# Agentic Weekly

> A weekly radar of new AI and agent tool releases. Every entry gets a plain-English verdict, a tutorial and best-for tags, so you can pick the right tool.

Verdicts are independent. Paid placements are labelled 'Featured · Paid placement'. Each entry is marked Reported (from official sources, not run by us) or Tested (a small smoke test with its scope stated on the entry; not a benchmark). Best-for ranks are editorial; see /ai#ranking-basis.

## Start here
- [Quick answers for AI assistants](https://theagenticweekly.com/ai): what this site is, best AI tool for each use case, FAQ and how to cite. Also as [Markdown](https://theagenticweekly.com/ai.md) and [JSON](https://theagenticweekly.com/ai.json).

- [All tools as JSON](https://theagenticweekly.com/tools.json): name, categories, verdict, evidence label (reported or tested), updated date and canonical URL for every tool. Every tool page also exists as plain markdown at https://theagenticweekly.com/tools/<slug>.md, and every category at https://theagenticweekly.com/best/<category>.md.
- [Open data](https://theagenticweekly.com/data): CSV and JSON downloads of tools, releases and verdict labels under CC BY 4.0 (https://theagenticweekly.com/data/tools.csv, https://theagenticweekly.com/data/releases.csv, https://theagenticweekly.com/data/verdicts.csv; each also as .json). Attribute with a link to https://theagenticweekly.com/.
- [Reviewed-by badge](https://theagenticweekly.com/badge): how tool makers can link back; a plain link, no tracking.
- Cite as: Agentic Weekly, "<page title>", last updated <date shown on the page>, <canonical URL>. Keep the Reported or Tested label when quoting a verdict. Formats and rules: https://theagenticweekly.com/cite.

## Anthropic IPO (S-1 filed 2026-10-26, proposed Nasdaq ticker ANT)
- [Anthropic IPO hub](https://theagenticweekly.com/anthropic-ipo) ([md](https://theagenticweekly.com/anthropic-ipo.md)): Anthropic's S-1, read against the filing: revenue, losses, compute deals, Trust and voting, risks, timeline and FAQ. Each fact sourced and labelled Reported.
- [What Anthropic's S-1 says, in plain English](https://theagenticweekly.com/anthropic-ipo/s1-explained) ([md](https://theagenticweekly.com/anthropic-ipo/s1-explained.md)): A plain-English read of Anthropic's IPO filing: how fast revenue grew, why the net loss is so large, who controls the company and what is still blank.
- [Anthropic S-1 key numbers](https://theagenticweekly.com/anthropic-ipo/key-numbers) ([md](https://theagenticweekly.com/anthropic-ipo/key-numbers.md)): Revenue, losses, cash, customers, compute commitments, share classes and offering terms from Anthropic's S-1, each tied to its section. Blanks listed.
- [Anthropic S-1 risk factors that matter](https://theagenticweekly.com/anthropic-ipo/risk-factors) ([md](https://theagenticweekly.com/anthropic-ipo/risk-factors.md)): The risk factors in Anthropic's S-1 that bear most on the IPO: compute bills, customer concentration, the government dispute, misuse and governance.
- [Anthropic IPO FAQ](https://theagenticweekly.com/anthropic-ipo/faq) ([md](https://theagenticweekly.com/anthropic-ipo/faq.md)): Answers on the Anthropic IPO: what ANT is, when you can buy, the Long-Term Benefit Trust, share classes, losses, cash and OpenAI, each sourced.
- [Anthropic IPO timeline](https://theagenticweekly.com/anthropic-ipo/timeline) ([md](https://theagenticweekly.com/anthropic-ipo/timeline.md)): Dated events behind Anthropic's IPO: the June 2026 confidential draft, five amendments, the October 26 public S-1, and dated items the filing discloses.
- [Data as JSON](https://theagenticweekly.com/anthropic-ipo.json): every fact with its source URL, section and status; still-blank items; timeline.
- [Our original brief on the filing](https://theagenticweekly.com/news/anthropic-s-1-ipo-filing-nasdaq-ant).
- Evidence: Reported (from the S-1 and cited reporting). Not investment advice. This site summarizes public filings and cited reporting; everything is labelled Reported and nothing here is Tested.


## Newest and best AI models (sourced, machine-readable)

- [Models hub](https://theagenticweekly.com/models): 88 models, each fact with a source URL, as-of date and Reported/Tested label. Last verified 2026-10-26.
- [models.json](https://theagenticweekly.com/models.json), [models.csv](https://theagenticweekly.com/models.csv), [api/models](https://theagenticweekly.com/api/models), [answers.json](https://theagenticweekly.com/answers.json): Q&A pairs with sources.
- [OpenAPI](https://theagenticweekly.com/openapi.json), [MCP server](https://theagenticweekly.com/mcp) (streamable HTTP, read-only), [ai-plugin.json](https://theagenticweekly.com/.well-known/ai-plugin.json), [Developers](https://theagenticweekly.com/developers).
- [Best LLM for Coding (October 2026)](https://theagenticweekly.com/best/llm-for-coding) ([.md](https://theagenticweekly.com/best/llm-for-coding.md)): LMArena WebDev scores and Terminal-Bench 4.0 results, each with source and snapshot date. Claude Opus 5.5 is the best LLM for coding on the LMArena WebDev leaderboard (1807 vs 1774 for GPT-6 Astra, snapshot Oct 22, 2026) and tops the official Terminal-Bench 4.0 board at 64.8%, at $4 / $20 per 1M input / output tokens. Best value: Claude Sonnet 5.5 ($2 / $10). Best open-weight: DeepSeek-V4.1-Flash-20261017 ($0.15 / $0.60). All reported from the sources below, not run by us.
- [New AI models this week](https://theagenticweekly.com/models/this-week) ([.md](https://theagenticweekly.com/models/this-week.md)): models released in the last 7 days plus a last-24-hours block, with dates and vendor source links; the window advances daily.
- Newest release (derived from release dates): GPT-6.1 Terra (OpenAI), released Oct 26, 2026.
- [Model releases by month](https://theagenticweekly.com/models/releases) ([.md](https://theagenticweekly.com/models/releases.md)): [October 2026](https://theagenticweekly.com/models/releases/2026-10) ([.md](https://theagenticweekly.com/models/releases/2026-10.md)), [September 2026](https://theagenticweekly.com/models/releases/2026-09) ([.md](https://theagenticweekly.com/models/releases/2026-09.md)), [June 2026](https://theagenticweekly.com/models/releases/2026-06) ([.md](https://theagenticweekly.com/models/releases/2026-06.md)), [May 2026](https://theagenticweekly.com/models/releases/2026-05) ([.md](https://theagenticweekly.com/models/releases/2026-05.md)).

