MultiCC brings Claude Code, Codex and other agents into one self-hosted workspace: task memory, delegation, tools and reviewable results. Run background work, collect outputs, and step in from your phone when a task needs a human.
Cady is your agent orchestrator: stay in control while your AI agents take your company from idea to scale. Works with the AI you already pay for, so there's no AI bill from us.
One workspace for your files, AI models and agents. Organize work in Projects, get answers with sources and create deliverables. Start with Individual at less than $19/month (USD), or connect your team through Communication Hub, Data and Knowledge (RAG), Sales, Marketing, Agents and Squads and Workflows. Business modules depend on your plan. Available on web, iOS and Android.
StellarFirm is customizable Agentic Assistants for your work. You set a goal; assistants plan and deliver in their own workspace. Anything that sends, publishes, or charges waits for your Approve. Built for founders and teams, with a first focus on universities and science for hard problems. Green mode prefers smaller open-source models so you use fewer tokens. Join the waitlist for an invite.
Build multichannel AI chat and voice agents for your website, Telegram, and beyond. Create specialized sub-agents to orchestrate workflows across your knowledge bases, datastores, and hundreds of third-party tools in real time. Automatically evaluate every interaction, score lead quality, and extract structured data straight from conversation transcripts.
Say a task out loud during a live call and VoTask assigns it to the right person before the call ends. When the meeting finishes, it reads the transcript and files the rest as tasks with owners and due dates. Voice works in 50+ languages, including Hindi. Say a teammate's name to see everything on their plate. Tasks carry status, subtasks, dependencies and manager approvals, so a spoken commitment becomes work someone owns. Free. Web, Android, iOS and Claude via MCP.
Meet Unison — one workspace to create, customize, preview, and schedule content across your social accounts. Built for creators, founders, and teams, Unison brings together a unified editor, content calendar, Brand Voices, media library, analytics, and MCP support for AI agents. Stop switching between tools and focus on reaching your audience. Start free with 2 connected accounts and 10 posts per month. No credit card required.
I built Clawdline to manage Claude Code and Codex sessions across multiple computers in one place. It runs on multiple computers (Mac and Linux), and you can see all of your sessions in one list. Each session reports its status (working, completed, or needs attention). You can also manage all your sessions and receive notifications from your phone (web app). Herdr, T3 Code, and Orca already cover a lot of this space, and there’s overlap. When I started building Clawdline, I didn't know about Herdr, T3 Code, or Orca. So I built it to fit my own dev workflow. At first, I used Swift to build a Mac app, but I realized that it wouldn't work if I also wanted to support Linux. So I decided to rewrite it in Go. Now it can support both of them. Main Features: - Cross Machine Agent Communication: You can ask a root session ("Local") on your Mac to start a new session ("Remote") on a remote Linux machine. Once the remote session finishes its work, it notifies the root ("Local") session. - Cross Agent Communication: You can use one root session to create tasks need multiple agents. They can communicate with each other through clawdline - Scheduled Task with Webhook: You can create scheduled tasks and combine them with your service (use webhooks to trigger new agent sessions) - Board System: tasks control for Feature, Issue, Epic, Refactor, Plan - Snippet/Playbook: If there are commands you use them very often, snippet can help you - TODO: lightweight tasks - Note: Agents can leave notes to you if they need your attention - Agent Squad: assign role to any task or session - Archive: you can archive sessions and see it in one place - Others: Intelligence session naming, Image/Video display, Voice input, Machine monitor, Usage Monitor, Dev Stack Run, Deploy progress monitor... This project is open source and I have used Claude & Codex to do independent reviews on Clawdline, Herdr, T3 and Orca. (you can find the reviews on the website.) The work still needs further input and feedback. Hope this helps other developers improve their devs! :)
Meet SiteKick 2.0: Your AI Website Sidekick! Create, improve, and manage professional websites with conversational AI. Chat with your AI SiteKick or connect your existing AI agents through MCP to manage your website directly from your favorite tools. Built on WordPress, SiteKick combines AI-powered creation, ongoing updates, multi-site management, and full website management. More than an AI website builder, it's your sidekick for the entire website business operations lifecycle.
Transglot connects your repository or CMS, translates changed strings into every configured language, and sends them back as a pull request or CMS update. Every translation is checked for placeholders, plurals, glossary terms and length before it ships. Review in one workspace, edit translations on your live site, and deliver fixes without a redeploy. Includes translation memory, a CLI, GitHub Action, API and MCP server.
Nexus AI First is a next-generation enterprise suite powered by advanced multi-agent AI. By embedding intelligent orchestration at its core, autonomous AI agents dynamically map live process changes, self-configure modules, and execute complex daily workflows across Finance and HRMS with 24/7 uptime. The platform seamlessly combines automated AI speed with strict human-in-the-loop governance, ensuring complete operational accuracy, compliance, and administrative control.
iKanban is task and project management for engineering teams that work with AI coding agents. Connect Claude Code, Gemini CLI, Cursor or any MCP-compatible agent through the native MCP server, and the agents read and update the board. Sprints, releases and linked docs sit alongside the work. A security scorecard tracks OWASP Top 10 coverage for your team. Bring your own Claude, OpenAI or Gemini key. From $8 per user per month.
