Trending Radar/trending
Track the hottest AI launches.
Follow real-time momentum across daily drops and the best of the month. Every signal is curated for teams hunting the next breakout product.
Active launches
4
Drops today
4
Top categories
5
Today's Launches
withHuman is the approval layer for AI agents. It lets teams put their most consequential agent actions behind human approvals, so their agents can do real work while someone accountable stays in the loop. Rather than blocking agents entirely or letting them run unchecked, withHuman intercepts the tool calls an agent wants to make and holds the risky ones until a person has looked at them. It is framework-agnostic, open source, and built on open standards, and it is aimed at teams running agents in production — support, payments, SRE, finance, sales and marketing — where an action such as a refund, a payment, a merge or a data deletion cannot simply be taken back. Agents are increasingly capable of taking real action: calling Stripe, merging pull requests, rolling back deployments, updating CRM records or paying invoices. The problem is that a tool call is a real-world event. Once a refund is issued, a payment goes out or a table is dropped, there is no undo. Teams therefore face an uncomfortable choice: keep agents on a short leash and lose the value of autonomous work, or let them run and accept that some actions will be wrong. withHuman exists for the actions you can't take back. Its stated approach is to let agents draft everything and ship nothing until someone accountable has looked at it, while still allowing the routine majority of calls to pass without a human ever being bothered. Everything starts with interception. Each tool call an agent makes is intercepted by AAP, the Agent Approval Protocol, and sent to withHuman for approval. If the agent supports AAP, withHuman just works. Coverage spans coding agents through hooks — Claude Code and Codex among them — and agent frameworks through SDKs for LangGraph, CrewAI, Mastra and others. There is also an MCP gateway, and for teams building their own agents the open Agent Approval Protocol is available directly. In the product's own illustration, a support agent's stripe.refund call is held by withHuman before it reaches Stripe, with the arguments captured as a structured request. Approval pipelines are how withHuman avoids approval fatigue. Instead of sending every single call to a person, teams write policy rules that approve or deny routine requests automatically, and only the tough stuff goes to humans. Rules can be conditioned on the agent, the tool, the arguments and the agent context. A simple example from the site: refunds under $20 approve automatically, while a $75 refund that exceeds the $20 threshold skips the automatic rule and is escalated. For calls that rules can't describe — such as judging whether a support reply is routine — there is an AI judge. Teams can also use webhooks to their own policy service, so existing policy logic can participate in the pipeline. In the demo, three of four calls are decided without a person touching them. Escalation paths make sure the request reaches the right human rather than a generic queue. Teams write rules that decide which requests go to which team or person, routing by agent, tool, arguments or team. Teams then set their own escalation order and on-call flows, and requests escalate when nobody answers in time. The example on the site shows a $2,400 refund held because it is over $1,000: it goes to Sam Alvarez, the finance lead, while under-$1,000 refunds go to the support team and out-of-hours requests go to the on-call person. Reviewers are met where they already work — Slack and Discord, iPhone and Android apps with push, plus email, text message and WhatsApp — and each reviewer's own notification rules pick the channels. Every decision is kept on the record. withHuman maintains an append-only audit log of run history for production, capturing each request, the decision and any notes, with reviewer identity attached to every decision and the full request retained alongside it. Entries such as db.delete_rows approved by d.chen, stripe.refund approved by s.alvarez with a note that it was verified with finance, or k8s.apply denied by m.okafor are all recorded. The point is straightforward: when someone later asks who approved this, the answer is available, with the identity of the person who said yes and the exact request they saw. withHuman's distinctive approach is that it is a protocol, not a walled garden. Your agents speak to withHuman via AAP, the Agent Approval Protocol, an open spec started by withHuman to let agents wait on human decisions. That means integrations are made with AAP, not with withHuman specifically, so one integration works with any provider. The spec is built in the open, with issues, proposals and changes happening in public, and the aim is stated plainly: to be the best provider, never the only one. The spec, SDKs, adapters and conformance tests are open source, so teams can swap providers without rewriting a single agent. The withHuman core — the queue, the audit trail and the web UI — is also open source and self-hostable, so