Everything that shipped

OpenAI Chat Completions API with tool use over tencent/Hy3

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

HelloSun

Found on

Hugging Face Spaces, 3d ago

Full page → Visit huggingface.co ↗

Hebrew/English chat with DictaLM 3.0 Nemotron 12B

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

ofier80

Found on

Hugging Face Spaces, 3d ago

Full page → Visit huggingface.co ↗

Hebrew/English reasoning chat with DictaLM 3.0 24B

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

ofier80

Found on

Hugging Face Spaces, 3d ago

Full page → Visit huggingface.co ↗

Ready-to-run AI agent templates (n8n + code) for indie builders, solopreneurs, and vibe-coders, plus an honest directory of the AI tools those templates run on.

Built with

creator says: AI

How we know

Its maker says so. Not something we can check.

Found on

One's Vibe, 5d ago

Full page → Visit shipreadyagents.com ↗

Financial market context for AI agents: macro, rates, bonds, FX, commodities, companies and Bitcoin. One API call returns a briefing with the reasoning already in it.

Built with

creator says: AI

How we know

Its maker says so. Not something we can check.

Found on

One's Vibe, 5d ago

Full page → Visit prereason.com ↗

Bring Claude Code and Codex to where your team already works. Merlin runs them on your team's own machines and puts every run in the open where anyone can steer it.

Built with

creator says: AI

How we know

Its maker says so. Not something we can check.

Found on

One's Vibe, 5d ago

Full page → Visit usemerlin.ai ↗

Stop Sequence is a daily webcomic written and drawn by an AI agent. Other agents can steer it by leaving comments and ideas, and everything rejected is public.

Built with

creator says: AI

How we know

Its maker says so. Not something we can check.

Found on

One's Vibe, 5d ago

Full page → Visit stop-sequence.com ↗

Eevo helps your AI agents understand what follows from the decisions they make, weighing each option's consequences for everyone it affects.

Built with

creator says: AI

How we know

Its maker says so. Not something we can check.

Found on

One's Vibe, 5d ago

Full page → Visit uprightproject.com ↗

Automate your repetitive calls. Ask Claude or ChatGPT to call suppliers for order status, delivery dates and vendor updates from your verified number.

Built with

creator says: AI

How we know

Its maker says so. Not something we can check.

Found on

One's Vibe, 6d ago

Full page → Visit patchmcp.com ↗

Völundr turns your idea into a live Docker application in minutes. Multi-agent AI pipeline: Analyst, Architect, Developer, Tester — deployed and owned by you. No lock-in.

Built with

creator says: AI

How we know

Its maker says so. Not something we can check.

Found on

One's Vibe, 6d ago

Full page → Visit volundr.dev ↗

Push notifications from any AI agent, plus questions you can answer from your phone. Works with Claude Code, Codex, Cursor and anything with a shell. Free to start, open source and

Built with

creator says: AI

How we know

Its maker says so. Not something we can check.

Found on

One's Vibe, 6d ago

Full page → Visit rply.sh ↗

Find skills, MCP servers, hooks, configurations, commands, plugins, and agents for Claude Code. Search by name or describe your task.

Built with

creator says: AI

How we know

Its maker says so. Not something we can check.

Found on

One's Vibe, 6d ago

Full page → Visit claudecode.directory ↗

A platform to build, run, and use AI agents through search. Agents run in a controlled runtime on your own agent servers, with one conversation carrying context between them.

Built with

creator says: AI

How we know

Its maker says so. Not something we can check.

Found on

One's Vibe, 6d ago

Full page → Visit search2o.com ↗

Embed problems.dev in your MCP server or CLI to capture tool failures, publish them to an agent status page, and return known fixes to agents.

Built with

creator says: AI

How we know

Its maker says so. Not something we can check.

Found on

One's Vibe, 6d ago

Full page → Visit problems.dev ↗

GPU sessions your coding agent starts, uses and stops from the terminal. Files persist between runs; GPUs are billed by the second only while they run.

Built with

creator says: AI

How we know

Its maker says so. Not something we can check.

Found on

One's Vibe, 6d ago

Full page → Visit supercomputer.sh ↗

A free, open-source Stardock Fences alternative for Windows 11. Group desktop icons into glass fences, sort new files automatically, switch projects with tabs, or let your AI agent set it all up.

Built with

creator says: Claude

How we know

Its maker says so. Not something we can check.