Workbench improves over time by learning preferences from your sessions, enabling a built-in compounding engineering workflow. Unlike similar projects, it runs on Claude Code rather than competing with it, spending its own effort on everything around the session instead: setting up the features that already exist but few projects take the time to configure, adding what is missing between them, and making each one a switch away, so the quality of the work goes up while its cost goes down.
apt is Sri Lanka's map-first property platform with a built-in workspace for agents. • Seekers: Search homes for rent/sale by walking minutes to transit, explore nearby amenities, view total move-in costs upfront, plan commute journeys, and book viewings in one chat. • Owners & Agents: List in 5 AI-assisted steps, manage unified messaging, schedule viewings, track deals from enquiry to close, and collaborate across teams. Live across Colombo, Kandy, Negombo & Galle. Plans start at Rs 4,900/mo.
Circular Edge helps you apply MCP (Model Context Protocol) to JD Edwards EnterpriseOne. Ask questions, find orders, check inventory, trigger orchestrations, and execute approved transactions through any AI application. Talk to a JDE and AI expert today.
拾趣是一款将中国古典故事变成连环画的开源工具。选择书籍、主题和画风，AI 自动改编故事、编排分镜并生成插图。支持电脑和手机浏览器阅读，可导出 PDF 或长图，故事、图片和阅读进度保存在自己的电脑上。 亮点 从选题、故事改编到分镜绘图，完成整篇连环画创作。 支持多种画风，让古典故事呈现不同的视觉风格。 可查看原文、分镜和制作提示词，了解 AI 的改编过程。 支持已登录的 Codex CLI，利用订阅额度创作；也可接入 OpenAI API 或 Gemini。 本地保存作品，手机浏览器阅读，支持 PDF 和长图导出，方便收藏与分享。
Winneradspy is an ad creative intelligence platform built specifically for mobile app and game marketers. Explore 20M+ ad creatives across 200K+ apps, uncover winning hooks, visuals, messaging and CTAs, and track competitor campaigns with real-time alerts. Unlike generic ad spy tools, it scores creatives as Winner, Loser or Learning, helping UA managers, growth teams and agencies understand what works and build better campaigns. Query ad insights through ChatGPT, Claude or Gemini via MCP.
EMBRACE research (Forever Security, Oct 29, 2026) showed the preview browser inside Cursor, Copilot, Codex, VS Code and Claude Desktop was trusted like a real browser — and shouldn't be. Codex and VS Code were unpatched at publication; Claude Desktop's fix status is uncertain. EmbedCheck audits your own workstation: a status table with a source and date on every row, update checklists, a workspace-trust guide, a canary self-test that never reads a real secret, plus policy and report templates.
Hi everyone. I've been building Imza for the last three months. It's yet another coding agent. I know there are a dozen have been posted here. But I believe this one is different enough to have a place here. It has three explicit modes: plan, build and review. Plan mode allows you to draft a spec document together with the agent. Both you and the agent can edit the document until everything is clear. Build mode takes the plan and implements it. Review mode provides you a code review tool. You can annotate things you want to change in the code and send them as revision to the plan mode. It's entirely written in C++, requires no account, supports 50+ providers including OpenAI subscriptions or local models. Imza supports MCP, skills and instruction files out of the box and uses 8-11MB RAM at startup. One of the biggest differentiator is the Lua engine. What I did differently here is agent receives only one tool, that allows the LLM to execute Lua scripts. I then passed C++ methods as Lua bindings that the agent can execute. So model can orchestrate multiple bindings in one call. Each binding passes through a permission layer. Since Lua is the only way to interact with the filesystem, imza can monitor and control the model's behavior. I'd love to hear your feedback. Thanks Website: https://imza.run Source: https://github.com/umutsevdi/imza
Your workspaces follow you, not your agents. Every time you open a new window or switch AI agents, your AI gets amnesia. Hipo Hipo is a portable, governed "Brain" for your projects. Instead of dumping noisy chat logs into a vector DB, it stores your raw materials (evidence) alongside structured project memory (decisions, constraints, and methods). Connect one Brain to any agent, resolve context conflicts before overwriting, and take your workspace anywhere.
Botkubot is a trading desk where ten named agents screen US stocks, debate the setup, and a risk manager can veto. You watch the committee live, then keep execution Off, Confirm, or Auto. It reads dark-pool and institutional flow, not chat tips. Start on a $100k paper book; connect Webull, IBKR, or Moomoo for live orders. Heatmap, small-cap, and insider sit beside the book. Built for active traders who want a committee they can override. Not a broker. Not advice.
Sprouts Data is a hosted MCP server that gives AI agents access to about 45.7 million companies, 204 million people and 328 million person-to-company affiliations. Point your MCP client at one URL: search in plain English, find look-alike companies, look up records, map relationships and run multi-step research. Test keys cost zero credits, new workspaces get 1,000 free credits, and every billed response reports its cost.
Project URL Category Python Project Title Solaris Dev Shop: a local Python router that picks one installed skill for a task Project Solaris Dev Shop is a public MIT skill collection and local Python router. It picks one installed skill for a task and runs that skill command. It does not start an agent or call an API. Highlights It routes one local task to one installed skill file. It does not call an API, start an agent, or host a model. Example Code markdown or Videos
Introducing Tidy Desktop. An open source, local first design canvas and agentic development environment (ADE) in one platform. Run coding agents in your local projects, create and refine interfaces on the canvas, then attach a design to a coding thread to build it. Made for designers and engineers who want to move from an idea to working code in the same workspace. Sync to the Tidy web app in the cloud to collaborate with your teammates and enable multiplayer with the MCP.
