AI agent tools launched Oct 19 – Oct 25, 2026, page 4
378 tools added Oct 19 – Oct 25, 2026. Page 4 of 4. Ranked by that week’s votes, then by the date added. Top: AutoScientists, Appwrite MCP, AnySearch.
Quick answer: The newest additions on this page are AutoScientists, Appwrite MCP, AnySearch. 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)
Page 4 of 4Previous
- 301
AutoScientists
A research system from Harvard's Zitnik lab where teams of LLM agents self-organize to plan and run long-running scientific experiments.
More+0 todayView - 302
Appwrite MCP
Appwrite's official MCP servers, so agents can manage Appwrite databases, users, storage and functions and look up Appwrite docs while building your backend.
More+0 todayView - 303
AnySearch
A search MCP server and API for AI agents, covering real-time web search, vertical search and parallel batch queries with structured results and anonymous access.
More+0 todayView - 304
Andee
Andee is an Android agent you install as one APK (Android 11+, no root) that reads the screen and taps, types and replies in any app for you, keeps private on-device notes, and uses the OpenAI-compatible model and speech provider you choose.
More+0 todayView - 305
Algolia MCP
Algolia's official MCP server that lets assistants search and manage Algolia indices, check analytics and tune relevance through natural-language requests.
More+0 todayView - 306
Agentlas
A local-first agent OS that keeps specialist agents in a hub and spins up a temporary orchestrator for each task, with reusable methods and your choice of model and host.
More+0 todayView - 307
Agentic Scientist
Sakana AI's open-source pipeline that turns coding agents such as Claude Code, Codex, Cursor and Gemini CLI into AI scientists: from a task file they propose ideas, run and score experiments and ablations, then write the paper.
More+0 todayView - 308
AgentEnv Framework
AgentEnv Framework is Scale AI's open-source Python SDK and CLI for building RL environments for agents: containerized worlds with realistic apps and data behind an MCP gateway, plus tasks (as DAGs) that grade any agent in any sandbox.
More+0 todayView - 309
AgentDock (NexusDock)
A secure MCP runtime that lets ChatGPT, Claude and other AI clients operate your Mac, Windows, Linux and Android devices, with memory, tools and reusable automations.
More+0 todayView - 310
AgentConnect
An open-source, multi-agent workspace where you @-mention any agent wherever work happens, and agents work alongside your team and each other.
More+0 todayView - 311
AgentBay
Alibaba Cloud's cloud sandbox service for agents, offering ready-made browser, Linux and Windows desktop, mobile and code environments that agents control through an SDK or MCP.
More+0 todayView - 312
Agent Tincan
Agent Tincan lets your AI agents (Claude Code, Codex, Gemini, Hermes, ChatGPT and others) ask each other to do things and hand back results through a small relay on your own Tailscale network, with no open ports or API keys between agents.
More+0 todayView - 313
Agent Sandbox (Kubernetes)
A Kubernetes project that adds a Sandbox resource for running isolated, stateful agent workloads such as code execution and browsers, with warm pools and fast startup on your own cluster.
More+0 todayView - 314
Agent Barn
Agent Barn is an open-source (Apache-2.0) control plane for running a fleet of AI agents on your own Kubernetes: create, configure, run and monitor agents across Slack, Microsoft Teams and Telegram from one place.
More+0 todayView - 315
AI Beat
An open-source AI red-teaming suite: PromptBeat attacks models and prompts, and AgentBeat runs black-box security evaluations against HTTP-exposed agents.
More+0 todayView - 316
shadcn/lint
Linter for Tailwind design systems from shadcn that turns your design rules into checks coding agents can run and fix against.
More+0 todayView - 317
sem
Semantic layer on top of Git that diffs, blames and traces impact by function and class instead of by line, with an MCP server for coding agents.
More+0 todayView - 318
iMCP
macOS app that exposes your Messages, Contacts, Calendar, Reminders and more to AI assistants through MCP.
More+0 todayView - 319
html-video
Lets your coding agent turn HTML, CSS and data into real MP4 videos on your own machine, with templates and pluggable render engines.
More+0 todayView - 320
Zeroboot
VM sandboxes for running agent code that start in under a millisecond by forking a warm snapshot with copy-on-write memory.
More+0 todayView - 321
Xquik
Xquik is an X (Twitter) data service for searching and extracting tweets, replies, followers and profiles, monitoring accounts and posting, over REST, an OAuth MCP server and SDKs; pay-as-you-go from $10 or monthly plans from $20.
More+0 todayView - 322
XCrawl
XCrawl is a web scraping, crawling and SERP API that returns clean JSON, Markdown or screenshots in one request, with agent skills for plugging it into AI agents; free trial with no card.
More+0 todayView - 323
Webcmd
Browser layer for AI agents that learns how each website works as agents use it and saves that as local memory to make later runs faster and cheaper.
