done, with consumer and enterprise tiers.
- [Microsoft Copilot Studio](https://theagenticweekly.com/tools/copilot-studio) ([md](https://theagenticweekly.com/tools/copilot-studio.md), Reported (not run by us), updated 2026-10-25): Microsoft's platform for creating and managing custom agents, workflows and apps with no code.
- [Mistral Le Chat](https://theagenticweekly.com/tools/le-chat) ([md](https://theagenticweekly.com/tools/le-chat.md), Reported (not run by us), updated 2026-10-25): Mistral's AI assistant: Free, Pro at $14.99 a month, Team at $24.99 per user.
- [Murf AI](https://theagenticweekly.com/tools/murf-ai) ([md](https://theagenticweekly.com/tools/murf-ai.md), Reported (not run by us), updated 2026-10-25): Text-to-speech platform with a $10 free API trial, pay-as-you-go credits and per-character API pricing.
- [Notion AI](https://theagenticweekly.com/tools/notion-ai) ([md](https://theagenticweekly.com/tools/notion-ai.md), Reported (not run by us), updated 2026-10-25): Notion's built-in AI and agents; Free $0, Plus $10 and Business $20 per member per month, with AI usage drawing on credits.
- [Ollama](https://theagenticweekly.com/tools/ollama) ([md](https://theagenticweekly.com/tools/ollama.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): The common way to run open models locally on macOS, Windows and Linux, with a cloud option and an MIT-licensed open-source core.
- [Open WebUI](https://theagenticweekly.com/tools/open-webui) ([md](https://theagenticweekly.com/tools/open-webui.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): Self-hosted AI platform: a web interface that connects to Ollama and OpenAI-compatible models, under its own Open WebUI License.
- [OpenRouter](https://theagenticweekly.com/tools/openrouter) ([md](https://theagenticweekly.com/tools/openrouter.md), Reported (not run by us), updated 2026-10-25): Unified API to many models with fallbacks; a Free tier with 25+ free models and 4 free providers.
- [OpusClip](https://theagenticweekly.com/tools/opus-clip) ([md](https://theagenticweekly.com/tools/opus-clip.md), Reported (not run by us), updated 2026-10-25): Turns long videos into shorts and posts to social platforms; Free forever plan.
- [Otter.ai](https://theagenticweekly.com/tools/otter) ([md](https://theagenticweekly.com/tools/otter.md), Reported (not run by us), updated 2026-10-25): AI meeting agent with real-time transcription, summaries and action items; free plan, paid per-user plans.
- [Perplexity](https://theagenticweekly.com/tools/perplexity) ([md](https://theagenticweekly.com/tools/perplexity.md), Reported (not run by us), updated 2026-10-25): AI search with citations in every answer; Pro is $20 a month ($17 billed annually) and Max is $200 ($167 billed annually).
- [Pika](https://theagenticweekly.com/tools/pika) ([md](https://theagenticweekly.com/tools/pika.md), Reported (not run by us), updated 2026-10-25): AI creative platform with a free plan and monthly tiers at $10, $35 and $95.
- [Pipedream](https://theagenticweekly.com/tools/pipedream) ([md](https://theagenticweekly.com/tools/pipedream.md), Reported (not run by us), updated 2026-10-25): Integration layer for AI agents with managed auth and 10,000+ tools across 3,000+ APIs; free to build, pay in production.
- [Power Automate](https://theagenticweekly.com/tools/power-automate) ([md](https://theagenticweekly.com/tools/power-automate.md), Reported (not run by us), updated 2026-10-25): Microsoft's automation platform with a 30-day free trial and per-user and per-bot plans.
- [Pydantic AI](https://theagenticweekly.com/tools/pydantic-ai) ([md](https://theagenticweekly.com/tools/pydantic-ai.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): Python agent framework built on Pydantic types, covering agents, realtime voice, image generation and embeddings.
- [Qodo](https://theagenticweekly.com/tools/qodo) ([md](https://theagenticweekly.com/tools/qodo.md), Reported (not run by us), updated 2026-10-25): AI code review platform with 15+ agentic workflows for IDEs, pull requests and security, priced by team credits.
- [Read AI](https://theagenticweekly.com/tools/read-ai) ([md](https://theagenticweekly.com/tools/read-ai.md), Reported (not run by us), updated 2026-10-25): AI notetaker that works across Teams, Meet and Zoom; Free plan covers 5 meetings per month.