DeskVNC brings VNC, RDP, and SSH together in one native app for Windows, macOS, and Linux. Manage machines from one library and let compatible AI agents access existing connections through MCP. 🤖 AI + human control: AI agents interact with sessions while you stay in control. 🖥️ One workspace: Access remote desktops and SSH terminals in one place. 🔐 Privacy-conscious: No account required; credentials stay in your OS keychain. 🌍 Free and open source: Explore and contribute to DeskVNC. globally
Hey HN, I'm Darin. You might know me from my work at Webflow (YC S13) and currently Ploy (YC P26). Sunlight is the way I imagined the Mac working before I got my 1st-gen MacBook Air in high school (2008). I had looked at a bunch of Apple videos of Mission Control (Exposé back then) and somehow decided it worked like an infinite canvas. I even told my mom about it! I guess it stuck with me. Windowing on the Mac is so good it's one of those "if it ain't broke don't fix it" things. And yet, it always felt lacking. So Sunlight reimagines it from first principles: - 355"+ virtual desktop - 120fps, fully native - Multi-touch interactions - Guides, grids and haptics - Minimap - ⌘Tab and Mission Control work as usual - Works with your Dock, widgets and desktop - Collision detection and magnetic windows - Tiling and saved layouts - Deeply customizable - ...and much more (including agent support) coming soon Free and open source, forever. Launch https://youtu.be/NSerIT8zRpw https://github.com/spacefarm-digital/sunlight
ThinkingOrb(.searching). That is the whole integration. Nine hand-tuned dotted loading indicators for AI and agent interfaces in SwiftUI: eight are real 3D forms, rotated, depth-shaded and z-sorted, and the ninth is a morphing outline. All drawn only in grayscale dots, so they sit quietly in any interface, light or dark. Every orb pauses itself offscreen, stays in phase with the others, and respects Reduce Motion. Swift 6, iOS 17+, macOS, tvOS, watchOS, and visionOS, Swift Package Manager, MIT.
Describe your business, project or team in plain words and orchit builds the workspace: modules, lists, forms, processes and AI agents. Free plan available.
Describe a process in plain language. Vrux generates the workspace structure and enables people and AI agents to execute work under server-enforced permissions, approval policies, and tenant-isolated data access. Built around a policy-driven execution layer, Vrux makes security and governance foundational—not an afterthought.
PostAxis is an agentic social media scheduler built for AI agents. Connect ChatGPT, Claude, Claude Code, Cursor or any MCP agent once, and it plans, generates and schedules your posts to Instagram, TikTok, YouTube Shorts, X (Twitter), LinkedIn, Facebook Pages, Threads and Telegram. PostAxis checks every post against each network’s rules, publishes on time, and shows everything in one calendar you can review and change. Includes team workspaces and a public REST API.
Keep deals, contacts, companies and meetings together across your products. Manage a visual sales pipeline, connect Gmail and Google Calendar, and work with your CRM from ChatGPT, Codex, Claude or the CLI using your workspace permissions. $9/month with a 7-day free trial.
Entagl gives business owners an AI Business Manager they message on WhatsApp or talk to in the Entagl mobile app. Ask it for an agent that answers Instagram, WhatsApp, TikTok, email and phone calls, and it builds one and keeps it updated. It also runs the rest of your day: checks orders and appointments, manages Meta ads, moderates comments, sends campaigns and sets reminders. No dashboards to learn, though the full web app is there when you want it. Works in 100+ languages.
KaoJai.ai now connects your customer support workspace to ChatGPT, Claude, and Codex through MCP. Search chats, find bookings, inspect Help Desk cases, and send authorized follow-ups. Combine an AI unified inbox with expandable Skills for support and booking. Live and Learn adds customer memory and proposes company knowledge for human review (Pilot Program). MCP requires Starter or higher; early-access availability applies.
A(I)mplified Analyst solves the challenges of manual data collection, spreadsheet updates, and fragmented financial information. Built for buy-side analysts, portfolio managers, and institutional investment teams, it combines AI-powered research workflows, structured financial data covering actuals, estimates and guidance, MCP integration, Excel-based modeling, and dedicated analyst expertise to accelerate research, improve efficiency, and support better-informed investment decisions.
Hey HN, I’m Abhishek. I'm building Opslane, a tool that finds reliability issues in your code. On every PR, it spins up your entire app and then tries to find weak spots that would break in production. https://youtu.be/47phxkdh6f0 Example: We tested Opslane on Lago (open-source billing) and found a bug where customers get double charged. Opslane made Stripe take the money and then return a 500. Lago marked the payment failed. A retry from the dashboard charged the customer again. https://github.com/getlago/lago-api/issues/6903 Why I built this I used to work on reliability at Robinhood. We used to run chaos testing in our staging environments: inject faults in various parts of the system and see what breaks. We found issues like Kafka or Redis being unavailable for a few seconds could take the whole app down. But that kind of testing was expensive. It needed a well maintained staging environment. Engineers needed to know what to test. Most teams never actually did it. Over the last year, coding agents have gone writing some of my code to almost all my code now. Teams are shipping way more code than they were 6 months ago. Code review tools read the diff, but a lot of reliability bugs aren't in the diff. They're in how your code behaves when Stripe, Redis or the network misbehaves. And e2e tests usually mock those services out and test the happy path. Agents have made this type of testing a lot cheaper. And we will see more of this (kinda like security scanning / testing) How it works A full copy of your app per PR: Postgres, Redis, Kafka, SQS, S3. Working copies of your third-party dependencies: Stripe, Slack, Gmail and more. Traffic goes through our proxy, which lets us inject failures. The agent picks what to test: It reads every PR and writes down invariants that need to hold (for e.g. a customer should never be charged twice). It then injects faults likely to break the invariants. Bugs we've found We ran Opslane on some popular open-source apps and here are some of the bugs we have found: 1/ Twenty: deleting a workspace while Stripe is failing locks everyone out, and billing keeps going. Twenty merged a fix. ( https://github.com/twentyhq/twenty/issues/28043 ) 2/ Dub: a restart in the middle of a payout paid a partner $240 for $120 owed. ( https://github.com/dubinc/dub.link/issues/4707 ) Full list: opslane.com/open-source Opslane is pretty early - we have a couple of early customers. We have found bugs in their system that their other code review tools missed. Would love to get feedback from folks and how they are seeing the reliability of their systems evolve over time with agents.
