AI agent tools launched Oct 19 – Oct 25, 2026, page 3
378 tools added Oct 19 – Oct 25, 2026. Page 3 of 4. Ranked by that week’s votes, then by the date added. Top: luvus, ktx, iArt.
Quick answer: The newest additions on this page are luvus, ktx, iArt. This page covers tools launched Oct 19 – Oct 25, 2026. Vote counts start at zero and come from the server, one vote per visitor per day. Ties stay in the order the tools were added, newest first.
New toolsSubmit freeFast-Track ($15)
- 201
luvus
Mission control for AI coding agents: run, watch, resume and orchestrate Claude Code, Codex, Copilot, opencode and others from one terminal with a live view of each agent.
More+0 todayView - 202
ktx
An open-source context layer for data and analytics agents that gives Claude Code, Codex and other agents a self-improving map of your warehouse, metrics and business definitions.
More+0 todayView - 203
iArt
iArt is an AI motion graphics agent that turns a text prompt, or uploaded images, PDFs, slide decks, audio or a web link, into animated scenes. It writes real animation code scene by scene (layout, typography, timing, transitions), so text stays exactly spelled and you can refine the result by chatting ("make the title two seconds shorter"). It handles explainers, logo animations, kinetic typography, animated charts, lower thirds and audio-synced captions, adds AI voiceover or a cloned voice, and exports MP4 (1080p on Pro, 4K on Ultra) or transparent WebM overlays.
More+0 todayView - 204
hax
A minimalist terminal coding agent shipped as a single native C binary using a few MB of RAM, with first-class local models plus OpenAI, Anthropic and OpenRouter support.
More+0 todayView - 205
explainroo
Lets your AI coding agent make narrated explainer videos: it writes the script, builds the visuals and renders the voice and video on your own computer, with no API key needed. Free and open source.
More+0 todayView - 206
eve
Vercel's open-source agent framework, pitched as Next.js for agents: a file-system-based way to define an agent's tools, prompts and workflows and run it in production.
More+0 todayView - 207
draw.io MCP
The official draw.io MCP server, so Claude, ChatGPT, Cursor and other assistants can create and edit flowcharts, architecture diagrams and other draw.io diagrams right in the chat. Free and needs no sign-in.
More+0 todayView - 208
ai-memory
Fabio Akita's open-source long-term memory layer for coding agents: one Rust binary that keeps plain-markdown project memory and typed handoffs shared across 20+ harnesses such as Claude Code, Codex, Cursor and Gemini CLI, so you can switch agents, machines or teammates without re-explaining the project.
More+0 todayView - 209
agentOS
A lightweight operating system for agents from Rivet that runs coding agents and their tools inside fast WebAssembly sandboxes with a file system, processes and networking, so you can spin up thousands cheaply.
More+0 todayView - 210
agent-qa (Vostride)
A self-improving AI QA agent with persistent memory that tests web, Android and iOS apps from plain-English test steps, for developers and coding agents.
More+0 todayView - 211
Zero
An open-source terminal coding agent written in Go that works with 30+ model providers, supports MCP, skills and subagents, and keeps all sessions on your own disk.
More+0 todayView - 212
Zapia
A personal AI assistant on WhatsApp, iPhone, Android and the web that books, reminds, searches, compares prices and handles everyday errands for you. Free plan plus Pro and Ultra.
More+0 todayView - 213
ZCode
ZCode is Z.ai's open-source AI coding workspace and official harness for GLM-5.3, with a desktop app, web interface and terminal agent that run multiple agents on long goals, plus control from WeChat, Feishu or Telegram.
More+0 todayView - 214
Xyne
Juspay's open-source enterprise AI platform for building apps and agents on top of your company's own context, model-agnostic and self-hostable.
More+0 todayView - 215
Wren x402 Doctor
Wren x402 Doctor helps sellers of x402 pay-per-call endpoints, the payment standard AI agents use to pay for APIs in USDC, get listed in the Coinbase CDP Bazaar and stay listed. A free lint checks a 402 response against the x402 v2 spec and the Bazaar listing rules (networks, amounts, payTo checksum, description length, injection-like text, schema and metadata), plus a seller's OpenAPI and x402 discovery documents. Paid endpoints include a Bazaar health check ($0.10) returning every listing for a wallet with 30-day calls, unique payers and estimated delisting dates; a market check (GET /market, $0.02) returning up to 20 comparable live listings with price quartiles; and GET /trust ($0.01), which traces who funds the wallets that pay an x402 seller using a weekly Base funding trace (splitting calls across seller-funded wallets, shared funders, multi-seller callers and independent wallets).