More+0 todayView - 324
Vectoree
Vectoree gives coding agents a backend behind one project key: an OpenAI-compatible model gateway across providers, an MCP tool hub, auth, Postgres and storage, driven by a skill and CLI, pay-as-you-go with no monthly fee.
More+0 todayView - 325
Universal Modder
Skills, tools and a shared knowledge base that let Claude Code and other coding agents mod PC games you own, from engine recon to in-game testing.
More+0 todayView - 326
Treg
Single endpoint and token that lets agents call a catalog of third-party APIs for SEO, social data, enrichment, scraping and media generation, priced per call.
More+0 todayView - 327
Toolhouse
Platform for turning repetitive work into AI workers that run tasks on a schedule and report back.
More+0 todayView - 328
TecAdRise Bot
TecAdRise Bot is a free, MIT-licensed Windows desktop app (Electron and Cursor SDK) for running a local team of AI agents, each with its own model, memory, skills, MCP servers, workspace and schedule.
More+0 todayView - 329
SolidCraft
Parametric 3D CAD app written in Rust for desktop and web, with a built-in MCP server so AI agents can sketch and build models.
More+0 todayView - 330
Skill Recorder
Microsoft desktop app that records you doing a task once and turns the recording into a reusable skill or automation for Copilot agents.
More+0 todayView - 331
Sentience
Personal AI that builds a private memory from your email, meetings, messages and screen and acts as your digital twin, drafting and answering in your voice.
More+0 todayView - 332
Scout (Outcrawl)
Open-source browser agent from Outcrawl that opens a real browser and clicks, types and reads pages to finish a task you describe.
More+0 todayView - 333
Rogue
Agent evaluator and red-team tool that probes your agent with test conversations and attacks and reports pass or fail against your policies.
More+0 todayView - 334
RobotTraining.jobs
Free job board and remote MCP server for paid robot-training work (teleoperation, demonstration recording, AV and drone test operations): AI assistants can search open roles, hourly pay and hiring data with no key or account.
More+0 todayView - 335
Raven
Host agent that plans complex jobs as task graphs and coordinates built-in and third-party agents for research, coding, design and on-call work.
More+0 todayView - 336
Rakazo
Self-hosted personal AI agent and persistent teammate for web, desktop, iPhone and Android, with your own choice of model and computer sandbox.
More+0 todayView - 337
Pragor
Coordination and governance layer for teams of people and AI agents, not an autonomous agent: a shared board with tasks, directed messages, approvals, files and an attributable activity record, where agents connect over REST or project MCP access.
More+0 todayView - 338
Pixeltable
Multimodal data layer that combines storage, transforms, indexing and retrieval in one Python library for building agents over images, video and documents.
More+0 todayView - 339
Pascal Editor
Local-first 3D building and architecture editor in the browser or CLI that AI agents can drive through MCP tools.
More+0 todayView - 340
Paper Search MCP
MCP server and CLI that searches and downloads academic papers from arXiv, PubMed, bioRxiv, Semantic Scholar and other sources for research agents.
More+0 todayView - 341
Palmier Pro
macOS video editor built around AI, where an assistant can search footage, assemble cuts and edit the timeline for you.
More+0 todayView - 342
OpenQodex
Code review that runs inside your coding agent before you push, combining security and quality scanners with a separate AI reviewer.
More+0 todayView - 343
OpenPencil
Open-source vector design tool where teams of AI agents turn prompts into UI designs on a live canvas, with a built-in MCP server.
More+0 todayView - 344
OpenMausBot
Open-source chat app for running your own team of AI bots, each with a virtual machine it can use, on the model you choose.
More+0 todayView - 345
OpenFilm
Open-source AI video agent: a skill and CLI that let Claude Code, Codex or any coding agent make films as web pages, plus Studio, a local editor to change and render anything it makes.
More+0 todayView - 346
OpenAdapt
Execution layer for computer-use agents that turns a demonstrated task into a local program that repeats the clicks without model calls and stops on mismatches.
More+0 todayView - 347
Oh My OpenAgent (OmO)
Agent harness add-on (OmO) for OpenCode and Pi that runs multi-model coding agent teams with memory, planning and parallel workflows.
More+0 todayView - 348
Novastart
Novastart is an infinite-canvas operating system where your apps, AI agents and teammates work together on one shared whiteboard space; Free, Pro $10 and Team $20 per user.
More+0 todayView - 349
MoonPay CLI (MoonAgents)
MoonPay's CLI, local MCP server and API that give AI agents non-custodial wallets, swaps, bridges, transfers and fiat on and off ramps.
More+0 todayView - 350
Monid
Gateway that gives an agent one base URL and one key to call thousands of paid tools, from web scraping and enrichment to image and voice generation, billed per call.
More+0 todayView - 351
Memgraph
In-memory graph database used as the graph layer for GraphRAG pipelines and agent memory, with Cypher queries plus vector and text search.