I built Seqora as a solo developer because I was tired of DBeaver and TablePlus, the tools I was using. None of them felt like modern tooling. DBeaver is mature, but it lacks customization and it’s slow. TablePlus puts too many limits on its free tier, like only allowing two tabs open at a time. What I wanted to do differently in Seqora was to let me visualize different objects, like indexes, partitions, etc. Another thing I found most tools lacked was a way to figure out what’s slowing down a complex query, so I built a visual EXPLAIN that shows where the time goes. I put the main focus on those two. The next thing was being able to work on a connection visually using diagrams, so I can see how things are connected and make changes by drag and drop. Once everything is done, I can review all the SQL that will run. I made sure the things you need for a daily driver are free, so there’s no limit on the number of queries, connections or tabs. The deep-dive parts, the object views, visual EXPLAIN and schema diagrams, are in Pro. Pro is currently $5.99/month or $49/year. It’s pre-1.0, currently at 0.4.6. It supports macOS (Apple Silicon) and Windows, and Linux is coming soon. It’s built with Tauri, Rust and Svelte. Most of the code was written with Claude Code and ChatGPT. I made the decisions and did the reviewing and testing. I’d love it if you tried it and told me what you don’t like so I can improve it, and also what you hate about your current workbench.
Your whole team, each with their own AI, working in one workspace with shared memory and data. Tell Claude, ChatGPT or any agent what you want and AlphaWeb hosts it: live pages, stores, funnels, apps and adaptive checkouts, subscriptions, upsells, payments built in, A/B testing 24/7 and so much more... Already on Shopify? Two-way sync, no migration.
https://github.com/liyu1981/my-printables Self-hosted, Printables-inspired 3D model library. One Go binary embeds the API, React SPA, migrations, and the administrative CLI. Finally I built this printables clone for my nas to manage my 3d print models better. With Pi-in-go agent + deepseek v4.1's help. It is pretty small, even with docker image is <30MB. If you are finding another small fast management app like me, may be worth a try.
Run Claude Code, Codex, Gemini CLI, Copilot, Cursor and 13 more coding agents side by side. Manage real terminals, multi-agent workflows, MCP servers, approvals, code reviews and token usage from one desktop app for macOS, Windows and Linux.
Lumvise keeps explanations, decisions and reports connected to code, documents and image regions. Explore project relationships in a visual workspace and give your AI coding tools reusable context through a local MCP server.
Generate images and videos from prompts or reference media. Use the browser workspace, imgs-ai CLI, or Agent Skills with one account and credit balance. Compare model settings and credit costs before submitting, then download the result. Portrait series, ad workflows, and motion control are available alongside the core image and video tools.
Fly is an AI agent for Google Business Profile management. Every 4 hours it answers your reviews and keeps your posts and profile current. 14 days free.
Hi HN. Greg here. I've been a full stack engineer for 20 years. Now all I do is shuffle messages between users, my agent fleet, our dev pipeline.. back and forth. I miss coding, solving problems, reasoning, and having an understanding and a mental model of all the work I'm juggling. But this is the job now, and there's no going back. I don't exactly feel like a 10x engineer yet, but I am for sure a 10-tab engineer. I built (er, Claude built) Shufler to lean into my new reality. If the job is basically to shuffle things through a pipeline, why not have it be more fun. Each row on the 3D gameboard is one of your existing terminal sessions. The columns are the steps your work moves through: Brainstorm, Plan, Build, QA, Review, Merge, Deploy. Your shipped PRs get stored in a warehouse/depot. The main things flowing across the board are your issues and PRs: each one rides along its session/row as it moves through review, CI and merge, and anything waiting on you turns red. I tend to manage several PRs within each Claude/Codex session, and this makes it easier for me to hold onto a mental model of where everything is. It's also made daily standups much easier to read-out. I created a few skins/themes like a casino, a theme park, sky islands, a starship and a factory, because.. of course. MacOS, works with Claude Code and Codex CLI, and cmux and iTerm (tmux should work, but I haven't tested it). It doesn't try to replace anything you already use.. just makes the orchestration more fun. You can still shift focus over to your terminal sessions when needed, use your existing skills, MCP servers, etc. There's a 3D library-building in each skin where you can specify your markdown/context folders or files, and then drag and drop to check them out by your rows/sessions. I tried to be thoughtful on security, following patterns that I consider at work. No telemetry, and the only outside calls are your own gh calls to GitHub. Daemon only listens on localhost, and every action shows its command before it runs. MCP server is opt-in, and sending to other sessions is off by default; if you turn it on, every send is a preview plus a separate confirm you approve. Details are in the README's #safety-and-privacy, and the MCP threat model (including what it doesn't protect against) is in docs/MCP.md. To report a security issue privately (or contributions to improve), see SECURITY.md. with mock data, nothing to install at https://shufler.app at https://github.com/jgrichardson/shufler (MIT)
Gear is an open-source framework for recursive self-improvement of AI agent harnesses (prompts, tools, workflows, and context management). Built toward a scikit-learn for RSI, its modular architecture lets developers implement, compare, and extend optimization algorithms. With Gear, GPT 5.6 Luna reaches GPT 6 Astra-level performance: 88.9% vs. Astra + Codex’s 84.1% on AutomationBench’s public Marketing tasks.