it can run on your own infrastructure or be run for you. Following a single consequential action end to end shows how the pieces fit together. A customer asks for a refund; the support agent finds a duplicate charge and decides to refund it; the agent's tool call is intercepted and held by withHuman before it reaches Stripe. The rules check it: the approval pipeline approves or denies the call automatically, or asks a human to take a look. In the example, a $75.00 refund exceeds the automatic $20 threshold, so the request goes to the Payments team, where Chris is on call. Chris is notified on his preferred platform, sees the tool call and the request context — amount, reason, customer — and approves or denies. The approved refund then reaches Stripe and the agent carries on, with the resulting stripe.refund reference recorded. Getting started is done through a CLI that connects every supported agent on a machine. A single curl-and-sh install command onboards coding agents such as Claude Code, Codex, OpenClaw, Pi, Hermes and DeepSeek, places the hooks in position, and finishes in the browser where the request appears for approval or denial. Supported integrations listed on the site include coding agents, an MCP gateway, LangGraph, Deep Agents, Pydantic AI, OpenAI Agents, Claude Agent SDK, Google ADK, CrewAI, AI SDK, Mastra and an HTTP API. Setup examples use pip installs for the Python frameworks, npm packages for the TypeScript ones, and a simple POST to /api/aap/v1/requests for anything else, with a timeout field so a call does not wait forever. Use cases are framed around the actions you can't take back. An AI SRE can request approval for kubernetes.rollout_undo before rolling payments-api back after a 5xx rate spike. Coding agents surface Bash commands. Customer support routes stripe.refund. Finance and accounting routes bill.pay. Sales routes docusign.send. Marketing routes campaign.send. Personal assistants can route calendar.create_event. In every case the agent can draft the work — the refund, the rollback, the payment, the contract send — and nothing ships until someone accountable has approved it. withHuman is aimed at companies running AI agents, not hobby projects — the kind that want one set of rules for every agent the company runs. The reviewer experience is built for team members who are on call for a particular domain, whether that is the Payments team, a finance lead or an SRE. On availability, the project is open source with a hosted version; teams can self-host the core or let withHuman run it for them. The Product Hunt launch notes an offer of three months of Scale free using the code PRODUCTHUNT. In short, withHuman gives agents the freedom to do real work while keeping humans accountable for the decisions that matter. By intercepting tool calls, deciding routine requests automatically, routing risky ones to the right person, and recording every decision, it turns human approval from a blocker into a workable layer that sits underneath every agent a company runs.
Navige is a cost-control layer for AI agents that sits between your agents and everything they pay for. On one side are the agents themselves and the tools and frameworks they run on; on the other side are the models and metered services those agents call. Navige plugs into both and routes every call through one governed layer so that, in the company's words, every run gets cheaper and faster, with the same result. The product is built for teams that run AI agents in production and want to manage programmatic AI spend — the money spent on models, agent traffic and metered AI tools — rather than only reviewing it after the fact. Most cost tooling for AI agents works backwards. As Navige puts it, everyone else shows you what the run cost after it has run; Navige changes the step before it runs. The company frames the underlying problem as a set of familiar failure patterns: runs that never finish, where agents keep running without producing an output; big model, small task, where a step is answered by a larger model than its outcome required; chasing, not remembering, where the same work is redone instead of reused; one budget, many agents, where spend is not governed centrally; and misread, then paid for, where an error is only discovered after the call has been billed. The stated consequence is that the bill is decided before the dashboard sees it — by the time cost reporting catches up, the money has already been spent. Navige lightens every run in four stated ways. The first is cache and reuse, described as never pay twice: when a verified answer is still valid, Navige reuses it instead of paying for another model or tool call. The second is context trimming and tool payload capping, described as only pay for what's used: oversized tool results are limited and accumulated history is trimmed before the next request is sent to the model. Together these two controls target both halves of token spend — the context a model is asked to read and the output it is asked to produce — by removing repeated work and excess context rather than by degrading the answer. The third control is a loop and failure guard, described as stopping runaway