Products from August 25, 2026

Private company data with 4x the depth and 2x the coverage of PitchBook, plus 100+ event signals and news across companies, industries, and topics. Source and diligence deals or make outreach lists and trigger outbound. Built for financial services and GTM teams, pay-as-you-go.

Hitting Claude's limit mid-work is annoying af. Diet Claude gives a live usage meter shows how much of your session you’ve used, how much time is left, and when your limits reset. It helps optimise token usage by context trimming, tightening prompts, suggesting apt models. And when you do run dry, it carries your conversation and context over to another LLM instead of starting from scratch.

Agnost AI analyzes conversations between users and your production AI agents and discovers: silent failures, agent behavior drift, hallucinations, user frustration, hidden feature requests, and churn signals. It groups them into recurring patterns, shows the exact users and conversations behind each insight, and turns them into evals and fixes.

Jotform Data Assistant turns the data you collect into answers, insights, and action. Simply ask it to create or organize tables, analyze submissions, uncover trends, generate charts, summarize responses, or update records in bulk. Built directly into Jotform Tables and Inbox, it helps you manage your entire post-submission workflow through natural conversation, no formulas, complex filters, or repetitive manual work required.

Nimbia is an AI that does screen-sharing calls to onboard and train new users of software products. It speaks, listens, and can actually click on the user's screen, so it can be truly helpful. The very first company using Nimbia is growing 40% faster because of it. When they ran an A/B test against their previous onboarding solution, Nimbia delivered 1.4X higher week-one activation and trial-to-paid conversion rates.

An orchestration layer that guides Claude Code to deliver your coding tasks without requiring your constant supervision. It fetches your context from Jira, Github, Notion and Slack, writes your prompts and verifies that claude code completes tasks correctly.

your agent can now buy things with one API call. tell it buy X from Y and Agentcard finds the product, runs checkout and pays with a single use card. works today with DoorDash, Amazon and most Shopify and Stripe stores. try it from agentcard.sh, your first order is free!

Most agentic coding tools hand you a chat log. Flare hands you the map. Every file is a node, every import an edge, with a real terminal underneath where you run claude, codex or opencode. The graph updates live as the agent edits, attributes every write to whoever made it, and pulls you in when it rewrites something the rest of the app imports. Change bursts snapshot to local history you can diff and revert. Agents take work from a board over MCP. Your machine. No account. MIT licensed.

Ninjō is infrastructure for AI sales agents on Instagram, WhatsApp & every channel where you sell. Create, test, analyze and improve agents by talking to Claude, ChatGPT, Claude Code or Codex via MCP — backed by templates validated across 150+ production agents that closed real revenue ($750K generated for clients). Versioned changes with instant rollback, synthetic-conversation testing, follow-ups, keyword triggers and a built-in CRM. Zero to live in minutes. Start free with 1,000 messages.

Shockingly thin, fully mechanical. Altar II combines a superlative typing experience with an unbelievable design.

The Claude Code Plugins repository is the official, Anthropic-managed directory for high-quality plugins that extend the Claude Code platform. It solves the problem of fragmented, hard-to-share custom configurations by providing a centralized marketplace for developers to discover, install, and contribute plugins that add skills, agents, automation hooks, and MCP servers. This is primarily for developers and engineering teams using Claude Code who want to enhance their workflows with reusable, community-vetted extensions.

Marble now ships an MCP server, letting you manage your CMS content directly from AI coding tools like Claude, Cursor, and Codex. Create posts, update content, and manage media without leaving your editor or terminal.

DockDuck is the native macOS file manager Finder should be — fast, beautiful, and 100% Swift. Tabs, dual-pane, a pinned Start dashboard, tags, instant search, batch rename, and connect to servers(SFTP/SMB) — all in one window that opens the moment you click. Pay once, no subscription. Your files never leave your Mac.

Keymap is a macOS menubar app that shows every menu shortcut in the app you're using. Double-press ⌘ to summon the panel. Local and private.

Particle Studio turns your images into interactive, customizable particle compositions. Upload an image, choose from circles, squares, triangles, or cubes, and fine-tune particle size, motion trails, and cursor interaction to create your own visual experience. When you're happy with the result, share it instantly with Copy Link or take it beyond the studio with Export HTML Bundle to create an offline, interactive version you can experiment with using your own images.

Postaway brings the charm of vintage postcards to the digital world. Pick a destination, write a message, and we’ll randomly pair it with a vintage postcard you can share by link. It’s free to use. Love postcards? Join the Postaway Mail Club for a real vintage postcard in the mail, plus other surprises. You never know what you’ll get.