- [Recraft](https://theagenticweekly.com/tools/recraft) ([md](https://theagenticweekly.com/tools/recraft.md), Reported (not run by us), updated 2026-10-25): Text-to-image model and design platform for photorealism and vector output; V4.1 Flash is listed as the latest model.
- [Relevance AI](https://theagenticweekly.com/tools/relevance-ai) ([md](https://theagenticweekly.com/tools/relevance-ai.md), Reported (not run by us), updated 2026-10-25): Platform for specialist AI agents for sales, customer success, marketing and HR, with an embedded deployment team.
- [Replicate](https://theagenticweekly.com/tools/replicate) ([md](https://theagenticweekly.com/tools/replicate.md), Reported (not run by us), updated 2026-10-25): Cloud API for running and fine-tuning open models, with per-use pricing.
- [Resemble AI](https://theagenticweekly.com/tools/resemble-ai) ([md](https://theagenticweekly.com/tools/resemble-ai.md), Reported (not run by us), updated 2026-10-25): Resemble AI now leads with real-time deepfake detection and watermarking for audio, video and images; plans from free to $1,000 a month.
- [Retell AI](https://theagenticweekly.com/tools/retell) ([md](https://theagenticweekly.com/tools/retell.md), Reported (not run by us), updated 2026-10-25): Voice AI agents for phone calls with pay-per-minute pricing and 20 free concurrent calls.
- [Speechify](https://theagenticweekly.com/tools/speechify) ([md](https://theagenticweekly.com/tools/speechify.md), Reported (not run by us), updated 2026-10-25): Text-to-speech app that reads PDFs, books and web pages aloud, with a Free plan and a $29 monthly premium price.
- [Synthesia](https://theagenticweekly.com/tools/synthesia) ([md](https://theagenticweekly.com/tools/synthesia.md), Reported (not run by us), updated 2026-10-25): Business video platform with AI avatars in 140+ languages and a free credit allowance.
- [Together AI](https://theagenticweekly.com/tools/together-ai) ([md](https://theagenticweekly.com/tools/together-ai.md), Reported (not run by us), updated 2026-10-25): AI cloud for open models: serverless inference, fine-tuning and GPU clusters, priced per token.
- [Vapi](https://theagenticweekly.com/tools/vapi) ([md](https://theagenticweekly.com/tools/vapi.md), Reported (not run by us), updated 2026-10-25): Developer platform for voice agents; $5 free credits, then pay for the minutes you run.
- [Voiceflow](https://theagenticweekly.com/tools/voiceflow) ([md](https://theagenticweekly.com/tools/voiceflow.md), Reported (not run by us), updated 2026-10-25): Platform for chat and voice AI agents for customer experience teams.
- [Warp](https://theagenticweekly.com/tools/warp) ([md](https://theagenticweekly.com/tools/warp.md), Reported (not run by us), updated 2026-10-25): Warp's terminal and agent platform; it now pitches 'open infrastructure for cloud software factories' defined as code, with any model.
- [Writesonic](https://theagenticweekly.com/tools/writesonic) ([md](https://theagenticweekly.com/tools/writesonic.md), Reported (not run by us), updated 2026-10-25): Platform for tracking and improving visibility in AI search with article generation.
- [You.com](https://theagenticweekly.com/tools/you-com) ([md](https://theagenticweekly.com/tools/you-com.md), Reported (not run by us), updated 2026-10-25): You.com now presents itself as search and inference infrastructure for AI: web search, answer and research APIs plus an inference router.
- [Zapier](https://theagenticweekly.com/tools/zapier) ([md](https://theagenticweekly.com/tools/zapier.md), Reported (not run by us), updated 2026-10-25): No-code automation with 9,000+ apps and AI agents; free plan of 100 tasks a month.
- [Zed](https://theagenticweekly.com/tools/zed) ([md](https://theagenticweekly.com/tools/zed.md), Reported (not run by us), updated 2026-10-25): High-performance, multiplayer code editor from the creators of Atom and Tree-sitter, open source with AI optional.
- [LangGraph](https://theagenticweekly.com/tools/langgraph) ([md](https://theagenticweekly.com/tools/langgraph.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): A dependable foundation for stateful agents; this release is a routine fix, so only update if the RemoteGraph or recursion fixes affect you.
- [Vercel AI SDK](https://theagenticweekly.com/tools/vercel-ai-sdk) ([md](https://theagenticweekly.com/tools/vercel-ai-sdk.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): Vercel's TypeScript SDK that gives one API across many model providers, with streaming and agent helpers.