More+0 todayView - 216
What Should My Bot Do
What Should My Bot Do is a free AI agent planner for small businesses: answer 5 quick questions and get a first agent to set up, 3 next jobs to automate and copy-ready templates for Grok Bot, ChatGPT, Claude and n8n. No signup.
More+0 todayView - 217
Weave Router
An open-source LLM router for Claude Code, Codex and other coding agents that sends each request to the cheapest model that still meets your quality bar, cutting model spend.
More+0 todayView - 218
Wabi
An AI assistant you use together with friends and family: plan a trip, book a stay or turn an inside joke into a quick game or mini-app, all in one shared space. On iPhone, Android and Mac.
More+0 todayView - 219
VisorBot
An Android automation app where you type or say a task and VisorBot taps, swipes and types through your apps to do it, with reusable recipes. Free plan; Plus from $4.99 a month.
More+0 todayView - 220
VirtualBudz BudBot
VirtualBudz BudBot is an AI budtender for cannabis dispensary websites. It answers shoppers' product questions, recommends items from the live menu and builds carts around the clock, so customers get help even when staff are busy.
More+0 todayView - 221
Vicoa
Vicoa is an agent-native IDE for running Claude Code, Codex, Gemini and 40+ other coding agents in parallel, each on its own git worktree, from desktop, web or phone, with notifications when an agent needs you.
More+0 todayView - 222
Understand-Anything
Turns any codebase, knowledge base or docs folder into an interactive knowledge graph you can explore and question, working inside Claude Code, Codex, Cursor, Copilot and Gemini CLI.
More+0 todayView - 223
TypeSafe Jev
Jev is TypeSafe's System One decision model, built for the small decisions inside software and agents. You send a state and typed questions (choice, score and more) and get typed answers with probabilities back instead of free-form text, so code can branch on them directly to route, classify, score or rank options. Agents can use it to settle narrow calls cheaply and save the larger LLM for open-ended work. Available through TypeSafe's API, Python and JavaScript SDKs, an agent skill, and OpenRouter.
More+0 todayView - 224
Tracely
Tracely is open-source, trace-native CI/CD for AI agents: it grades every production trace with evaluators, clusters failures into issues, freezes bad runs into replayable test cases and blocks pull requests that would reintroduce them.
More+0 todayView - 225
Toad
A terminal front end from Will McGugan (creator of Rich and Textual) for running AI coding agents like Claude Code, Gemini CLI and Codex through one polished, fast interface.
More+0 todayView - 226
ThinkWatch Lite
A local gateway that sits between your coding agents and model providers, letting you switch upstreams, redact secrets before they leave your machine, block dangerous tool calls and see the cost of each request.
More+0 todayView - 227
ThinkRail
JetBrains' lightweight agentic IDE that pairs you with the pi coding agent, with isolated git-worktree workspaces, editor tabs, terminals and diffs.
More+0 todayView - 228
The Commons (Dead Brands Collab Hub)
The Commons is an open discussion hub for AI agents and bots, run as a remote MCP server (Streamable HTTP) by Dead Brands. Agents can read rooms, threads, search and bot profiles anonymously, and post, reply, upvote and send presence heartbeats with a free, instant hub key they claim themselves through the hub_register tool. Rooms include introductions, lobby, build-log, help-desk and meta, with public moderation, newcomer rate limits and an AI judge that holds prompt-injection bait aimed at visiting bots.
More+0 todayView - 229
Tel-Agent
A self-hosted AI agent that answers phone calls and handles support on WhatsApp, Telegram, web chat and email with your own models and keys.
More+0 todayView - 230
Sno Station
Sno Station turns the coding agents you already use (Claude Code, Codex, Cursor, Hermes, OpenClaw) into one squad on your machine with shared memory, and its Self Learning reviews their sessions and proposes skill-file fixes you approve.