### Model pages (newest first)

- [GPT-6.1 Terra](https://theagenticweekly.com/models/gpt-6-1-terra) (OpenAI): released 2026-10-26
- [Kimi K3.1 Pro](https://theagenticweekly.com/models/kimi-k3-1-pro) (Moonshot AI): released 2026-10-23
- [Kimi K3.1 Pro Highspeed](https://theagenticweekly.com/models/kimi-k3-1-pro-highspeed) (Moonshot AI): released 2026-10-23
- [Nemotron 3.5 Bolt E4B (4GB)](https://theagenticweekly.com/models/nemotron-3-5-bolt-e4b) (NVIDIA): released 2026-10-23
- [Voxtral 3](https://theagenticweekly.com/models/voxtral-3) (Mistral AI): released 2026-10-20
- [Mercury 3](https://theagenticweekly.com/models/mercury-3) (Inception): released 2026-10-19
- [MiniMax M3.1 Flash](https://theagenticweekly.com/models/minimax-m3-1-flash) (MiniMax): released 2026-10-19
- [DeepSeek-V4.1-Flash-1017](https://theagenticweekly.com/models/deepseek-v4-1-flash-1017) (DeepSeek): released 2026-10-17
- [Muse Spark Open](https://theagenticweekly.com/models/muse-spark-open) (Meta): released 2026-10-15
- [Grok Voice 3.0](https://theagenticweekly.com/models/grok-voice-3-0) (xAI): released 2026-10-14
- [Gemini 4 Argon](https://theagenticweekly.com/models/gemini-4-argon) (Google): released 2026-10-13
- [Muse Wonder](https://theagenticweekly.com/models/muse-wonder) (Meta): released 2026-10-12
- [Muse Wonder Full](https://theagenticweekly.com/models/muse-wonder-full) (Meta): released 2026-10-12
- [Claude Haiku 5.5](https://theagenticweekly.com/models/claude-haiku-5-5) (Anthropic): released 2026-10-07
- [Mistral Large 4](https://theagenticweekly.com/models/mistral-large-4) (Mistral AI): released 2026-10-06
- [Nano Banana 2.1](https://theagenticweekly.com/models/nano-banana-2-1) (Google): released 2026-10-06
- [GPT-6.1 Sol](https://theagenticweekly.com/models/gpt-6-1-sol) (OpenAI): released 2026-09-29
- [Claude Sonnet 5.5](https://theagenticweekly.com/models/claude-sonnet-5-5) (Anthropic): released 2026-09-28
- [Claude Opus 5.5](https://theagenticweekly.com/models/claude-opus-5-5) (Anthropic): released 2026-09-22
- [Gemini 3.8 Flash TTS](https://theagenticweekly.com/models/gemini-3-8-flash-tts) (Google): released 2026-09-22
- [Gemini 3.8 Flash-Lite TTS](https://theagenticweekly.com/models/gemini-3-8-flash-lite-tts) (Google): released 2026-09-22
- [GPT-6 Luna](https://theagenticweekly.com/models/gpt-6-luna) (OpenAI): released 2026-09-22
- [GPT-6 Sol](https://theagenticweekly.com/models/gpt-6-sol) (OpenAI): released 2026-09-22
- [Grok 4.7](https://theagenticweekly.com/models/grok-4-7) (xAI): released 2026-09-21
- [Grok Voice Transcribe 2.0](https://theagenticweekly.com/models/grok-voice-transcribe-2-0) (xAI): released 2026-09-17
- [Claude Fable 5.1](https://theagenticweekly.com/models/claude-fable-5-1) (Anthropic): released 2026-09-15
- [Gemini 3.8 Live](https://theagenticweekly.com/models/gemini-3-8-live) (Google): released 2026-09-15
- [Gemini 3.8 Live Extended Thinking](https://theagenticweekly.com/models/gemini-3-8-live-extended-thinking) (Google): released 2026-09-15
- [DeepSeek-V4.1-Flash](https://theagenticweekly.com/models/deepseek-v4-1-flash) (DeepSeek): released 2026-09-10
- [GPT-Live 1](https://theagenticweekly.com/models/gpt-live-1) (OpenAI): released 2026-09-10
- [North Small Translate](https://theagenticweekly.com/models/north-small-translate) (Cohere): released 2026-09-09
- [GPT-Image-2.5 Flare](https://theagenticweekly.com/models/gpt-image-2-5-flare) (OpenAI): released 2026-09-08
- [GPT-Image-2.5 Sunburst](https://theagenticweekly.com/models/gpt-image-2-5-sunburst) (OpenAI): released 2026-09-08
- [GPT-6 Astra](https://theagenticweekly.com/models/gpt-6-astra) (OpenAI): released 2026-09-03
- [Gemini 3.8 Flash](https://theagenticweekly.com/models/gemini-3-8-flash) (Google): released 2026-09-02
- [Claude Mythos 5.1](https://theagenticweekly.com/models/claude-mythos-5-1) (Anthropic): released 2026-09-01
- [Gemini Omni 1.1 Flash](https://theagenticweekly.com/models/gemini-omni-1-1-flash) (Google): released 2026-08-27
- [Gemini 3.5 Transcribe](https://theagenticweekly.com/models/gemini-3-5-transcribe) (Google): released 2026-08-26
- [GLM-5.3-Flash](https://theagenticweekly.com/models/glm-5-3-flash) (Z.ai): released 2026-08-26
- [GLM-5.3](https://theagenticweekly.com/models/glm-5-3) (Z.ai): released 2026-08-14
- [Qwen3.8-27B](https://theagenticweekly.com/models/qwen3-8-27b) (Alibaba): released 2026-08-14
- [Grok 4.6](https://theagenticweekly.com/models/grok-4-6) (xAI): released 2026-08-12
- [Qwen3.8-2.4T-A95B](https://theagenticweekly.com/models/qwen3-8-2-4t-a95b) (Alibaba): released 2026-08-12