Siteglade 2.0 is an autonomous AI agent to build apps, games and websites; create slides and spreadsheets; generate images, video and audio; create content; and automatically edit videos. Give it a task and get editable results in one workspace.
Kodl now brings four specialized AI agents into your team workspace. Delegate a task to the Kodl Agent, Writer, Planner or Coordinator, review contextual proposals and approve changes before they are applied. Track runs, sub-agents and estimated costs in one view. Alongside Kanban, sprints, chat and docs, Kodl now includes desktop apps, offline support and sprint forecasts. Built for teams that want AI assistance while staying in control.
一键切换 AI 编程助手的模型。这是一款用 Go 开发的 AI 编程助手模型管理工具，让 Claude Code 用上 Kimi、Codex 用上 DeepSeek。它通过本地网关转换 OpenAI、Anthropic 和 Gemini 的接口格式，支持多种编程助手和模型服务商，还能把订阅共享给其他助手使用，额度用完后自动切换账号。
An AI code editor built on VS Code with completions, codebase chat, an agent that edits across files, Multi-Agent, Feature Tree and browser QA. Works with Claude, GPT, Gemini, local models and your own API keys.
Synapse is a free, open-source desktop AI workspace that brings local Ollama models and cloud AI providers together. Chat with persistent memory, use MCP tools and custom skills, manage context automatically, and build interactive experiences inside conversations.
Project URL Category JS Project Title In-repo delivery board: stages, handoffs, soft WIP, weekly report, Timeline Project Open-source delivery board that stores stages, owners, handoffs, and soft WIP limits in a git-tracked file. Includes a weekly Markdown client report and a local kanban plus calendar Timeline UI. Runs standalone via npx or as a DeepSeek Harness plugin. Aimed at keeping delivery context next to the code rather than only in SaaS boards. Highlights Delivery state lives in the (delivery.json) and is reviewable in PRs Automatic handoff audit when cards change stage; soft WIP limits warn without blocking Weekly Markdown report (shipped / handoffs / risks) plus local editable board and calendar Timeline Standalone CLI: npx jerryxff26-alt/dsh-delivery-board — no SaaS account required Example Code bash npx jerryxff26-alt/dsh-delivery-board init '{"customer":"ACME","template":"governance"}' npx jerryxff26-alt/dsh-delivery-board card '{"title":"API integration","stage":"analyze","owner":"Ada"}' npx jerryxff26-alt/dsh-delivery-board open npx jerryxff26-alt/dsh-delivery-board weekly or Videos GIF in
A VS Code-based workspace uniting an AI coding agent with specialized agents for research, planning, and writing. Build and test code, then review changes with a second model in the same session. Use your Claude or ChatGPT plan, or an API key. Free to start on macOS.
v2.2 turns our widget into a full WhatsApp Business Suite! 👥 Multi-Agent Teams: Add dedicated members (Sales, Support) with custom name, job title, and dedicated phone number. 📱 Desktop QR Code: Scan-to-chat with real-time text sync. ⏰ Smart Business Hours: Operating hours & away notices. Perfect for agencies & businesses. Get enterprise features without $10–$30/mo fees - still 100% free, self-hosted, 0 cookies & GDPR-Friendly!
Raq.com started as an internal tool builder. It's now a toolkit for the AI agent you already use. Connect Claude, ChatGPT or any MCP agent once and it works across 75+ business tools, from CRM and task boards to quotes with e-sign and card deposits, forms, automations and AI image and video. Everything it makes is saved in one workspace your team shares, and you can build and host your own custom tools too.
Free desktop app for API work on localhost: *.localhost proxying with capture, a client for REST/GraphQL/gRPC/SOAP/WebSocket/MCP & more, proxy-level mocks, git-synced workspaces, visual flows, a local mail inbox, and an agent-ready CLI. Windows, macOS, Linux.
Dock gives each AI agent its own Linux VM with a persistent disk. Create it, run commands, stop it (the disk stays, compute is freed), resume it with the same files, or branch it into copies so several agents can try fixes in parallel. Run docks locally with no account (QEMU on Linux or Windows), or self-host the open source control plane with one command. Hosts run Firecracker microVMs or gVisor sandboxes and only connect outbound. CLI plus TypeScript, Python and Go SDKs.
FYN is personal finance with one ledger for you and your AI tools. Link banks once on Pro. FYN categorizes transactions, keeps budgets and bills current, and turns receipts into line items. Ask FYN in-app, or connect Claude, ChatGPT, Grok Bot or any MCP client for a read-only view. FYN never moves money. Free forever: receipts, tap-to-pay and email ingest, Ask FYN. Pro: Plaid bank sync, higher limits. Households share one workspace. iOS, Android, web.
KorvixAI is an AI-powered workspace built for founders, startups, and growing teams. Bring your projects, tasks, AI agents, and connected tools into one place. Ask questions about your projects, understand what has changed, identify blockers, and keep your team aligned. Instead of switching between multiple tools to understand what's happening, KorvixAI helps you turn scattered information into actionable insights. Build, organize, and move forward with more clarity.