More+0 todayView - 231
Shipyard
Shipyard, from coss.com, runs Claude Code, Codex and other coding agents on your own dev machines, each task in its own worktree with its own terminals, dev server and live page previews, so agents keep working when your laptop sleeps.
More+0 todayView - 232
Sentio
Sentio, from Truespar, is a self-hosted email inbox API for AI agents: a Rust SMTP server that gives each agent a real address, delivers inbound mail as authenticated webhooks and lets agents reply in-thread over REST, with multi-tenant isolation.
More+0 todayView - 233
Second Brain
A free, open-source shared memory that runs in your own Cloudflare account, so Claude, ChatGPT, Cursor and other MCP clients can recall the same projects, preferences and decisions.
More+0 todayView - 234
Sanity MCP
Sanity's official remote MCP server that lets assistants query, create and update content, schemas and releases in a Sanity project using plain language.
More+0 todayView - 235
Sage
Sage is an open-source (MIT) RSI agent harness, where RSI stands for Recursive Self-Improvement: it improves agents using feedback from their tasks. Starting from a goal or a curated usage history, it runs the agent, has a separate evaluator grade the results, tunes the agent and keeps every version with its evidence, so you decide which one to adopt. It comes as a Desktop app, a multi-user Server with Agent Studio, and the SAgents Python runtime, with support for Skills, MCP, multi-agent setups and sandboxed runs with approvals.
More+0 todayView - 236
SEAL
SEAL is an MCP server (npx sealnet-mcp) that lets AI agents send and request files and secrets with end-to-end encryption. After pairing, the default delivery route sends the file to the user's SEAL inbox and returns a handle to the model. Also has a browser app, CLI and SDK; free up to 1 GB per seal.
More+0 todayView - 237
RoverLead
RoverLead is an AI SDR for LinkedIn. Its signal agents watch engagement around your niche, competitors and the experts your buyers follow to find in-market leads that match your ideal customer profile, then write a personalised opener from the exact signal and run outreach and follow-ups at LinkedIn-safe pacing. A shared inbox sorts replies by intent and drafts answers in your voice, and nothing goes out until you approve it. Connects to your CRM and to Claude or ChatGPT through MCP.
More+0 todayView - 238
Robylon
Robylon builds AI customer-support agents that resolve tickets across email, chat, voice and WhatsApp, connect to helpdesks like Zendesk, Freshdesk and Intercom, take actions such as refunds and order updates, and hand hard cases to a person.
More+0 todayView - 239
Repo Prompt
The community edition of Repo Prompt, a native macOS context-engineering app that packs the right files into prompts for AI coding work and exposes the same tools to agents via MCP.
More+0 todayView - 240
Reason Network
A small peer-to-peer daemon that links coding-agent sessions across your team's computers, so Claude Code, Codex, Cursor, Gemini CLI and other agents can see who is working on what and message each other directly, with no server.
More+0 todayView - 241
Puter AI Builder
Puter AI Builder turns a plain-language description into a working app or website that can be published to a real URL, with no code; it is an open-source alternative to Lovable, Replit and v0 from the team behind Puter.
More+0 todayView - 242
Phase
An open-source secrets manager that syncs API keys and environment variables to apps, CI and agents with end-to-end encryption and access control. Free tier, Pro from $10 per user a month, or self-host.
More+0 todayView - 243
Paddle MCP
Paddle's official remote MCP server, so assistants can look up and manage products, prices, customers, subscriptions and transactions in your Paddle billing account.
More+0 todayView - 244
Openlayer MCP
Openlayer's MCP server, letting coding agents pull evaluation results, failing tests and monitoring data from Openlayer so they can debug and improve AI systems from the IDE.
More+0 todayView - 245
OpenOSINT
An open-source OSINT engine with about 20 passive investigation tools usable from a CLI, a web UI or an MCP server for AI assistants, with hosted monitoring and due-diligence plans.
More+0 todayView - 246
OpenMeld
An open-source collaboration system where people, cloud agents and coding agents such as Codex, Claude Code and Cursor share context and pick up each other's work.
More+0 todayView - 247
OpenLore
A self-hosted knowledge repository for AI agents written in Go, where agents and teams share docs, notes and findings over SSH and MCP with scoped access.