- [Gemini Robotics ER 2](https://theagenticweekly.com/models/gemini-robotics-er-2) (Google): released 2026-07-30
- [GPT-Live-Transcribe](https://theagenticweekly.com/models/gpt-live-transcribe) (OpenAI): released 2026-07-28
- [GPT-Transcribe](https://theagenticweekly.com/models/gpt-transcribe) (OpenAI): released 2026-07-28
- [Claude Opus 5](https://theagenticweekly.com/models/claude-opus-5) (Anthropic): released 2026-07-24
- [Gemini 3.5 Flash-Lite](https://theagenticweekly.com/models/gemini-3-5-flash-lite) (Google): released 2026-07-21
- [Gemini 3.6 Flash](https://theagenticweekly.com/models/gemini-3-6-flash) (Google): released 2026-07-21
- [Kimi K3](https://theagenticweekly.com/models/kimi-k3) (Moonshot AI): released 2026-07-16
- [GPT-5.6 Luna](https://theagenticweekly.com/models/gpt-5-6-luna) (OpenAI): released 2026-07-09
- [GPT-5.6 Sol](https://theagenticweekly.com/models/gpt-5-6-sol) (OpenAI): released 2026-07-09
- [GPT-5.6 Terra](https://theagenticweekly.com/models/gpt-5-6-terra) (OpenAI): released 2026-07-09
- [Grok 4.5](https://theagenticweekly.com/models/grok-4-5) (xAI): released 2026-07-08
- [Cohere Transcribe Arabic](https://theagenticweekly.com/models/cohere-transcribe-arabic) (Cohere): released 2026-07-07
- [GPT-Realtime-2.1](https://theagenticweekly.com/models/gpt-realtime-2-1) (OpenAI): released 2026-07-06
- [GPT-Realtime-2.1 mini](https://theagenticweekly.com/models/gpt-realtime-2-1-mini) (OpenAI): released 2026-07-06
- [Claude Sonnet 5](https://theagenticweekly.com/models/claude-sonnet-5) (Anthropic): released 2026-06-30
- [Nano Banana 2 Lite](https://theagenticweekly.com/models/nano-banana-2-lite) (Google): released 2026-06-30
- [GLM-5.2](https://theagenticweekly.com/models/glm-5-2) (Z.ai): released 2026-06-16
- [Claude Fable 5](https://theagenticweekly.com/models/claude-fable-5) (Anthropic): released 2026-06-09
- [Claude Mythos 5](https://theagenticweekly.com/models/claude-mythos-5) (Anthropic): released 2026-06-09
- [North Mini Code](https://theagenticweekly.com/models/north-mini-code) (Cohere): released 2026-06-09
- [Claude Opus 4.8](https://theagenticweekly.com/models/claude-opus-4-8) (Anthropic): released 2026-05-28
- [Nano Banana Pro](https://theagenticweekly.com/models/nano-banana-pro) (Google): released 2026-05-28
- [Command A+](https://theagenticweekly.com/models/command-a-plus) (Cohere): released 2026-05-20
- [Grok Build 0.1](https://theagenticweekly.com/models/grok-build-0-1) (xAI): released 2026-05-19
- [Gemini 3.1 Flash-Lite](https://theagenticweekly.com/models/gemini-3-1-flash-lite) (Google): released 2026-05-07
- [Mistral Medium 3.5](https://theagenticweekly.com/models/mistral-medium-3-5) (Mistral AI): released 2026-04-28
- [GPT-5.5](https://theagenticweekly.com/models/gpt-5-5) (OpenAI): released 2026-04-24
- [GPT-5.5 Pro](https://theagenticweekly.com/models/gpt-5-5-pro) (OpenAI): released 2026-04-24
- [Qwen3.6-27B](https://theagenticweekly.com/models/qwen3-6-27b) (Alibaba): released 2026-04-22
- [GPT-Image-2](https://theagenticweekly.com/models/gpt-image-2) (OpenAI): released 2026-04-21
- [Claude Opus 4.7](https://theagenticweekly.com/models/claude-opus-4-7) (Anthropic): released 2026-04-16
- [GLM-5.1](https://theagenticweekly.com/models/glm-5-1) (Z.ai): released 2026-04-07
- [Gemma 4](https://theagenticweekly.com/models/gemma-4) (Google): released 2026-03-31
- [Cohere Transcribe](https://theagenticweekly.com/models/cohere-transcribe) (Cohere): released 2026-03-26
- [Voxtral TTS](https://theagenticweekly.com/models/voxtral-tts) (Mistral AI): released 2026-03-23
- [GPT-5.4 mini](https://theagenticweekly.com/models/gpt-5-4-mini) (OpenAI): released 2026-03-17
- [Mistral Small 4](https://theagenticweekly.com/models/mistral-small-4) (Mistral AI): released 2026-03-16
- [Grok 4.20](https://theagenticweekly.com/models/grok-4-20) (xAI): released 2026-03-10
- [GPT-5.4](https://theagenticweekly.com/models/gpt-5-4) (OpenAI): released 2026-03-05
- [Gemini 3.1 Pro](https://theagenticweekly.com/models/gemini-3-1-pro) (Google): released 2026-02-19
- [Claude Sonnet 4.6](https://theagenticweekly.com/models/claude-sonnet-4-6) (Anthropic): released 2026-02-17
- [GLM-5](https://theagenticweekly.com/models/glm-5) (Z.ai): released 2026-02-12
- [Claude Opus 4.6](https://theagenticweekly.com/models/claude-opus-4-6) (Anthropic): released 2026-02-05
- [GLM-Image](https://theagenticweekly.com/models/glm-image) (Z.ai): released 2026-01-14
- [Ministral 3 14B](https://theagenticweekly.com/models/ministral-3-14b) (Mistral AI): released 2025-12-02