- [Activepieces](https://theagenticweekly.com/tools/activepieces) ([md](https://theagenticweekly.com/tools/activepieces.md), Reported (not run by us), updated 2026-10-25): Open-source workflow automation with chat, agents, tables and 770+ apps; $20 or $200 flat monthly plans.
- [Agno](https://theagenticweekly.com/tools/agno) ([md](https://theagenticweekly.com/tools/agno.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): Open-source agent framework that now sells a self-driving agent platform you run in your own cloud.
- [Claude Code](https://theagenticweekly.com/tools/claude-code) ([md](https://theagenticweekly.com/tools/claude-code.md), Tested (smoke test, 2026-10-25, local Qwen2.5-3B-Instruct, not vendor models), updated 2026-10-26): Update now if you use the sandbox or run Claude Code on a cloud provider; skip if you wanted flashy new features, this is a hardening release.
- [Codex CLI](https://theagenticweekly.com/tools/codex-cli) ([md](https://theagenticweekly.com/tools/codex-cli.md), Tested (smoke test, 2026-10-25, local Qwen2.5-3B-Instruct, not vendor models), updated 2026-10-26): A quality-of-life release: worth updating if you re-type the same prompts or switch models a lot, not a reason to switch tools.
- [Composio](https://theagenticweekly.com/tools/composio) ([md](https://theagenticweekly.com/tools/composio.md), Reported (not run by us), updated 2026-10-25): Managed tool-calling and authentication for agents across 1,500+ apps, with a free tier of 100,000 tool calls a month.
- [Context7](https://theagenticweekly.com/tools/context7) ([md](https://theagenticweekly.com/tools/context7.md), Tested (smoke test, 2026-10-25, no language model involved), updated 2026-10-26): Up-to-date, version-specific library docs served to coding agents.
- [CrewAI](https://theagenticweekly.com/tools/crewai) ([md](https://theagenticweekly.com/tools/crewai.md), Tested (smoke test, 2026-10-25, local Qwen2.5-3B-Instruct, not vendor models), updated 2026-10-25): Reasonable if you like the crew-of-agents mental model; the memory and tool-loop fixes in this release are worth taking.
- [Dify](https://theagenticweekly.com/tools/dify) ([md](https://theagenticweekly.com/tools/dify.md), Reported (not run by us), updated 2026-10-25): Open-source platform for building LLM apps and agent workflows with a visual canvas; licensed under a modified Apache 2.0 with extra conditions.
- [Gemini Notebook](https://theagenticweekly.com/tools/gemini-notebook) ([md](https://theagenticweekly.com/tools/gemini-notebook.md), Reported (not run by us), updated 2026-10-25): A good fit for turning a pile of documents into drafts and decks you can check against sources; availability of new features is rolling out.
- [goose](https://theagenticweekly.com/tools/goose) ([md](https://theagenticweekly.com/tools/goose.md), Tested (smoke test, 2026-10-25, local Qwen2.5-3B-Instruct, not vendor models), updated 2026-10-26): Pick goose if you want an open-source agent with real subagent controls; v1.56.0 is a solid, subagent-heavy update.
- [Kilo Code](https://theagenticweekly.com/tools/kilo-code) ([md](https://theagenticweekly.com/tools/kilo-code.md), Reported (not run by us), updated 2026-10-25): Open-source AI coding agent for VS Code, JetBrains, CLI and Cloud, with 500+ models at zero markup or your own keys.
- [Luma](https://theagenticweekly.com/tools/luma) ([md](https://theagenticweekly.com/tools/luma.md), Reported (not run by us), updated 2026-10-25): A good pick for creators who want several video models in one workspace; Ray 3.2 launched on June 9, 2026, so check which models are live on your plan.
- [OpenHands](https://theagenticweekly.com/tools/openhands) ([md](https://theagenticweekly.com/tools/openhands.md), Reported (not run by us), updated 2026-10-25): Open-source AI coding agent platform you can start locally, automate with workflows and run with any model.
- [Replit](https://theagenticweekly.com/tools/replit) ([md](https://theagenticweekly.com/tools/replit.md), Reported (not run by us), updated 2026-10-25): Strong pick if you want build, hosting and monitoring in one place; read the credit and overage rules first.