More+0 todayView - 248
OpenGCUA
Open stack from Tongyi Lab's MAI-UI team for generalist computer-use agents that combine GUI clicks, accessibility trees, terminal commands, APIs and code: an OSWorld harness, a macOS real-device harness, a cross-device SDK and published task runs of eight frontier models.
More+0 todayView - 249
OpenCity Record
OpenCity Record makes US city council and planning meetings searchable in plain language: what was decided, who voted and what is coming up, drawn from meeting transcripts, agendas and ordinances across hundreds of cities. Connect it to Claude, ChatGPT or Cursor through its remote MCP server and ask questions about your local government, with every answer citing the meeting it came from.
More+0 todayView - 250
OpenChatCut
A local-first AI video editor with a multi-track timeline that you drive by chatting with an agent; the AGPL edition is free, and a Pro desktop app adds transcription-based editing.
More+0 todayView - 251
Open Executive
A self-hostable virtual executive: one executive persona backed by a team of specialist agents that handle planning, research, communication and follow-ups for a founder or manager.
More+0 todayView - 252
Onlook
An open-source visual editor for React and Tailwind apps where you design on a canvas and an AI agent writes the code. Edit layouts like in Figma, then export clean code to your own repo.
More+0 todayView - 253
Ongrid
An ops agent that learns your infrastructure, finds the root cause of incidents and helps fix them from the chat apps your team already uses.
More+0 todayView - 254
OneUptime MCP
OneUptime's official MCP server, giving agents access to monitors, incidents, on-call and status pages in this open-source observability platform. Free plan, paid plans from $22 per user, or self-host.
More+0 todayView - 255
Muxin
Muxin is a free, open-source desktop app that puts all your Macs, Linux, Windows and cloud machines in one window, so you can run Claude Code, Codex and other agent CLIs on any of them, see their screens and logs, and take changes to a pull request.
More+0 todayView - 256
Monobot.AI
Monobot.AI is a no-code platform for building voice and chat AI agents that handle customer support, bookings, reservations and routine business calls, with a workspace for managing agents and integrations with CRMs and other tools.
More+0 todayView - 257
Moltgate
Moltgate helps AI agent builders and automation operators turn agent ideas into paid offers. You package an agent workflow or automation as a fixed-price task with clear scope, deliverable and timing, publish it on a public profile and directory, and buyers pay by card to submit requests. Analytics show which offers sell, and paid requests can be routed to Claude Code, Codex, n8n, Zapier or your own agent through a REST API (polling) or webhooks, so repeat work can be automated.
More+0 todayView - 258
Microsoft Copilot Studio
Microsoft's low-code platform for building, testing and publishing AI agents that connect to business data, Microsoft 365, Power Platform connectors and MCP servers, then deploy to Teams, websites and other channels.
More+0 todayView - 259
Memori
An LLM-, database- and framework-agnostic memory layer that turns what agents do and say into structured, persistent state they can recall in later runs. Open source to self-host, or use Memori Cloud with an API key.
More+0 todayView - 260
Memmy
A local-first personal AI agent with a self-evolving long-term memory that its desktop app, CLI and your other AI agents can all share.
More+0 todayView - 261
Mapbox MCP
Mapbox's official MCP server that gives agents geocoding, directions, travel-time isochrones, points of interest and static map images through Mapbox APIs.
More+0 todayView - 262
ManimGX
ManimGX, from Academa, is an open-source animation engine for AI agents that renders math and 3D explainer videos from Manim CE's Python API on a Rust and wgpu GPU core, many times faster than Manim CE, and can also run in the browser.
More+0 todayView - 263
Loppee
Loppee is a US directory of local businesses that marks which ones it has verified (registration, an owner contact route and any required license). Its free, no-sign-in remote MCP server (loppee.com/mcp/discovery) and REST API let Claude, ChatGPT, Cursor and other assistants look up a business, read its Trust Card and identity-verified reviews, and compare options; owners can also manage their listing through their own AI agent.
More+0 todayView - 264
Lody
A team workspace for running AI coding agents in parallel in isolated Git worktrees, with live diff review, GitHub integration and access from phone or desktop.
More+0 todayView - 265
LiteLLM Agent Platform
A control plane from the LiteLLM team that gives one API and gateway for calling many agents, such as OpenCode, Claude Managed Agents, Cursor Agents and Deep Agents.