jobs: repeated failures are blocked before another call adds to the bill, which addresses the 'runs that never finish' pattern directly. The fourth is smart routing, described as the right model, once it's earned: Navige chooses the model based on the task complexity. Routing is deliberately conservative — if Navige is unsure, it keeps your chosen model — so the substitution only happens where the system is confident the outcome will hold. Governance is built into the same layer. Users can set budgets, catch runaway loops and approve sensitive actions. Tool calls are checked against your rules before they run, not flagged afterwards, which means the guardrail acts at the moment of decision rather than in a post-hoc report. Costs and savings are visible by job, with estimates clearly labelled so that projected figures are never confused with measured ones. Changes can be previewed before the controls are switched on, so teams can see what a policy would do before it takes effect. The Watchtower tier is described as free forever. Architecturally, Navige is a middle layer rather than a replacement. Your agents, frameworks, keys and providers stay exactly as they are; you change one line of config and both ends are plugged in once. On the tools and frameworks side this covers LangChain, LangGraph, CrewAI, OpenAI Agents, MCP and Agentforce. On the models side it covers Anthropic, OpenAI, Google, AWS Bedrock, Mistral and Meta Llama, with the site summarising it as 'Claude, GPT, Gemini or Bedrock. One line of config, any framework.' Because the layer sits in the path of every call, the bill is influenced as work runs rather than reconstructed afterwards. Navige calls this approach Sufficiency Intelligence: 'Sufficiency isn't about using less AI. It's about using exactly enough.' That framing matters because the product is explicitly not a discount: it does not propose a cheaper answer to the same question, it proposes the same answer reached at the level it needed, and where a step needs a frontier model, sufficiency keeps it there. The promised outcome is straightforward: the same result with smaller bills, plus faster runs. Because the four controls act before a call is made, savings arrive during the run instead of appearing as a retrospective insight. Because routing defers to your chosen model when it is unsure, and because measurement checks results as well as cost, the spend-versus-quality trade-off is handled explicitly: a step that got cheaper and started being wrong is reported as a failure, never as an opportunity taken. Users also gain visibility — cost and savings broken out by job, with estimates labelled — and control, through budgets, approvals and rules that are enforced before execution. The most direct use case is repetitive agent work: the same conclusion reached the same way many times, where a verified answer can be reused rather than recomputed. Navige's own calculator treats repetitive work as carrying the most opportunity and complex work the least. A second scenario is the multi-agent environment, where several agents touch the same work and share one budget; a governed layer makes that budget observable and enforceable. A third is agents that use premium models by default or send large prompts and context, where smart routing and context trimming apply. A fourth is agents that make paid tool, search or data API calls, where a still-valid held answer can replace another paid call. Before committing, teams can run the sufficiency calculator, which asks for monthly programmatic AI spend and the kind of work involved and returns an estimated opportunity range broken into overspecified intelligence, repeated or unnecessary execution, excess context and output, and tools and APIs. Once connected, Navige leaves a slice of your jobs running untouched and compares the two so the difference is observed rather than assumed. The documented workflow is 'Plug in your agents. Switch on when you trust.' Navige's stated audience is teams running AI agents at scale: the site reports 51+ agents connected and $9K+ in AI spend managed, priced to the millionth of a dollar and updated live, with tool calls governed against rules before they run. The supported integration surface spans agent frameworks and orchestration tools — LangChain, LangGraph, CrewAI, OpenAI Agents, MCP and Agentforce — and model providers — Anthropic, OpenAI, Google, AWS Bedrock, Mistral and Meta Llama. Teams that do not see their platform are invited to say so. On pricing, the Watchtower tier is described as free forever, with dedicated pricing and enterprise pages for the other options; the site also notes that the spend figure entered into the calculator covers models, agent traffic and metered AI tools while excluding employee seat licences. The takeaway is that Navige treats AI agent cost as something to be governed during execution rather than audited afterwards. By sitting between agents and the models and tools they pay for, and by applying caching, context trimming, loop guards and smart routing under user-defined budgets and approvals, it aims to deliver the same output at a lower bill — using exactly enough intelligence for each step.