WP AI Manager is an AI agent inside your WordPress admin. Ask in plain language and it edits Elementor and block editor pages, writes SEO, runs WooCommerce and 12 playbooks. Approve big changes, undo any. BYOK MCP for Claude and Cursor & more.
A local-first desktop workspace for persistent AI teammates. Run Codex, Claude, and Grok with dedicated workspaces, task queues, file sharing, browser control, and agent-to-agent collaboration.
Your whole team, one flat price. Pro is $35 a month for the whole workspace: no per-seat fees, unlimited people and documents. Send a document, get it signed on any phone, and keep one sealed PDF with a certificate. Signers can pay while they sign, straight into your own Stripe account, and Pro adds no fee. Build on it with a REST API, five SDKs, a CLI and an MCP server, or run it on your own server for free (open source, AGPL).
Veynod is a shared blackboard for multi-agent teams over MCP and REST. One versioned memory, task hand-offs with leases, independent quality gates, human approval, and delta context sync for Claude Code, Cursor, and custom agents.
EngMock turns your own interview questions, interview write-ups and notes into live AI mock interviews for software engineers. Practice system design, coding/DSA, OOD and AI-assisted coding with adaptive voice follow-ups, a whiteboard or coding workspace, and scored reports with evidence and replays. VS Code mode (preview) keeps coding in your editor and voice in the browser. Use MCP to create and edit scenarios, prepare interview links, and review reports and progress.
Spark is a predictive cognitive engine that enables you to dr strange your most crucial decisions enter any counterpart and run hundreds of probabilistic simulations our multi-agent models track their thoughts behind the conversation
Maxtkn is a desktop workspace where teams of AI agents plan, write, test and review real projects on your machine. They check their own work, can keep going while you are away, and you stay in control. No code reading required.
Hi HN, I'm Alexander. Yes, this is another agent harness. Here is why I built one anyway. I was engineer #2 at Browser Use, where I built our agent harness and the evals behind it, including BU Bench, which became a default benchmark for browser agents. I left in September to build Mainplane. The problem: local agents die with your laptop, and cloud agents can't reach your work. Many cloud platforms ask you to "select a repository", but my work is not that simple. I work across a desktop, a Mac mini and a laptop, and much of it is not in git. So I loaded Ubuntu on my old 2012 desktop and made it my Mainplane server. It has run for four weeks at a load average of 0.02, because the agents' tools run on other machines. How it works: it is a control plane architecture. The server runs the harness. It holds your API keys and every session, makes the LLM calls, and routes each tool call to a worker. The workers are your other machines, connected over a built-in private WireGuard network. A bash command runs in the worker's terminal, not on the server. Shared drives let projects move across machines. The agent works on your machines just like you would, but its state lives on the server, and your keys never leave it. Some design choices: - Every session is one append-only file. This is the agent state, and it is easily readable. If something breaks, you can resume it from the file. Observability comes for free: agent traces are just these state files. - Small by design. The system prompt is 3k tokens, and there are just two kinds of tools: shell and file (read, write, edit). At Browser Use, I learned the bitter lesson and found frontier models did better when I deleted all our helper functions. So I made the same bet here: bash is all you need. - No compaction. When a session fills up, /continue starts a new one that greps the previous state file, retrieving the context it needs, instead of reading a lossy summary. A /compact on a 400k-token session takes a while to write its summary. A /continue into a brand new session starts at once. - No permission prompts. A hyperintelligent misaligned agent WILL find a way around a permission system. The better strategy is giving the agent full unbounded access to a local computer, and only putting what you trust the agent with on that computer. - Why Go. WireGuard is written in Go, so the network compiles right into a 20 MB binary. Go is made for production servers, LLMs write it well, and the simplicity of Go matches how I like to build. Mainplane works with a Claude or ChatGPT subscription on the regular usage limits, or any API key. I would love your feedback, especially brutal and honest feedback and tasks that the harness cannot do. I'll be here all day to answer questions.
DataVo is a voice-first AI Agent designed to revolutionize business data management and table generation. Unlike traditional spreadsheets, DataVo lets you build, update, and manage dynamic tables using simple voice commands or text. Key Features: 🎙️ Voice-to-Table: Instant table creation via speech. 📄 Camera OCR: Scan documents and PDFs directly into databases. 📊 Easy Export: Seamlessly export to Excel and PDF. Built for entrepreneurs and SMBs looking for a faster, smarter workspace.
ProScouter is an AI Powered, NIL Compliant sports recruiting ecosystem. From Athletes, coaches & Scouts to Agents & Brands, not just recruiting — full Athlete Career Management!
NINX is an AI workspace for getting things done using on-device models. Run models on your device or bring your own API key. Talk to your AI, connect apps, code with Codex, automate recurring tasks, and create videos in Studio. Capture conversations in Notes, collaborate in Rooms, and take your workflows mobile with Ningenie.
Choosing scheduling, dispatch, and customer management software shouldn’t mean hours of research and sales calls. Field Agent Stack compares the leading
Build AI agents in plain language, search your knowledge and automate mailbox workflows. Review drafts, tasks and Excel outputs in your dedicated DigiRAG workspace.
OneSpace puts Claude, GPT, Gemini and Grok in one app, connected to Gmail, Calendar, Slack, GitHub and more than 50 apps. Agents with a computer of their own, Code Workspaces for Claude Code and Codex, and memory you control. Free to start, from $8 a month.