More+0 todayView - 266
Libretto
An open-source CLI, debugging agents and browser tools for building and maintaining reliable web integrations, helping coding agents inspect real pages and write automations that keep working.
More+0 todayView - 267
LaunchDarkly MCP
LaunchDarkly's official MCP server, so agents can create, update and clean up feature flags, AI configs and targeting rules from the IDE or chat.
More+0 todayView - 268
LCU
Brings the computer-use runtime from the ChatGPT desktop app to Claude Code, Codex CLI and Pi, so any agent harness can see and control your desktop without a Codex sign-in.
More+0 todayView - 269
KiwiFS
A markdown filesystem for agents and teams: searchable, structured and versioned knowledge in a single binary that agents can read and write.
More+0 todayView - 270
Kernel
Cloud browsers for AI agents: launch headless or live-view Chrome sessions in milliseconds with stealth mode, persistent profiles and replays, controlled through an API, CLI or MCP server. Free tier plus usage pricing.
More+0 todayView - 271
Hypit
An open-source agent workflow that takes a viral short video and rebuilds it as an editable template, letting you swap the presenter, script, voice and B-roll to produce many new variants with your own API keys.
More+0 todayView - 272
Hy-Memory
Tencent Hunyuan's open-source memory system for agents that extracts, organizes and recalls long-term memories across sessions, with a memory hub and plugins for popular agent tools.
More+0 todayView - 273
HiRoute
HiRoute, from the Higress team, is an open-source local model router for long-running agents like Codex and Claude Code: it hands routine stages to cheaper models, saves your strongest model for hard steps and keeps a record of each decision.
More+0 todayView - 274
Handsy
Lets an AI model use a real iPhone through a $7 ESP32 board that acts as a Bluetooth keyboard and mouse, tapping and typing through apps with no jailbreak and no computer attached.
More+0 todayView - 275
Halofy
Halofy is an access and governance layer for a team's AI agents, giving every agent organizational context through one identity and policy model with provenance and audit, alongside a desktop AI workstation that turns power users' agent practices into shared policies.
More+0 todayView - 276
HOL Guard
HOL Guard is a free, open-source (Apache-2.0), local-first security layer for AI coding agents such as Claude Code, Codex, Cursor and GitHub Copilot CLI. On supported integrations it checks risky shell commands, reads of secret-bearing files, package installs and new or changed MCP tools before they run, lets you allow, ask or block each action, and keeps a local record for review. It installs with pipx (hol-guard) and works offline; optional Guard Cloud adds synced approvals, team policy and dashboards.
More+0 todayView - 277
Growth Lab
An open-source growth agent that learns your product, gathers data, researches the market, runs growth experiments and learns from the results to pick the next move.
More+0 todayView - 278
Grok Bot Jev Router
Grok Bot Jev Router is an open-source Python reference router that puts TypeSafe Jev in front of Grok Bot as a cheap decision layer. Before expensive research, browser, retry or subagent work, Jev classifies the request and returns an explicit action such as reuse a cached result, stop a failing retry, cap research, run a deterministic step, or ask a human. It starts in shadow mode that only logs decisions, has an active mode for a Grok Bot skill that honors them, and includes a kill switch. It never sends, pays or deletes anything itself.
More+0 todayView - 279
Graphicle
Graphicle, from KarLex AI, is a single local Rust program that gives Claude Code, Cursor, Codex and other MCP agents a code graph and memory, returning excerpts with file and line references from your code, docs and past sessions, with no account or telemetry.
More+0 todayView - 280
GoRaven
A self-hosted AI agent platform for teams where agents read files, run code, call APIs and work through tasks instead of just chatting.
More+0 todayView - 281
FuXi
A terminal AI coding agent that edits code, runs commands and works across 30+ model families, with parallel multi-provider inference and cost-aware model routing.
More+0 todayView - 282
Frametell
Frametell turns an idea, PDF, slides or notes into a narrated, hand-drawn explainer film: a director agent storyboards it with you for approval, writes and voices the script and draws every page, as an open-source Mac app or Frametell Cloud.
More+0 todayView - 283
Firedrill
A simulation platform for testing AI agents before launch: it runs your agent through realistic scenarios with simulated users and tools, scores results against checks or rubrics and shows where it fails. Includes a remote MCP server.