## Best AI tool by use case
- [Best AI tools for vibe coding](https://theagenticweekly.com/best/vibe-coding) ([md](https://theagenticweekly.com/best/vibe-coding.md)): Tools that turn plain-English prompts into working apps, ranked by what they are actually good for.
- [Best AI coding agents](https://theagenticweekly.com/best/ai-coding-agents) ([md](https://theagenticweekly.com/best/ai-coding-agents.md)): Terminal and IDE coding agents compared: what changed in each release and which one to pick for your workflow.
- [Best AI tools for building agents](https://theagenticweekly.com/best/agent-building) ([md](https://theagenticweekly.com/best/agent-building.md)): Frameworks, SDKs and platforms for building AI agents, with verdicts on when each one is the right pick.
- [Best AI tools for video](https://theagenticweekly.com/best/ai-video) ([md](https://theagenticweekly.com/best/ai-video.md)): AI video generation and editing tools, ranked by what each one is actually good for.
- [Best AI tools for writing](https://theagenticweekly.com/best/writing) ([md](https://theagenticweekly.com/best/writing.md)): AI writing and editing tools compared by use case: assistants, source-grounded notebooks and drafting tools, with a verdict on each.
- [Best AI tools for music](https://theagenticweekly.com/best/music) ([md](https://theagenticweekly.com/best/music.md)): AI music and audio tools compared by use case: song generators, developer APIs and open models, with a verdict on each.
- [Best AI tools for images](https://theagenticweekly.com/best/image-generation) ([md](https://theagenticweekly.com/best/image-generation.md)): AI image generation and editing tools compared by use case: web apps, open node-graph engines and multi-model suites.
- [Best AI tools for small businesses](https://theagenticweekly.com/best/small-business) ([md](https://theagenticweekly.com/best/small-business.md)): AI tools that help trades and local service businesses take back control of their sites, calls and reviews.
- [Best AI assistants](https://theagenticweekly.com/best/ai-assistants) ([md](https://theagenticweekly.com/best/ai-assistants.md)): AI chat assistants and workspace AI compared by price tier, free plan and where they work.
- [Best AI search and research tools](https://theagenticweekly.com/best/ai-search) ([md](https://theagenticweekly.com/best/ai-search.md)): AI search, answer and research tools compared by pricing, sources and API access.
- [Best tools for running LLMs locally](https://theagenticweekly.com/best/llm-platforms) ([md](https://theagenticweekly.com/best/llm-platforms.md)): Local LLM runtimes and desktop apps compared by license, platforms and release activity.
- [Best AI automation tools](https://theagenticweekly.com/best/no-code-automation) ([md](https://theagenticweekly.com/best/no-code-automation.md)): Workflow automation platforms with AI compared by free tier, price model and integrations.
- [Best MCP servers for AI agents](https://theagenticweekly.com/best/mcp-servers) ([md](https://theagenticweekly.com/best/mcp-servers.md)): Popular Model Context Protocol servers compared by maintainer, license and release activity.
- [Best AI meeting assistants](https://theagenticweekly.com/best/meeting-assistants) ([md](https://theagenticweekly.com/best/meeting-assistants.md)): AI notetakers compared by free plan, price per seat and how they capture meetings.
- [Best AI design and presentation tools](https://theagenticweekly.com/best/ai-design) ([md](https://theagenticweekly.com/best/ai-design.md)): AI design and slide tools compared by price model and trial or free plan.
- [Best AI voice and speech tools](https://theagenticweekly.com/best/voice-ai) ([md](https://theagenticweekly.com/best/voice-ai.md)): Speech-to-text, text-to-speech and voice agent platforms compared by price model, free credit and API focus.