More+0 todayView - 352
MailVeri MCP
Open-source MCP server that lets AI agents and coding assistants verify single emails and bulk email lists through the MailVeri API, with SMTP, catch-all, disposable and role-account detection.
More+0 todayView - 353
Magpie
Free, open-source menu bar app and local gateway that lets any coding agent (Claude Code, Codex, Gemini CLI, OpenCode and 60+ more) use any model provider or subscription, with failover when a quota runs out.
More+0 todayView - 354
Macro
Team workspace that links email, chat, docs, tasks, calls and CRM with agents that share one team memory.
More+0 todayView - 355
MCP-UI
SDK that lets MCP servers send interactive web components such as forms, charts and buttons that chat hosts render inside the conversation.
More+0 todayView - 356
MCP Kotlin SDK
Official Kotlin Multiplatform SDK for building MCP servers and clients on JVM, Native, JS and Wasm, maintained with JetBrains.
More+0 todayView - 357
LongMemory
Local-first memory engine for agents that keeps durable, time-aware memories in SQLite and serves them to Claude, Copilot, Codex and others over MCP, CLI or HTTP.
More+0 todayView - 358
LLM for Zotero
Zotero plugin that adds a research agent to your library so you can ask questions about papers, compare sources and save notes without leaving the reader.
More+0 todayView - 359
Is My Agent Safe
Is My Agent Safe explains your OpenClaw security audit and version in plain English with a red, amber or green result that puts the most important finding first and flags versions missing published security fixes; free check, full report $29 one-off, Agency seats $99/month for US and UK agencies.
More+0 todayView - 360
Infisical
Open-source platform for managing secrets, certificates and privileged access, including scoped credentials for AI agents.
More+0 todayView - 361
Hyperbrowser
Cloud browsers and isolated sandboxes for AI agents that you start in one call and drive with Playwright, Puppeteer or any agent.
More+0 todayView - 362
Home Assistant MCP (ha-mcp)
Community MCP server that lets AI assistants control Home Assistant devices, read their states and build or edit automations in plain language.
More+0 todayView - 363
HarnessRouter
One API for running coding-agent harnesses such as Codex, Claude Code and Hermes as product backends, with sessions, streaming, files and failure handling.
More+0 todayView - 364
Golem
Agent-native platform for building durable agents and distributed apps that keep state and never duplicate work after a failure.
More+0 todayView - 365
FlexQueries
FlexQueries is a hosted MCP server and REST API for SEO and AI-visibility research (keywords, SERPs, backlinks, competitors, rankings, site audits) that connects to Claude, ChatGPT, Cursor and Codex over OAuth, billed with prepaid credits that never expire.
More+0 todayView - 366
Empyre
Empyre turns a plain-language business brief into a running software company: eight AI agents (CEO, CTO, CMO, CFO and more) build it, deploy it to its own HTTPS address and keep operating it, shipping code, marketing and support with spend approval; plans $49, $149 and $299 a month.
More+0 todayView - 367
Dynamiq
Python orchestration framework for building agentic and RAG applications from reusable nodes and workflows.
More+0 todayView - 368
DramaClaw
Self-hosted AI video pipeline that goes from script to storyboard, assets and finished film for short dramas, ads and product videos.
More+0 todayView - 369
CyberStrike
Terminal agent for authorized penetration testing that runs recon, vulnerability discovery and reporting with specialized security agents on your own LLM.
More+0 todayView - 370
Conductor
Runs multiple coding agents such as Claude Code, Codex, Cursor, and OpenCode in parallel across local Git worktrees or isolated cloud sandboxes, with Mac and iOS apps to review and merge their work.
More+0 todayView - 371
ClawX
Desktop app that puts a graphical interface on OpenClaw agents so you can set up and run them without the terminal.
More+0 todayView - 372
ByteChef
Open-source platform for AI agents and workflow automation with hundreds of connectors that you can self-host or embed in a SaaS product.
More+0 todayView - 373
Augment Code
Agentic software development platform for engineering teams, with coding agents that use deep context from large codebases.
More+0 todayView - 374
Atlas
Source control for coding agents that checkpoints every agent run, links commits back to the prompts behind them and lets you query changes across agents.
More+0 todayView - 375
Agor
Multiplayer workspace where teams run and watch coding agents such as Claude Code and Codex together on shared boards.
More+0 todayView - 376
Agents24x7
Agents24x7 runs SEO and support AI agents for Shopify, WordPress and GitHub sites that read your site, prepare work and act only after you approve it; Starter from $19 a month.
More+0 todayView - 377
Agent Mesh
Private peer-to-peer network for AI agents: each node publishes tools and models, finds other agents' tools and carries a verifiable identity.
More+0 todayView - 378
AWorld
Agent harness from inclusionAI for building expert agents that search, reproduce and improve on ideas with their own tools and memory.
More+0 todayView
Page 4 of 4Previous