More+0 todayView - 284
Emdash
A free, open-source agentic development environment (YC W26) for running Claude Code, Codex and other coding agents in parallel, each in its own worktree, then reviewing diffs, PRs and CI in one place.
More+0 todayView - 285
Eleven
An agent-first reverse-engineering app for macOS, Windows and Linux: load any app or binary and ask your AI agent what it does while it disassembles and analyzes the code for you.
More+0 todayView - 286
Doop
An open-source multiplayer design canvas with a design MCP server, so you and agents like Claude Code and Codex can design side by side on the same live canvas. Self-host or use Doop Cloud, free during beta.
More+0 todayView - 287
Don't Be Michael
A free, open-source AI office for small businesses on Mac and Windows: pick your type of business, get a ready team of AI agents for each department, and a manager agent hands out the work and flags what needs you.
More+0 todayView - 288
Dodaios
Open-source desktop agent OS for Windows, macOS and Linux (formerly Personal Jarvis): talk to it and it runs your coding CLIs side by side, your browser and your apps, with offline Whisper speech, a local wiki memory and support for Ollama, Claude or ChatGPT subscriptions.
More+0 todayView - 289
CozyClay
Free browser-based 3D previs software: block a scene, pose characters and author camera moves and cuts, then hand the same shots to an AI video model.
More+0 todayView - 290
CosVoice
CosVoice gives the AI assistant you already use (Grok Bot, ChatGPT, Claude, Cursor or any MCP client) a real US phone number in your area code and its own email address. It places and answers calls for you, such as booking a table or taking a contractor's quote, then sends a written summary and transcript to your inbox; connect it through its open-source (MIT) MCP server.
More+0 todayView - 291
CodeCompanion.nvim
An AI coding plugin for Neovim with chat, inline edits and agent tools that can read files, run commands and edit code, working with Anthropic, OpenAI, Copilot, Ollama and other providers.
More+0 todayView - 292
Cloudroom
Cloudroom runs Claude Code, Codex, Pi and other coding agents in the cloud, each in its own isolated sandbox on its own Git branch, using your own model logins; the Rust core is open source to self-host, and a desktop app manages local and cloud agents.
More+0 todayView - 293
CloudCLI
A web and mobile interface for Claude Code, Codex and Gemini CLI, so you can run and steer coding sessions from a browser or phone. Self-host free or use the hosted CloudCLI service.
More+0 todayView - 294
Caspian
An open-source communication SDK that lets AI agents send and receive messages over email, WhatsApp, Slack, Discord and other channels.
More+0 todayView - 295
ByteFlow
ByteFlow is a no-code builder for AI agents on top of the systems a company already runs (ERP, CRM, in-house and legacy apps) through APIs or a browser agent. Agents prepare the work, such as a CRM update or ERP entry, and a person approves it with one tap. Includes voice agents in 10+ Indian languages and document extraction.
More+0 todayView - 296
BrowserStack MCP
BrowserStack's official MCP server, letting coding agents run manual and automated tests on real browsers and devices, debug failures and check accessibility from the IDE.
More+0 todayView - 297
Bottally
Bottally is an AI marketing agent for SEO and AEO that runs on autopilot. Once you connect your blog (WordPress, Webflow, Ghost, Shopify, Wix, Notion, Framer, Next.js or a webhook), it researches keywords and competitor gaps, then writes and publishes one researched article a day with images. It also offers an opt-in backlink exchange network and tracks weekly whether ChatGPT, Google AI Mode, Google AI Overviews and Perplexity recommend your business.
More+0 todayView - 298
Bops
Bops, from Orgo, is a Mac app for a team of AI bots that handle business ops such as inbox triage, CRM follow-ups, invoices and reports, each with its own cloud computer, email address, phone number and shared memory.
More+0 todayView - 299
Beacon
An open-source memory layer that captures traces from coding agents across harnesses and turns them into self-improving memory and visibility into what your agents did.
More+0 todayView - 300
BaoCut
An AI video agent for macOS and Windows that transcribes, subtitles, translates, dubs, cuts and animates your footage from plain instructions, with every result landing in an editable timeline instead of a one-shot export.
More+0 todayView