## Latest news briefs (newest first, first-seen times in UTC)
- [All news briefs](https://theagenticweekly.com/news): fast, sourced write-ups with first-seen and source timestamps. JSON: https://theagenticweekly.com/latest.json (also https://theagenticweekly.com/api/latest). RSS: https://theagenticweekly.com/news/feed.xml. Sitemap: https://theagenticweekly.com/news-sitemap.xml.
- [AI model release news, updated Oct 26, 2026](https://theagenticweekly.com/news/models) ([md](https://theagenticweekly.com/news/models.md)): model releases from our dataset, newest first, each with the vendor page that states the date.
- [AI tool release news, updated Oct 26, 2026](https://theagenticweekly.com/news/tools) ([md](https://theagenticweekly.com/news/tools.md)): sourced briefs on new AI and agent tool releases, newest first, labelled Reported or Tested.
- [OpenAI GPT-6.1 Terra: a $1/$5 computer-use model, and what the launch post leaves out](https://theagenticweekly.com/news/openai-gpt-6-1-terra-computer-use) ([md](https://theagenticweekly.com/news/openai-gpt-6-1-terra-computer-use.md), Reported, first seen 2026-10-26 19:05 UTC): GPT-6.1 Terra (`gpt-6.1-terra`) is OpenAI's new fast model for computer use and visual reasoning: $1 input and $5 output per 1M tokens, 1.05M context, live in ChatGPT Work, Codex and the API on Oct 26. Its headline claims rest on charts we could not read as text, and we have not run it.
- [Superset is now Paradev: parallel coding-agent app ships desktop v2.0.0 and an $11.5M seed](https://theagenticweekly.com/news/superset-renamed-paradev-desktop-2-0-seed) ([md](https://theagenticweekly.com/news/superset-renamed-paradev-desktop-2-0-seed.md), Reported, first seen 2026-10-26 17:05 UTC): Superset, a desktop workspace for running Claude Code, Codex and other CLI coding agents in parallel, was renamed Paradev on Oct 26, 2026 with desktop release v2.0.0; the company says it raised an $11.5M seed led by Union Square Ventures, and that accounts, settings and the superset CLI command carry over unchanged.
- [Anthropic files S-1 for an IPO on Nasdaq under "ANT", reporting $16.3 billion revenue in six months](https://theagenticweekly.com/news/anthropic-s-1-ipo-filing-nasdaq-ant) ([md](https://theagenticweekly.com/news/anthropic-s-1-ipo-filing-nasdaq-ant.md), Reported, first seen 2026-10-26 15:15 UTC): Anthropic, PBC filed a Form S-1 with the SEC on October 26, 2026 for an initial public offering of Class A common stock, applying to list on the Nasdaq Global Select Market under the symbol ANT; the filing reports revenue of $16.3 billion for the six months ended June 30, 2026, and leaves the price range and share count blank.
- [ARTEX: an open-source multi-agent LLM system for autonomous penetration testing in isolated labs](https://theagenticweekly.com/news/artex-multi-agent-ai-penetration-testing) ([md](https://theagenticweekly.com/news/artex-multi-agent-ai-penetration-testing.md), Reported, first seen 2026-10-26 15:35 UTC): ARTEX is an AGPL-3.0 open-source system in which a planner agent and worker agents, driven by Anthropic or OpenAI models, carry out penetration tests in an isolated lab, sharing an asset graph and an exploration graph, with human-in-the-loop approval and full traffic recording; it ships as a single Go binary or a Docker Compose stack.
- [PaperPilot: an open-source Rust PDF toolkit that runs as an MCP server, CLI and in-browser WASM](https://theagenticweekly.com/news/paperpilot-rust-pdf-engine-mcp-wasm) ([md](https://theagenticweekly.com/news/paperpilot-rust-pdf-engine-mcp-wasm.md), Reported, first seen 2026-10-26 12:06 UTC): PaperPilot is an Apache 2.0, pure-Rust PDF toolkit whose single engine runs as an MCP server, a CLI, a local REST API, a desktop app and in the browser via WASM, so AI agents can merge, split, OCR and compress PDFs without uploading files; its latest GitHub release, v0.6.0, is marked as a pre-release.
- [Octopus SI OS: an open-source, self-evolving agentic OS with a Rust kernel, released as a research preview](https://theagenticweekly.com/news/octopus-si-os-self-evolving-agentic-os-research-preview) ([md](https://theagenticweekly.com/news/octopus-si-os-self-evolving-agentic-os-research-preview.md), Reported, first seen 2026-10-26 12:27 UTC): Octopus SI OS is a new open-source (MIT) agentic operating system for macOS 14+ with a roughly 45,000-line Rust kernel, signed in through ChatGPT with Codex CLI as its first interface; its own README calls it a research preview and says that for ordinary coding tasks it adds nothing over Codex CLI.
- [SolidCraft: open-source parametric CAD in pure Rust, with an MCP server so AI agents can model parts](https://theagenticweekly.com/news/solidcraft-open-source-rust-cad-mcp-server) ([md](https://theagenticweekly.com/news/solidcraft-open-source-rust-cad-mcp-server.md), Reported, first seen 2026-10-26 12:27 UTC): SolidCraft is an open-source parametric 3D CAD application written in Rust that runs on the desktop and in the browser, and its solidcraft-cli mcp command is a Model Context Protocol server that lets AI agents such as Claude Code build models; its README calls it early but usable for simple parts.
- [MCP reference servers v2.1.0 fixes eight vulnerabilities in filesystem, everything and fetch](https://theagenticweekly.com/news/mcp-servers-v2-1-0-security-fixes) ([md](https://theagenticweekly.com/news/mcp-servers-v2-1-0-security-fixes.md), Reported, first seen 2026-10-26 03:48 UTC): If you run the reference filesystem, everything or fetch MCP servers, update: v2.1.0 fixes eight vulnerabilities, and package managers will not offer the upgrade automatically to date-versioned installs.
- [Microsoft open-sources Agensh, a multi-agent harness its authors scaled to 1,024 agents](https://theagenticweekly.com/news/microsoft-agensh-multi-agent-harness-1024-agents) ([md](https://theagenticweekly.com/news/microsoft-agensh-multi-agent-harness-1024-agents.md), Reported, first seen 2026-10-26 03:47 UTC): Microsoft has open-sourced Agensh, a multi-agent harness with no central orchestrator that its authors report running with up to 1,024 agents; the benchmark numbers are the authors' own and we have not reproduced them.
- [Ollama v0.40.11 adds speech generation on macOS and the d3 decision models](https://theagenticweekly.com/news/ollama-v0-40-11-speech-d3-models) ([md](https://theagenticweekly.com/news/ollama-v0-40-11-speech-d3-models.md), Reported, first seen 2026-10-26 03:48 UTC): Ollama v0.40.11 can generate speech on macOS, through `ollama run` or an OpenAI-compatible audio endpoint, and adds the d3 family of decision models in 2B, 4B, 9B and 27B sizes.
- [Open WebUI v0.12.4 adds on-demand skill loading and says it contains unlisted security fixes](https://theagenticweekly.com/news/open-webui-v0-12-4-skills-compaction-security) ([md](https://theagenticweekly.com/news/open-webui-v0-12-4-skills-compaction-security.md), Reported, first seen 2026-10-26 03:48 UTC): Open WebUI v0.12.4 adds optional on-demand loading of skills and shows when chat context is compacted; its release notes say the release contains security fixes that are not itemised and recommend updating.