- [Chrome DevTools MCP](https://theagenticweekly.com/tools/chrome-devtools-mcp) ([md](https://theagenticweekly.com/tools/chrome-devtools-mcp.md), Tested (smoke test, 2026-10-25, no language model involved), updated 2026-10-26): Chrome DevTools for coding agents.
- [Google ADK](https://theagenticweekly.com/tools/google-adk) ([md](https://theagenticweekly.com/tools/google-adk.md), Tested (smoke test, 2026-10-25, local Qwen2.5-3B-Instruct, not vendor models), updated 2026-10-25): Update with care: a big, useful release for Gemini users, but it includes a telemetry default change.
- [LangChain](https://theagenticweekly.com/tools/langchain) ([md](https://theagenticweekly.com/tools/langchain.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): Open-source framework for building LLM applications and agents in Python and JavaScript, from the team behind LangGraph and LangSmith.
- [opencode](https://theagenticweekly.com/tools/opencode) ([md](https://theagenticweekly.com/tools/opencode.md), Tested (smoke test, 2026-10-25, local Qwen2.5-3B-Instruct, not vendor models), updated 2026-10-26): Update when convenient for the runtime security fixes; pick opencode if you want an open-source agent that is not tied to one model vendor.
- [Claude](https://theagenticweekly.com/tools/claude) ([md](https://theagenticweekly.com/tools/claude.md), Reported (not run by us), updated 2026-10-25): A strong writing partner; try Claude Duet only if you are on Pro or Max and comfortable with a research-preview product.
- [GitHub MCP Server](https://theagenticweekly.com/tools/github-mcp-server) ([md](https://theagenticweekly.com/tools/github-mcp-server.md), Tested (smoke test, 2026-10-26, no LLM involved), updated 2026-10-26): GitHub's official MCP server for repos, issues and pull requests.
- [Haystack](https://theagenticweekly.com/tools/haystack) ([md](https://theagenticweekly.com/tools/haystack.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): Apache-2.0 Python framework for building search, RAG and agent pipelines, maintained by deepset.
- [Mastra](https://theagenticweekly.com/tools/mastra) ([md](https://theagenticweekly.com/tools/mastra.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): A strong TypeScript option if you are building agents in a Node stack; read the breaking-change note on sessions before upgrading.
- [MCP Inspector](https://theagenticweekly.com/tools/mcp-inspector) ([md](https://theagenticweekly.com/tools/mcp-inspector.md), Tested (smoke test, 2026-10-25, no LLM involved), updated 2026-10-25): The quickest way to check what an MCP server exposes; run it on a current Node or npm may quietly install version 0.15.0.
- [ChatGPT](https://theagenticweekly.com/tools/chatgpt) ([md](https://theagenticweekly.com/tools/chatgpt.md), Reported (not run by us), updated 2026-10-25): Still the broadest all-round assistant; the October updates matter most if you write documents, decks or work with audio.
- [FastMCP](https://theagenticweekly.com/tools/fastmcp) ([md](https://theagenticweekly.com/tools/fastmcp.md), Tested (smoke test, 2026-10-25, no language model involved), updated 2026-10-26): If you run FastMCP servers, upgrade and read the security notices; the OAuth issuer step is not automatic.
- [Gemini CLI](https://theagenticweekly.com/tools/gemini-cli) ([md](https://theagenticweekly.com/tools/gemini-cli.md), Reported (not run by us), updated 2026-10-25): Skip it as a new starter on a consumer plan; keep it only if you are on an enterprise license or a paid API key.
- [Jan](https://theagenticweekly.com/tools/jan) ([md](https://theagenticweekly.com/tools/jan.md), Reported (not run by us), updated 2026-10-25): Open-source alternative to ChatGPT that runs open models locally or connects to cloud models like GPT and Claude.
- [n8n](https://theagenticweekly.com/tools/n8n) ([md](https://theagenticweekly.com/tools/n8n.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): Great fit for small teams that want to wire apps and AI together without code; the license is fair-code, not open source.
- [ElevenLabs](https://theagenticweekly.com/tools/elevenlabs) ([md](https://theagenticweekly.com/tools/elevenlabs.md), Reported (not run by us), updated 2026-10-25): Best for builders adding voice or music to products; the Video to Music API is the interesting new piece for creators.
- [v0](https://theagenticweekly.com/tools/v0) ([md](https://theagenticweekly.com/tools/v0.md), Reported (not run by us), updated 2026-10-25): Good for UI-heavy web work, especially if you deploy on Vercel; the October changes are about teamwork and polish.