Hacktron already reviews your code, detects real vulnerabilities, and learns from your feedback. Now it fixes the vulnerabilities too. With automations, Hacktron acts like a real engineer, validating security issues, eliminating false positives, and implementing patches. Set the rules once, and Hacktron performs an action on every trigger. The first action is remediation - Hacktron validates the finding dynamically, and hands your team a well-tested, ready-to-review fix.

Per-project semantic search over your Claude Code session history — not a shared or centralized memory store. Indexes JSONL transcripts into a local SQLite file, retrieves via bge-m3 embeddings (Ollama) with automatic FTS5 BM25 fallback, and auto-injects relevant past context at session start. Companion to session-end: session-end gives "where I left off," session-indexer gives "what we decided" — same Stop/SessionStart hooks. Apache 2.0, 75 passing tests, go install and nothing to deploy.

Not only can AI agents build your UI, they can now test what it actually looks like. Buddy Visual Tests captures every UI change, compares it pixel by pixel with an approved baseline, and brings visual regression testing straight into your delivery flow. With CLI, MCP and Skills support, agents can spot visual bugs, fix them, rerun tests, and hand over intentional changes for human approval.

The first public library of sponsored ads running inside ChatGPT: 11,103 advertisers, 415,289 ad placements, and 43,410 unique creatives across 970 niches each linked to the exact prompt that triggered it. Spy on Competitors ads and optimise your CTR.

Alchemize is an AI code review platform that helps teams understand and test code. Agentic coding has 10x’d code output, creating larger PRs more frequently, but existing review workflows haven’t kept up. Alchemize breaks large changes into smaller, dependency-ordered PRs and guided reviews. It surfaces the prompts, intent, and assumptions behind agent-written code, then uses browser agents to test affected workflows.

Awesome LLM Apps is a curated repository of 100+ free and open-source AI Agents, Agent Skills, and RAG (Retrieval-Augmented Generation) applications. It solves the problem of discovering and accessing high-quality, production-ready AI tools by providing a centralized, real-time updated ecosystem. It is designed for AI builders, developers, and engineers looking to leverage pre-built components to accelerate their own high-impact AI projects.

Assistly is a live meeting assistant for macOS and Windows. No bot joins your call — it works from your computer's audio and puts guidance on your screen the moment a question lands, in a private overlay that never shows in screen shares or recordings. Every speaker tracked, dozens of languages, and notes with action items after every session.

Most chatbot analytics tell you how many conversations happened. Bot Report Card tells you what actually went wrong. Upload your chatbot conversations and get an AI-powered audit that uncovers hidden issues, hallucinations, customer frustration, missed sales opportunities, and risky responses. Every finding is backed by real conversations and includes practical recommendations, so you know exactly what to fix first.

Connect your website and let Splitsense AI do the heavy lifting. The platform analyses your analytics and session recordings, spots conversion blockers, answers questions about your users through AI chat, then creates and runs A/B tests to find what works best. No endless dashboards, no hours spent watching recordings, and no need to write every variation yourself. Just connect your site, ask questions, and let your website get better over time.

Every goat from history and fiction, ranked by how much people paid to put them there. Outbid anyone. There is no committee.

Ponytail is a ruleset for AI coding agents that enforces a 'lazy senior dev' mindset, drastically reducing over-engineering. It makes your agent stop at the first, simplest working solution—reusing existing code, leveraging standard libraries, and avoiding speculative features. It's for developers who want their AI assistants to produce minimal, maintainable, and robust code without unnecessary complexity.

Hister is a self-hosted search engine that indexes the full content of the web pages you visit and the files you keep. It solves the problem of losing useful information by creating a private, searchable memory of your digital content, putting you back in control of your data. It's for privacy-conscious individuals, researchers, and anyone who wants to reliably find information they've previously encountered without relying on external services.

Marin is an open-source framework for collaboratively researching and developing foundation models. It solves the problem of opaque, siloed AI research by programmatically documenting every step—code, data, experiments, and results—in real-time. It's for researchers, engineers, and anyone who shares a vision of open science and wants to contribute to building powerful models from scratch.

Linguar pairs you with a tandem partner — you're learning their language, they're learning yours. Text, voice, and video are built in, with AI on your side: inline translations and explanations without leaving the chat. Highlight any word or correction and it becomes a spaced-repetition flashcard. Unlike lesson apps, everything you learn comes from real conversations with a real person. Free to use, built by a solo founder learning Vietnamese in Ho Chi Minh City.