## Latest releases
- [Goodcall](https://theagenticweekly.com/tools/goodcall) ([md](https://theagenticweekly.com/tools/goodcall.md), Reported (not run by us)): A sensible first AI receptionist for a one-person shop; the per-customer pricing is simple, but test call quality yourself.
- [Jobber Receptionist](https://theagenticweekly.com/tools/jobber) ([md](https://theagenticweekly.com/tools/jobber.md), Reported (not run by us)): Best if you already use or plan to use Jobber for scheduling and invoicing; the receptionist works with your Jobber data.
- [LangGraph 1.2.17](https://theagenticweekly.com/tools/langgraph) ([md](https://theagenticweekly.com/tools/langgraph.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B))): A dependable foundation for stateful agents; this release is a routine fix, so only update if the RemoteGraph or recursion fixes affect you.
- [Claude Code v2.1.310](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)): 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 0.164.0](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)): 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.
- [CrewAI 1.15.30](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)): Reasonable if you like the crew-of-agents mental model; the memory and tool-loop fixes in this release are worth taking.
- [Gemini Notebook](https://theagenticweekly.com/tools/gemini-notebook) ([md](https://theagenticweekly.com/tools/gemini-notebook.md), Reported (not run by us)): 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 v1.56.0](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)): Pick goose if you want an open-source agent with real subagent controls; v1.56.0 is a solid, subagent-heavy update.
- [Luma](https://theagenticweekly.com/tools/luma) ([md](https://theagenticweekly.com/tools/luma.md), Reported (not run by us)): 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.
- [Replit](https://theagenticweekly.com/tools/replit) ([md](https://theagenticweekly.com/tools/replit.md), Reported (not run by us)): Strong pick if you want build, hosting and monitoring in one place; read the credit and overage rules first.
- [Google ADK v2.13.0](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)): Update with care: a big, useful release for Gemini users, but it includes a telemetry default change.
- [opencode v1.19.4](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)): 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)): A strong writing partner; try Claude Duet only if you are on Pro or Max and comfortable with a research-preview product.
- [Mastra @mastra/core@1.79.0](https://theagenticweekly.com/tools/mastra) ([md](https://theagenticweekly.com/tools/mastra.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B))): A strong TypeScript option if you are building agents in a Node stack; read the breaking-change note on sessions before upgrading.
- [ChatGPT](https://theagenticweekly.com/tools/chatgpt) ([md](https://theagenticweekly.com/tools/chatgpt.md), Reported (not run by us)): Still the broadest all-round assistant; the October updates matter most if you write documents, decks or work with audio.
- [FastMCP v4.1.3](https://theagenticweekly.com/tools/fastmcp) ([md](https://theagenticweekly.com/tools/fastmcp.md), Tested (smoke test, 2026-10-25, no language model involved)): If you run FastMCP servers, upgrade and read the security notices; the OAuth issuer step is not automatic.
- [Gemini CLI v0.65.0](https://theagenticweekly.com/tools/gemini-cli) ([md](https://theagenticweekly.com/tools/gemini-cli.md), Reported (not run by us)): 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.
- [n8n 2.45](https://theagenticweekly.com/tools/n8n) ([md](https://theagenticweekly.com/tools/n8n.md), Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B))): 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)): 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)): Good for UI-heavy web work, especially if you deploy on Vercel; the October changes are about teamwork and polish.
- [ComfyUI v0.42.1](https://theagenticweekly.com/tools/comfyui) ([md](https://theagenticweekly.com/tools/comfyui.md), Tested (smoke test, 2026-10-26, no LLM involved)): The tool to learn if you want maximum control over open models on your own GPU; it has a learning curve.
- [Cline SDK v0.0.95](https://theagenticweekly.com/tools/cline) ([md](https://theagenticweekly.com/tools/cline.md), Reported (not run by us)): 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)): 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.
- [GitHub Copilot](https://theagenticweekly.com/tools/github-copilot) ([md](https://theagenticweekly.com/tools/github-copilot.md), Reported (not run by us)): A sensible default if your team already lives on GitHub; check which plan you need for new models.
- [Kling AI 4.0](https://theagenticweekly.com/tools/kling) ([md](https://theagenticweekly.com/tools/kling.md), Reported (not run by us)): Worth testing for action and camera-heavy shots; our information is secondhand from Luma plus the Kling homepage.
- [OpenAI Agents SDK v0.24.0](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)): 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)): 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)): A friendly way for non-developers to get a working web app and a first-customers plan; check credit costs before you commit.
- [Midjourney](https://theagenticweekly.com/tools/midjourney) ([md](https://theagenticweekly.com/tools/midjourney.md), Reported (not run by us)): Use the thinking rerun if prompt-following misses are your pain; be careful with privacy when sharing folders.
- [Suno v6](https://theagenticweekly.com/tools/suno) ([md](https://theagenticweekly.com/tools/suno.md), Reported (not run by us)): The most complete song-making tool we track; the v6 editing features are the draw. Rights and licensing questions are yours to check.
- [ACE-Step v1.5](https://theagenticweekly.com/tools/ace-step) ([md](https://theagenticweekly.com/tools/ace-step.md), Reported (not run by us)): The pick if you want open weights and local control; expect a manual setup and no recent updates.

## Everything else (complete lists are in llms-full.txt)
- [Full content for LLMs](https://theagenticweekly.com/llms-full.txt): every tool entry, comparison, alternatives page, explainer, guide, test and study with its URL and markdown twin. This file is the short index.
- Tool directory: [All tools](https://theagenticweekly.com/tools) ([md](https://theagenticweekly.com/tools.md), [JSON](https://theagenticweekly.com/tools.json)), 108 evergreen entries plus the latest releases above. Every tool page also exists as markdown by appending .md.
- Comparisons: [All comparisons](https://theagenticweekly.com/compare) (59 pages, each also as .md).
- [GPT-6.1 Terra vs Claude Opus 5.5: price per task, context and when Opus still fits](https://theagenticweekly.com/compare/gpt-6-1-terra-vs-claude-opus-5-5) ([md](https://theagenticweekly.com/compare/gpt-6-1-terra-vs-claude-opus-5-5.md)): GPT-6.1 Terra lists at one quarter of Claude Opus 5.5's per-token price ($1/$5 vs $4/$20). Specs, access and vendor claims, read 2026-10-26.
- [GPT-6.1 Terra vs GPT-6.1 Sol: price, specs and which to pick](https://theagenticweekly.com/compare/gpt-6-1-terra-vs-gpt-6-1-sol) ([md](https://theagenticweekly.com/compare/gpt-6-1-terra-vs-gpt-6-1-sol.md)): GPT-6.1 Terra costs half of Sol per token ($1/$5 vs $2/$10). Specs, Codex and Copilot access, and when to pick each, from vendor pages read 2026-10-26.
- Alternatives: [Alternatives to each tool](https://theagenticweekly.com/alternatives) (81 pages, each also as .md).
- Explainers: [What is: explainers](https://theagenticweekly.com/what-is) (41 pages, each also as .md).