- [ComfyUI](https://theagenticweekly.com/tools/comfyui) ([md](https://theagenticweekly.com/tools/comfyui.md), Tested (smoke test, 2026-10-26, no LLM involved), updated 2026-10-26): The tool to learn if you want maximum control over open models on your own GPU; it has a learning curve.
- [Cline](https://theagenticweekly.com/tools/cline) ([md](https://theagenticweekly.com/tools/cline.md), Reported (not run by us), updated 2026-10-25): A good open-source pick if you want an agent inside your IDE or a CLI and an SDK to embed it; the October notes are incremental.
- [Cursor](https://theagenticweekly.com/tools/cursor) ([md](https://theagenticweekly.com/tools/cursor.md), Reported (not run by us), updated 2026-10-26): Worth a look if you run agents on several repos or want one place for editor, cloud agents and Git hosting; the October changes are mostly for teams.
- [Browser Use](https://theagenticweekly.com/tools/browser-use) ([md](https://theagenticweekly.com/tools/browser-use.md), Reported (not run by us), updated 2026-10-25): Open-source library that lets AI agents drive a browser, with a pay-as-you-go cloud browser starting at $0.02 an hour.
- [GitHub Copilot](https://theagenticweekly.com/tools/github-copilot) ([md](https://theagenticweekly.com/tools/github-copilot.md), Reported (not run by us), updated 2026-10-25): A sensible default if your team already lives on GitHub; check which plan you need for new models.
- [Kling AI](https://theagenticweekly.com/tools/kling) ([md](https://theagenticweekly.com/tools/kling.md), Reported (not run by us), updated 2026-10-25): Worth testing for action and camera-heavy shots; our information is secondhand from Luma plus the Kling homepage.
- [OpenAI Agents SDK](https://theagenticweekly.com/tools/openai-agents-sdk) ([md](https://theagenticweekly.com/tools/openai-agents-sdk.md), Tested (smoke test, 2026-10-25, local Qwen2.5-3B-Instruct, not vendor models), updated 2026-10-25): Pick it if you want a small, official framework for multi-agent flows on the OpenAI API; the update is incremental.
- [Runway](https://theagenticweekly.com/tools/runway) ([md](https://theagenticweekly.com/tools/runway.md), Reported (not run by us), updated 2026-10-25): A strong choice if you want one place to drive many video, image and audio models from an agent; many items are paid-plan only.
- [Lovable](https://theagenticweekly.com/tools/lovable) ([md](https://theagenticweekly.com/tools/lovable.md), Reported (not run by us), updated 2026-10-25): A friendly way for non-developers to get a working web app and a first-customers plan; check credit costs before you commit.
- [Supabase MCP](https://theagenticweekly.com/tools/supabase-mcp) ([md](https://theagenticweekly.com/tools/supabase-mcp.md), Tested (smoke test, 2026-10-26, no LLM involved), updated 2026-10-26): Connect Supabase projects to AI assistants.
- [DSPy](https://theagenticweekly.com/tools/dspy) ([md](https://theagenticweekly.com/tools/dspy.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): Worth a look if you want structured, testable LM pipelines; start with a plain Predict module before optimisers.
- [Midjourney](https://theagenticweekly.com/tools/midjourney) ([md](https://theagenticweekly.com/tools/midjourney.md), Reported (not run by us), updated 2026-10-25): Use the thinking rerun if prompt-following misses are your pain; be careful with privacy when sharing folders.
- [Semantic Kernel](https://theagenticweekly.com/tools/semantic-kernel) ([md](https://theagenticweekly.com/tools/semantic-kernel.md), Reported (not run by us), updated 2026-10-25): Microsoft's model-agnostic SDK for building AI agents; its README calls Microsoft Agent Framework the enterprise-ready successor.
- [Sentry MCP](https://theagenticweekly.com/tools/sentry-mcp) ([md](https://theagenticweekly.com/tools/sentry-mcp.md), Tested (smoke test, 2026-10-26, no LLM involved), updated 2026-10-26): Sentry's agentic tooling and MCP server for errors and traces.
- [Playwright MCP](https://theagenticweekly.com/tools/playwright-mcp) ([md](https://theagenticweekly.com/tools/playwright-mcp.md), Tested (smoke test, 2026-10-25, no language model involved), updated 2026-10-26): Microsoft's MCP server that lets agents drive a browser with Playwright.