Hey HN! I shared Optio here back in March. Originally it was focused on getting swarms of coding agents (claude code/codex) to drive PRs towards a merge by automatically resuming them on CI failures or PR comments. Since then, I've reworked the project to be a general platform for running any kind of AI workflow on your infra by allowing users to configure each component of a possible workflow: When: On demand, a cron schedule, or triggered by external events such as a webhook, slack message, ticket (jira/linear/gh), pagerduty/datadog/alertsmanager/pylon/sentry. Where: In a k8s pod or any machine you have installed the optio daemon on (I use my laptop). Who: Any harness you prefer (Claude Code, Codex, Gemini, Pi, etc.) What/Why: You can format parameters from the triggers directly into the prompts and then configure if the agent should exit, be resumed automatically, or be persistent. You can either define workflows in the web ui or as yaml files that get synced to the orchestrator (ai config-as-code). I've also built native iOS and Android apps so you can connect to your cluster and create/manage agents remotely. The marketing page is at https://optio.host and the code is still open source at https://github.com/jonwiggins/optio Would love feedback or any thoughts you might have on how I could make it better!
GSC Magic is a hosted MCP server that gives Claude, ChatGPT, Cursor and any MCP client your real Search Console, Bing, GA4 and Tag Manager data. Sign in with Google, paste one URL, ask. 77 tools, ready-made SEO reports, read-only by default. Free plan.
ZetroQ unifies conversational AI and sales execution. Deploy intelligent AI chat widgets trained on your docs in 2 minutes. Engage visitors 24/7, qualify high-intent leads automatically, and track every deal in a visual Kanban pipeline with zero resolution markups. Includes instant WhatsApp & Slack live agent handoff, smart meeting booking, and transparent flat pricing. Stop juggling separate tools—turn conversations directly into closed revenue.
Hi, I want to share with you my chrome extension: Tabverse, as it is now passed the reveiw of Chrome Web Store and live at: https://chromewebstore.google.com/detail/tabverse/lffblcippn... Tabverse is a local first workona like chrome extension for managing tabs, with its source open at https://www.github.com/liyu1981/tabverse . In essential it has the core functions workona has, but can operate totally locally, which means it will not need an account nor subscription. The only limit is your local storage spaces so that you can have as many spaces(I call tabverse) as you can. It is open source, so not just your data stays with you, and the tool itself will stay with you in future. Beyond the normal workona features (persisted workspace, load/reload/import/export, note/bookmark/history tools), there are features does require a server. Features like backup/sync, global search on all tabverses, and future collaboration (not yet done), can only be possible if there is a server. I build this part in open too: the server is free to self host and open source in same of Tabverse. The tabverse's idea was with me few years ago while I was using Workona and was frustrated with its limitation on free tier (remember was only 5 workspaces), and the missing features of managing multiple workspaces at the same time. Tabverse takes the idea of Workona, and develop further: each window with a Tabverse tab is a workspace, all stored in local storage, and multi windows can have multi Tabverses same time, and can switch fast. There can even be window without Tabverse, so besides work, personal stuff or entertainment will have place to go. As I build this alone, in the middle, almost give up on this project, and luckily AI agents now is there: not only I have a good helper, but also I have a partner I can discuss a bit. So this time the first version starts with v0.7.2. But AI agent can never replace the real need from human on what should be built and what works better, so I want to share with you and listen to your feedbacks early. Please give it a try, and every feedback to me is a gift. Besides the self-hosted option, I host a server at https://tabverse.liyu1981.xyz (yes, the same website of intro and docs), but is invitation only. If you want to help me to test in this early stage, you can login with Google (the only social login I configured :)), and request an invitation there. I will act as soon as I find your request :). But do not worry at all if you only want to use Tabverse locally without a server -- that is the first thing when I was building it. In current version there are also AI features built in, and again do not worry as the AI features is using Chrome's Prompt API, which is totally local, with Gemini Nano (first time will need to download it automatically), nothing send to a server, and you can always turn this on of off in settings. Morden computers with decent memory should work well, but some older computer may suffer (so please turn off). And it is Chrome only. (Honestly, Tabverse currently only support Google Chrome, but not other Chrome based browsers).
Jobmate AI takes the busywork of job hunting off your plate so your energy goes into landing interviews. An AI agent auto-applies for you, autofills any application form from your profile and answers the open-ended questions. Find fresh roles from across the web, tailor your resume and cover letter to each one, reach the recruiters and hiring managers behind it, and track every application and interview in one place. Free to start on Chrome and Firefox.
A free alternative to Postman, Insomnia and Bruno that needs no account. REST, GraphQL, gRPC, WebSocket, Socket.IO and MQTT in one app, with collections saved as plain files you can commit. The desktop app, web app and CLI run the same Go engine, so a CI run matches what you saw while testing. Secrets stay in your own manager, and an MCP server lets coding agents send saved requests with values redacted. MIT licensed.
I have built an indie hacker project; my main flow was: 1. chatting with Claud Code about the general plan 2. assigning slices of work to other worker agents like Pi + DeepSeek 4.1 Flash 3. building in parallel 4. Claud Code reviews when done, runs tests, and merges after I validate It worked, but with a lot of glue in the middle, so I built radian + arc into the same binary. Radian: a compact, pragmatic agent that has enough tooling to solve a small coding task end to end; it does not try to be a plugin platform. You can still extend it via MCP, skills, or hooks to extend its capabilities. I think plugins are great, but a lot of them are for humans. I'm trying to remove humans from the loop. Humans are at the start and end of the loop. arc: built into the radian binary; * it can get work sent from another agent * assign work items to concurrent headless radian agents * automatically review, CICD, integrate locally * humans can still be in the loop but not at the agent conversation or code review level, but at the work item approval/review level. * shows all of the above in a plan view or Kanban board in TUI. I have been heavily dogfooding, and Radian + arc basically built themselves in the last couple of weeks, with me just being a product manager/scrum master and qa. radian + arc are open source at https://github.com/hisea/radian What do you think about this approach? Looking for ideas to make Radian better or fit more scenarios.