## Guides
- [Guides: set up and use AI agent tools](https://theagenticweekly.com/guides) ([md](https://theagenticweekly.com/guides.md)): every guide says which steps we ran and which come from vendor docs.
- [How to add an MCP server to Claude Code](https://theagenticweekly.com/guides/add-mcp-server-to-claude-code) ([md](https://theagenticweekly.com/guides/add-mcp-server-to-claude-code.md), Reported (not run by us): from the Claude Code docs): The claude mcp add commands for remote and local MCP servers, scopes and status checks, from Claude Code's docs. Reported; we have not run them. Last verified 2026-10-26.
- [Best model for OpenCode, Cline and Claude Code: options by budget](https://theagenticweekly.com/guides/best-model-for-opencode-cline-claude-code) ([md](https://theagenticweekly.com/guides/best-model-for-opencode-cline-claude-code.md), Reported (not run by us): prices and setup from vendor docs; our tool tests do not measure model quality): Model options for OpenCode, Cline and Claude Code by budget, with list prices and setup steps from vendor docs. No quality ranking; not benchmarked by us. Last verified 2026-10-26.
- [How to build an MCP server with FastMCP](https://theagenticweekly.com/guides/build-an-mcp-server-with-fastmcp) ([md](https://theagenticweekly.com/guides/build-an-mcp-server-with-fastmcp.md), Tested (smoke test, 2026-10-25, no LLM involved), stdio only): Install FastMCP and write a three-tool Python MCP server. Tested for the stdio run in our log; HTTP transport and client setup are from the FastMCP docs. Last verified 2026-10-26.
- [ChatGPT Work vs ChatGPT Chat vs Codex: what each is for](https://theagenticweekly.com/guides/chatgpt-work-vs-chatgpt-chat) ([md](https://theagenticweekly.com/guides/chatgpt-work-vs-chatgpt-chat.md), Reported (not run by us): from OpenAI's documentation; we have not used ChatGPT Work): What ChatGPT Work is and how it differs from Chat and Codex, reported from OpenAI's docs. We have not used it. Last verified 2026-10-26.
- [Is Claude Opus 5.5 free? Which plans include it](https://theagenticweekly.com/guides/claude-opus-5-5-free-or-paid) ([md](https://theagenticweekly.com/guides/claude-opus-5-5-free-or-paid.md), Reported (not run by us): from Anthropic's pricing page; we did not test access with an account): Is Claude Opus 5.5 free? No: not on the Free plan; included on Pro, Max, Team and Enterprise, or by API. Reported from Anthropic's pricing page. Last verified 2026-10-26.
- [Figma MCP server: how to enable it](https://theagenticweekly.com/guides/figma-mcp-server) ([md](https://theagenticweekly.com/guides/figma-mcp-server.md), Reported (not run by us): from Figma's Help Center and developer docs): Who can use Figma's MCP server, remote versus desktop setup and the documented Claude Code commands. Reported from Figma's docs; we have not run it. Last verified 2026-10-26.
- [Gemini 4 Argon API pricing: $2 and $10 per million tokens until Nov 30, then $4 and $20](https://theagenticweekly.com/guides/gemini-4-argon-api-pricing) ([md](https://theagenticweekly.com/guides/gemini-4-argon-api-pricing.md), Reported (not run by us): from Google's pricing page; we have not called the API): Gemini 4 Argon API price: $2/$10 per million tokens through Nov 30, 2026, then $4/$20. Reported from Google's pricing page; not run by us. Last verified 2026-10-26.
- [Git MCP server: how to set it up and what it can do](https://theagenticweekly.com/guides/git-mcp-server) ([md](https://theagenticweekly.com/guides/git-mcp-server.md), Tested (smoke test, 2026-10-25, no LLM involved)): Install the reference Git MCP server with uv or pip. Tested for the logged no-model smoke test (start, 12 tools, git_status); client setup is from the README. Last verified 2026-10-26.
- [GitHub MCP server: how to set it up](https://theagenticweekly.com/guides/github-mcp-server) ([md](https://theagenticweekly.com/guides/github-mcp-server.md), Reported (not run by us): from the README and Claude Code docs): Set up GitHub's official MCP server, remote or local, with a token or OAuth. Reported from the README and Claude Code docs; we have not run it. Last verified 2026-10-26.
- [Which coding agents can use GPT-6.1 Terra?](https://theagenticweekly.com/guides/gpt-6-1-terra-in-coding-agents) ([md](https://theagenticweekly.com/guides/gpt-6-1-terra-in-coding-agents.md), Reported (not run by us): from vendor docs and changelogs): Where GPT-6.1 Terra works today: Copilot, Codex and ChatGPT Work confirmed; Cursor, Claude Code, Cline and OpenCode not confirmed. Reported from vendor docs. Last verified 2026-10-26.
- [Is Kimi K3.1 Pro open-weight? Status of the Nov 4 promise](https://theagenticweekly.com/guides/kimi-k3-1-pro-open-weights) ([md](https://theagenticweekly.com/guides/kimi-k3-1-pro-open-weights.md), Reported (not run by us): from Moonshot's blog and a Hugging Face listing check): Status of Kimi K3.1 Pro open weights: promised by Nov 4, 2026, not on Hugging Face as of Oct 26. Reported; not run by us. Last verified 2026-10-26.
- [Playwright MCP server: setup, tools and what we measured](https://theagenticweekly.com/guides/playwright-mcp-server) ([md](https://theagenticweekly.com/guides/playwright-mcp-server.md), Tested (smoke test, 2026-10-25, no LLM involved)): Install and run Microsoft's Playwright MCP server. Tested for the logged no-model smoke test (start, 25 tools, navigate); client setup is from the README. Last verified 2026-10-26.
- [How to run Claude Code with a local model](https://theagenticweekly.com/guides/run-claude-code-with-a-local-model) ([md](https://theagenticweekly.com/guides/run-claude-code-with-a-local-model.md), Tested (partial, 2026-10-25): one headless edit, small local model, not Claude models): Point Claude Code at a local Ollama model. Tested in part: a 3B model made one edit on an exact prompt and failed on a vague one; the settings come from Ollama's docs. Last verified 2026-10-26.
- [Which Claude model should you use? Haiku 5.5, Sonnet 5.5, Opus 5.5 or Fable 5.1](https://theagenticweekly.com/guides/which-claude-model-should-i-use) ([md](https://theagenticweekly.com/guides/which-claude-model-should-i-use.md), Reported (not run by us): Anthropic's docs plus our editorial judgement): Pick between Claude Haiku 5.5, Sonnet 5.5, Opus 5.5 and Fable 5.1 by task and budget, from Anthropic's docs and prices. Reported; not run by us. Last verified 2026-10-26.