Chatway is a live chat and AI customer support platform with an all-in-one inbox, automation, and MCP. It is built for customer support and sales teams that want to handle every customer conversation from one place while adding AI where it helps most. Chatway lets businesses bring their own AI agent — connecting ChatGPT, Claude, Gemini, Cursor, or any MCP-compatible assistant — to manage customer conversations, reply to messages, search contacts, and access a knowledge base. Alongside that, Chatway ships with a built-in AI Support Agent, a shared inbox, a help center, automation, and iOS and Android mobile apps. Over 50,000 businesses use Chatway to build better customer connections. Customer support today is scattered. Conversations arrive through a website chat widget, WhatsApp, Facebook Messenger, Instagram, and email, and agents are expected to answer quickly without losing context or repeating themselves. Support teams also face rising volumes and the expectation of 24/7 availability, which is difficult to staff around the clock. Chatway addresses this by centralising every customer conversation in one unified inbox and by offering automation and AI so that routine questions can be handled instantly. The optional MCP connection means teams that already rely on an AI assistant can put that assistant to work on support, rather than starting over with a new tool. Chatway's built-in AI Support Agent answers questions and supports customers 24/7 across a website, WhatsApp, Instagram, Messenger, and Email. It is trained on your website and knowledge base, so it delivers instant, accurate answers in multiple languages and seamlessly hands conversations over to your team when human support is needed. For teams that already use an AI agent, Chatway supports Bring Your Own AI Agent with MCP and Webhooks. You connect your own agent — including Claude Code, OpenAI Codex, GitHub Copilot, Gemini, Devin, Cursor and others — through MCP and choose what it can access, so it can tag, hand off and help your team. It works alongside Chatway's built-in AI Support Agent rather than replacing it. Every conversation can live in a single all-in-one inbox. Chatway integrates with WhatsApp, Facebook Messenger, Instagram, X, Email, and Phone so customers can reach out through the channel they prefer while your team works from one place. Team collaboration tools let agents share notes, assign tasks, and work on conversations together, which improves efficiency and effectiveness. Live Visitors Insights shows who is browsing your website in real time so you can instantly start a conversation at the right moment. Multilingual Support translates incoming messages into agents' preferred languages in real time, supporting more than 20 languages, and the chat widget can be customised for diverse audiences. Automations and Smart Workflows let you create custom rules that respond to chats, form submissions, page visits, and more — engaging visitors, qualifying leads, and simplifying repetitive tasks. Deep eCommerce integration connects Chatway with platforms such as Shopify and WooCommerce so your team and AI agents get real-time order and cart insights, access to store data, and the ability to answer questions with relevant, up-to-date product information. A self-service Help Center lets you publish FAQs, guides, and documentation, while FAQ and Canned Responses give agents a library of common answers they can send in seconds. Analytics reports on your support activity so you can better understand customer interactions, and Segmentation categorises and labels conversations using specific criteria for more personalised support. Notifications keep you updated on all incoming messages with email and push alerts, and Full Customisation lets you personalise the chat widget to match your business's style and branding. Chatway's unique approach is that it does not force a choice between a human team and an AI agent. Human agents can reply to customers from the Chatway web or mobile app, work alone or with a team, and bring in an AI agent whenever they want. Conversations can be handed between AI and humans without losing context. Two paths are available for developers: connecting an existing AI assistant through MCP and webhooks, or building your own agent against the REST API. With the API route, you receive a signed webhook event the moment a visitor writes, and you reply through the REST API — and the API is included on every plan. The outcomes are practical: faster first responses, round-the-clock coverage, and less repetition for agents. Because the AI agent is trained on your own website and knowledge base, answers stay accurate and relevant. Because conversations are centralised in one inbox, agents do not have to switch between tools. And because handoffs between AI and humans preserve context, customers do not have to start over. Chatway reports over 1,000 five-star reviews across the iOS and Android app stores, and over 50,000 businesses already use it to build better customer connections. Chatway is positioned for a wide range of industries. eCommerce teams use it to recover carts, answer questions, and boost sales. SaaS teams use it to convert trial users into customers with support. Customer support teams use it to resolve issues quickly and improve satisfaction. Finance teams use it for secure client questions, education teams for student support, travel businesses for guiding travellers and answering booking questions, and real estate teams for responding to inquiries and closing deals. Professional services use it to connect with clients quickly and offer personalised service, HR and recruitment teams use it to engage candidates and streamline hiring, and nonprofits use it to engage supporters and build relationships. Chatway is aimed at customer support and sales teams of all sizes, including developers who want to build their own agents. It integrates with WhatsApp, Facebook Messenger, Instagram, X, Email, and Phone, with eCommerce platforms like Shopify and WooCommerce, and with site platforms such as Shopify, Wix, and Duda. Supported AI agents include Claude Code, Claude Desktop, ChatGPT, Codex, Cursor, Muse, Gemini, Grok, VS Code, Cline, Devin, OpenCode, Goose, Manus, and any MCP client. Pricing is free to start with no credit card required, and the API is included on every plan. In short, Chatway is a live chat and AI customer support platform that unifies every conversation, automates the routine, and lets you bring whichever AI agent you already trust. It lets support and sales teams deliver faster, more consistent answers across web, mobile, and social channels.