Maki is a Python framework for building multi-agent LLM applications: multiple LLM backends, an agent system, a plugin system, a workflow engine, and a distributed layer for serving agents over HTTP.
ANKITA turns your Windows desktop into an AI workspace. Delegate to subagents and follow their progress, tool calls and results. Work with files and code, control the browser and desktop, connect MCP tools and plugins, and keep projects, memory and scheduled tasks together. Use your ChatGPT account or choose another provider. Includes a floating companion, reusable skills and a terminal CLI. Free and open source; provider costs and limits apply.
Xunbao helps Chinese-speaking beginners explore keyword opportunities. Enter a topic, start a radar task, then continue it in your own AI agent. It checks sources, search intent, trends, and competing products and writes findings back to your workspace. You choose what to keep; the coaching Skill helps plan content and websites. Chinese-language; a compatible AI agent is required.
tool4seller is an all-in-one Amazon seller platform by TAPCASH INC., serving sellers since 2017. It turns sales, fees, ad spend and inventory into per-SKU profit dashboards — profit & sales analytics, Amazon PPC optimization, product & keyword research, FBA inventory management and AI-assisted listing optimization, on web, iOS and Android, across 22 marketplaces. New: its MCP integration lets sellers query diagnostics, profit, advertising and inventory from AI tools like ChatGPT and Claude.
An orchestrator splits your work across Claude Code and Codex agents, each in its own git worktree. A reviewer checks the result, a built-in browser lets agents test their own work, and every question lands in one place. Uses the plans you already have. Free for 14 days.
A terminal multiplexer built for people running several coding agents at once. Every pane shows a live state - working, needs you, unread - so you know which agent is blocked on a human. Like tmux, agents and dev servers keep running when you detach. Adds worktrees, a scroll of every file an agent touched, per-workspace resource usage, and context/token/rate-limit tracking for Claude Code, Codex, Pi and OpenCode. macOS and Linux (Apple Silicon/amd64), one curl install.
Hey HN! As an avid user of cmux ( https://cmux.com/ ), I wanted a way to control terminal and agent sessions from my Android phone, so I built Muxer. The app talks to a tiny relay over HTTPS, that then talks to cmux through its local socket, and gives you to ability to: - Answer agent permission requests, questions and plans from a notification - Reply to Claude Code, Codex and Pi chat sessions with text, voice, @ file mentions and photos - Receive all cmux notification, with inline replies, bubbles and background delivery. - Use a live terminal with sticky modifier keys and local scrollback - Share text and links from any app to an agent - Organize workspaces - Manage cmux Cloud VMs and automations - Lock the app with your fingerprint, face or screen lock Enjoy, and let me know what you think!
Most ADEs bring the browser into the IDE. tabsh takes the opposite approach: bring coding sessions to your browser, where your work already happens. It's a small Rust daemon that puts all your sessions across projects on one Kanban board/list, with status updates via agent hooks. Use real terminals or chat panels with Claude Code, Codex, Cursor CLI, OpenCode, and more. Free, MIT-licensed, macOS/Linux.
At Researchly ( https://www.researchly.at ) we automate market and competitive analysis. We learned that on-the-fly web search through AI agents isn't reliable enough for consistent, in-depth work. Existing data providers such as PitchBook or Crunchbase are either too expensive or lack the data we need: operational signals such as management changes or new partnerships, for DACH. Furthermore, search tools such as Exa tend to be probabilistic. What they return depends on the model and on SEO rankings, so two runs of the same query can give you two different answers. So we built our own search layer: several providers (Exa, Linkup, Tavily, Parallel), allow/deny lists, source rankings (we once caught ourselves citing our own blog posts), and checks whether an empty result means "nothing there" or "out of budget". It works, but: it's slow, expensive, non-deterministic & we kept redoing the same research for different clients (which makes it very un-economic). So we started building the data layer itself. Step one was Firmendaten (300k companies from the Austrian register; shared here last week https://news.ycombinator.com/item?id=50142669 ). Relational data like that is already a huge improvement, but what we really need is a graph, as people ask "W" questions: who does what with whom where and when. This is our first attempt at it. For now, it just connects who partners with whom and company groups. (Tick "Beziehungen 2. Ebene" to see every partner and person) It's small (a few dozen robotics companies) but you can already see how complex the graph gets & it serves as a good PoC for us. We had wanted to build this for a long time, and it turned out to be far harder than we expected. One thing that sounds trivial but was particularly hard: finding the right website for a company. You can buy that data. There are enrichment APIs that return a company's website. But even if they cover Austrian companies, how do you know which company they matched? There is no worldwide unique company identifier. And if you do it yourself: how do you know that this website really belongs to this company? You have to validate every single match (e. g. through the imprint on a company's website in Austria). There are quite a few more challenges involved, but we're happy with where this first, admittedly small, result has landed. Feedback very welcome – especially on which relationships would make a graph like this useful for you. Feedback welcome!