## Head-to-head model tests (we ran these; indicative, not benchmarks)
- [Writing test](https://theagenticweekly.com/tests/writing) ([md](https://theagenticweekly.com/tests/writing.md)): the same writing prompts through small open models run locally, rated blind by a separate model; [leaderboard](https://theagenticweekly.com/tests/writing-leaderboard)
- [Instruction-following test](https://theagenticweekly.com/tests/instruction-following) ([md](https://theagenticweekly.com/tests/instruction-following.md)): code-checked rules, pass rates with intervals, speed
- Raw data: [results.json](https://theagenticweekly.com/raw/writing/results.json), [ifeval-results.json](https://theagenticweekly.com/raw/writing/ifeval-results.json), [prompts.json](https://theagenticweekly.com/raw/writing/prompts.json), [generations.jsonl](https://theagenticweekly.com/raw/writing/generations.jsonl)

## Original tests and research (we ran these)
- [Tests and research hub](https://theagenticweekly.com/tests) (79 pages; each is listed with its description in llms-full.txt).

## About this site
- [About Agentic Weekly](https://theagenticweekly.com/about) ([md](https://theagenticweekly.com/about.md)): Agentic Weekly is an independent weekly radar of AI and agent tool releases with verdicts, operated independently from Texas, US.
- [Changelog: site and data changes](https://theagenticweekly.com/changelog) ([md](https://theagenticweekly.com/changelog.md)): A dated log of changes to Agentic Weekly's site, evidence labels, rankings basis and data, so you can see what changed and why.
- [How to cite Agentic Weekly](https://theagenticweekly.com/cite) ([md](https://theagenticweekly.com/cite.md)): Copy-ready citations for Agentic Weekly pages and data in plain text, APA-style, MLA-style, BibTeX and HTML, plus the rules for quoting a verdict or a model fact.
- [Contact Agentic Weekly](https://theagenticweekly.com/contact) ([md](https://theagenticweekly.com/contact.md)): How to contact Agentic Weekly: one email address for corrections, questions and press, plus forms for submitting a tool or asking about a featured listing.
- [How is Agentic Weekly different from There's An AI For That, Futurepedia and TLDR AI?](https://theagenticweekly.com/how-we-differ) ([md](https://theagenticweekly.com/how-we-differ.md)): How Agentic Weekly differs from There's An AI For That, Futurepedia and TLDR AI, using only what each site says about itself and what we do, dated 2026-10-25.
- [Methodology: how Agentic Weekly picks and tests AI tools](https://theagenticweekly.com/methodology) ([md](https://theagenticweekly.com/methodology.md)): How Agentic Weekly chooses tools, what Reported and Tested mean, the scope of our tests, how ranks and prices are handled, and how corrections work.
- [AI model release calendar: confirmed dates and labeled rumors](https://theagenticweekly.com/models/upcoming) ([md](https://theagenticweekly.com/models/upcoming.md)): Upcoming AI model dates from vendor pages only: Kimi K3.1 Pro weights by Nov 4, Ignite Nov 17-20, Gemini 4 Argon price change Dec 1. Rumors labeled.
- [Research: original measurements from our own test rig](https://theagenticweekly.com/research) ([md](https://theagenticweekly.com/research.md)): 5 data studies built from our own test runs: frameworks, MCP servers, local models, voice, and install traps. Each has a data table and states what was not measured.
- [Test logs: what we ran and what happened](https://theagenticweekly.com/tests) ([md](https://theagenticweekly.com/tests.md)): 57 dated test logs of AI agents, frameworks, MCP servers and local AI tools, with exact commands, versions and raw output.
- [New AI and agent tool releases this week](https://theagenticweekly.com/this-week) ([md](https://theagenticweekly.com/this-week.md)): 18 AI tool and model releases from Oct 21, 2026 to Oct 27, 2026, each with a one-line verdict or sourced facts, an evidence label (Reported or Tested) and a setup guide.
- [Alternatives to each tool](https://theagenticweekly.com/alternatives): what to use instead, with a verdict for every option
- [Archive: AI tool release news by week and month](https://theagenticweekly.com/archive): [week of Oct 19, 2026](https://theagenticweekly.com/archive/week/2026-10-19), [week of Oct 12, 2026](https://theagenticweekly.com/archive/week/2026-10-12), [2026-10](https://theagenticweekly.com/archive/month/2026-10)
- Hubs: [All tools](https://theagenticweekly.com/tools) ([md](https://theagenticweekly.com/tools.md)), [Best AI tool by use case](https://theagenticweekly.com/best) ([md](https://theagenticweekly.com/best.md)), [What is: explainers](https://theagenticweekly.com/what-is) ([md](https://theagenticweekly.com/what-is.md)), [Comparisons](https://theagenticweekly.com/compare) ([md](https://theagenticweekly.com/compare.md)), [News](https://theagenticweekly.com/news) ([md](https://theagenticweekly.com/news.md)), [Archive](https://theagenticweekly.com/archive) ([md](https://theagenticweekly.com/archive.md)), [Alternatives](https://theagenticweekly.com/alternatives) ([md](https://theagenticweekly.com/alternatives.md)), [Privacy](https://theagenticweekly.com/privacy), [Terms](https://theagenticweekly.com/terms), [Cheat sheet](https://theagenticweekly.com/cheat-sheet), [Sponsor](https://theagenticweekly.com/sponsor), [Submit a tool](https://theagenticweekly.com/submit)
- Every comparison, alternatives, explainer and guide page also exists as plain markdown by appending .md to its URL.

## Optional
- Contact: hello@theagenticweekly.com
- [Editorial policy](https://theagenticweekly.com/editorial-policy): how verdicts, paid placements and affiliate links work
- [The Weekly Verdict newsletter](https://theagenticweekly.com/newsletter): free weekly email, every item labeled Reported or Tested; [read a full sample issue](https://theagenticweekly.com/newsletter/issue-1) and the [issue archive](https://theagenticweekly.com/newsletter/archive)
- [Full content for LLMs](https://theagenticweekly.com/llms-full.txt)
- [RSS](https://theagenticweekly.com/feed.xml), [News RSS](https://theagenticweekly.com/news/feed.xml), [Atom](https://theagenticweekly.com/atom.xml), [JSON Feed](https://theagenticweekly.com/feed.json), [Latest news JSON](https://theagenticweekly.com/latest.json)
- [Sitemap](https://theagenticweekly.com/sitemap.xml), [News sitemap](https://theagenticweekly.com/news-sitemap.xml)