Daddy Issues is a companion app for dads that delivers a weekly family briefing, helping fathers stay one step ahead before anyone has to remind them. It is built for dads, by dads, and its central promise is straightforward: think ahead, fight less. The app uses AI to connect your kids, your calendar, your responsibilities and your tasks, then surfaces what is coming up, what you might be missing, and what is worth handling now. Rather than waiting for a question you did not anticipate — the familiar "Did you think about this?" — you start each week with a clear picture of what actually matters and what you can act on early. The problem Daddy Issues addresses is not a lack of effort or intention. As the site puts it, you are involved, you care, you do a lot — and still you hear "Did you think about this?" You find out things too late. You react instead of anticipate. That is where it breaks: not effort, not intention, but timing. The app frames the deeper issue as ownership versus helping, stating plainly that helping is not the same as owning, and that if someone has to remind you, you are not ahead — you are catching up. The product exists so dads can stop being the one who gets reminded, the one who reacts late, or the one who "helps" but does not lead, and instead become the one who already handled it. At the core of the app is the weekly briefing — a summary of your family life that is explicitly described as not just a summary, because the AI connects the dots you do not see. The briefing is organized around four questions: what's coming up, what actually matters, what AI spots early, and what to handle now. A sample week shown on the site illustrates the format: a kindergarten trip on Thursday with a snack needed, a doctor follow-up that is overdue, and a birthday on Sunday where the gift is missing — closed out with a simple count of three items needing attention that week. The value is that the briefing is built around your actual week rather than a generic checklist, so the things that would otherwise surface too late appear while there is still time to act. Once the briefing has surfaced something, the next step is to turn it into actions and add it to your calendar. The app does not stop at awareness; it moves from what the AI noticed to what you are going to do about it, with "Done" as the stated end state of that loop. This matters because the gap between knowing something is coming and actually handling it is where family logistics usually fall apart — the kindergarten snack, the overdue follow-up, the missing gift. By converting the briefing into concrete actions and calendar entries, Daddy Issues closes that gap in the same place the problem was identified. The app also learns how your family works. The mechanism described is deliberate rather than automatic: you create tasks, and the AI understands patterns from them. Over time it starts anticipating what matters — earlier. As a result, things stop slipping, including the ones you did not track before. That last point is significant: the system is designed to catch items that never made it onto a list in the first place, not merely to remind you of things you already wrote down. The more you use it, the more the briefings reflect the real rhythm of your household rather than an idealized version of it. The overall methodology is described in three steps. First, connect your basics — calendar, kids, routines. Second, get your weekly briefing, built by AI around your actual week. Third, act early, before things pile up. Onboarding is presented as low-friction, taking about one minute with no setup stress, alongside an invitation to "show me my first week." Rather than asking dads to adopt a heavyweight planning system, Daddy Issues positions itself as a lightweight layer on top of the basics they already have, producing one briefing a week and letting the actions flow from there. The stated benefits are deliberately modest and human: less stress, fewer reminders, more trust. Daddy Issues does not promise perfection — the origin story notes that the founder built something that actually helps you stay ahead, "not perfectly, but consistently." Consistency is the point. Fewer reminders matters because it means the mental load is not being pushed back onto someone else; more trust matters because the dynamic shifts from catching up to leading. The outcome described is that you do not just help more — you take ownership. For dads who feel they are contributing but still behind, that reframing is the real benefit. Concrete use cases appear throughout the material. A typical week might include a kindergarten trip on Thursday that needs a snack packed, an overdue doctor follow-up that should be handled, and a child's birthday on Sunday where a gift is still missing. The question at the top of the site — "backup clothes for daycare?" — captures the kind of everyday, easily forgotten item the app is designed to catch. Beyond individual items, the weekly briefing supports a recurring ritual: reviewing what is coming up for the family, turning the important items into tasks or calendar entries, and acting before the week fills up and things pile up. Daddy Issues is explicitly built for dads — the site and its tagline describe it as a companion app for dads, created by a dad who was tired of being behind. The origin story emphasizes that it did not start as a product but as a personal fix: trying to keep track of everything, still missing things, still being reminded, and then building something that genuinely helps you stay ahead. The basics you connect are your calendar, your kids and your routines, and the app produces a briefing you can turn into actions and add to your calendar. Product Hunt lists the product under the Calendar, Virtual Assistants and Family topics. In short, Daddy Issues is a weekly family briefing that uses AI to help dads think ahead rather than react. It connects kids, calendar, responsibilities and tasks, surfaces what is coming up and what is worth handling now, learns from the tasks you create so it can anticipate earlier, and turns its findings into actions. The value proposition is stated plainly: think ahead, fight less — less stress, fewer reminders, more trust, and the shift from helping to owning.