- [Mem0](https://theagenticweekly.com/tools/mem0) ([md](https://theagenticweekly.com/tools/mem0.md), Tested (smoke test, 2026-10-26, local 3B model plus a local embedder), updated 2026-10-26): Open-source and hosted memory layer that lets agents remember users across sessions, with a free tier and published request quotas.
- [LlamaIndex](https://theagenticweekly.com/tools/llamaindex) ([md](https://theagenticweekly.com/tools/llamaindex.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): Open-source data framework for retrieval-augmented generation and document-centred agents, with a hosted document platform alongside.
- [Notion MCP Server](https://theagenticweekly.com/tools/notion-mcp) ([md](https://theagenticweekly.com/tools/notion-mcp.md), Tested (smoke test, 2026-10-26, no LLM involved), updated 2026-10-26): Official Notion MCP server for reading and editing workspace content.
- [Instructor](https://theagenticweekly.com/tools/instructor) ([md](https://theagenticweekly.com/tools/instructor.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): A small, light way to get typed output from a model; good first step before reaching for a full framework.
- [Suno](https://theagenticweekly.com/tools/suno) ([md](https://theagenticweekly.com/tools/suno.md), Reported (not run by us), updated 2026-10-25): The most complete song-making tool we track; the v6 editing features are the draw. Rights and licensing questions are yours to check.
- [Piper](https://theagenticweekly.com/tools/piper) ([md](https://theagenticweekly.com/tools/piper.md), Tested (smoke test, 2026-10-25, no LLM involved), updated 2026-10-25): Fast, private speech synthesis on a CPU; mind the GPL-3.0 license if you embed it.
- [Flowise](https://theagenticweekly.com/tools/flowise) ([md](https://theagenticweekly.com/tools/flowise.md), Reported (not run by us), updated 2026-10-25): Open-source drag-and-drop builder for LLM flows and agents; GitHub marks the main repository as archived with its last push in Aug 2026.
- [Continue](https://theagenticweekly.com/tools/continue) ([md](https://theagenticweekly.com/tools/continue.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): A configurable open-source assistant; the CLI worked with a local model through a YAML config.
- [Windsurf (now Devin Desktop)](https://theagenticweekly.com/tools/windsurf) ([md](https://theagenticweekly.com/tools/windsurf.md), Reported (not run by us), updated 2026-10-25): Windsurf was renamed Devin Desktop on June 2, 2026: a full IDE with an Agent Command Center for managing local and cloud coding agents.
- [smolagents](https://theagenticweekly.com/tools/smolagents) ([md](https://theagenticweekly.com/tools/smolagents.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): Hugging Face's small Python library for agents that write and run code; the docs say the core logic fits in roughly a thousand lines.
- [Letta](https://theagenticweekly.com/tools/letta) ([md](https://theagenticweekly.com/tools/letta.md), Reported (not run by us), updated 2026-10-25): Platform and open-source framework for stateful agents that keep and improve memory across sessions.
- [Aider](https://theagenticweekly.com/tools/aider) ([md](https://theagenticweekly.com/tools/aider.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): Open-source AI pair programming in your terminal that maps your codebase and connects to almost any LLM, including local models.
- [ACE-Step](https://theagenticweekly.com/tools/ace-step) ([md](https://theagenticweekly.com/tools/ace-step.md), Reported (not run by us), updated 2026-10-25): The pick if you want open weights and local control; expect a manual setup and no recent updates.
- [faster-whisper](https://theagenticweekly.com/tools/faster-whisper) ([md](https://theagenticweekly.com/tools/faster-whisper.md), Tested (smoke test, 2026-10-25, no language model involved), updated 2026-10-26): Fast local transcription; on CPU use float32 and check int8 against a reference before trusting it.
- [AutoGen](https://theagenticweekly.com/tools/autogen) ([md](https://theagenticweekly.com/tools/autogen.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)), updated 2026-10-25): Microsoft's open-source multi-agent framework; its README now says the project is in maintenance mode and points to Microsoft Agent Framework.
- [GPT4All](https://theagenticweekly.com/tools/gpt4all) ([md](https://theagenticweekly.com/tools/gpt4all.md), Tested (smoke test, 2026-10-26, local 3B model (Qwen2.5-3B)), updated 2026-10-26): Local chatbot from Nomic that runs open-source models on your device; the latest GitHub release we saw is v3.10.0 from Feb 2025.

## How to cite

Agentic Weekly, "AI and agent tools we track", last updated 2026-10-26, https://theagenticweekly.com/tools