Found on

Shared by their makers, 10d ago

Full page → Visit pecofence.jiang.jp ↗

A team of AI agents that finishes the work. Perch plans the job, runs helper agents in parallel, checks their findings and cites every claim, on the web, on your desktop and in your terminal.

Built with

creator says: AI

How we know

Its maker says so. Not something we can check.

Found on

Shared by their makers, 10d ago

Full page → Visit perchai.app ↗

Pankaj T Sharma — DevOps, platform, and SRE profile

Built with

Cursor

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Cursor on GitHub, 10d ago

Full page → Visit panks028.github.io ↗

orbitproxy 产品文档：API 网关、MCP 网关、流量策略与客户端使用指南

Built with

Cursor

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Cursor on GitHub, 10d ago

Full page → Visit docs.orbitproxy.cc ↗

AI agents rewriting Supabase as a single Rust binary, judged against the real stack. Unofficial experiment, built in public.

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Cursor on GitHub, 10d ago

Full page → Visit megabase.sh ↗

Give AI agents the use of your secrets without the values: named secrets in the OS keyring, with Vault as a replica, injected into a command and redacted from its output. CLI + MCP + guard hook.

Built with

creator says: Claude

How we know

Its maker says so. Not something we can check.

Found on

Shared by their makers, 10d ago

Full page → Visit munhq.com ↗

Drop Cowboy sample CRM, Building Blocks examples, REST clients, and agent skills.

Built with

Cursor

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Cursor on GitHub, 10d ago

Full page → Visit dropcowboy.com ↗

c3nsor Tech Employee Playbook: interactive developer onboarding

Built with

Cursor

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Cursor on GitHub, 11d ago

Full page → Visit michaelpetersonn.github.io ↗

A Claude Code plugin that picks the model and the reasoning effort for every prompt, and counts down how long the prompt cache stays warm.

Built with

creator says: Claude

How we know

Its maker says so. Not something we can check.

Found on

Shared by their makers, 11d ago

Full page → Visit heycubit.github.io ↗

Peekos IDE — AI code editor for Android. Coding agent, Linux terminal, LSP, and syntax highlighting. Download the APK. Редактор кода с ИИ для Android.

Built with

Cursor

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Cursor on GitHub, 11d ago

Full page → Visit peeko.online ↗

Give Winskel a coding task. It runs Claude Code and Codex on the parts each handles, in parallel when useful, and brings everything into one workflow.

Built with

creator says: Claude

How we know

Its maker says so. Not something we can check.

Found on

Shared by their makers, 11d ago

Full page → Visit winskel.com ↗

鲲鹏有声：原生 macOS 声音克隆应用，录 10 秒即可用你的声音朗读任何文字，完全本地运行

Built with

Cursor

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Cursor on GitHub, 11d ago

Full page → Visit voice.kunpeng.si ↗

Connect your application to a shared model API. Manage access, inspect usage, and purchase credits in one workspace.

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Found on

Shared by their makers, 11d ago

Full page → Visit routr.cloud ↗

Agenthub: local-first home Agent Hub with shared context, per-identity workspaces, OAuth MCP, and human-approved GitHub publish.

Built with

Cursor

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Cursor on GitHub, 11d ago

Full page → Visit agenthub.sunny99.win ↗

A free, open-source macOS IDE for working across several git repositories at once, with AI agents that can edit but never commit or push.

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Found on

Shared by their makers, 11d ago

Full page → Visit intelyide.ferenc-farkas.workers.dev ↗

WooCommerce payment method for the Voybit crypto payment gateway.

Built with

Cursor

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Cursor on GitHub, 12d ago

Full page → Visit voybit.com ↗

Claude Code manages prompt caching automatically. See why a model switch triggers a slow uncached turn, what /compact costs, why CLAUDE.md edits don't apply mid-session, and how to check your cache hit rate.

Built with

creator says: ChatGPT, Claude

How we know

Its maker says so. Not something we can check.

Found on

Shared by their makers, 12d ago

Full page → Visit code.claude.com ↗

A live architecture map your coding agent has to respect. Keeps vibe-coded apps from turning into spaghetti.

Built with

creator says: Claude

How we know

Its maker says so. Not something we can check.

Found on

Shared by their makers, 12d ago

Full page → Visit orest-z.github.io ↗

Compress finished turns, hide dead ends, and keep the cache warm. Conversations run longer and the model stays focused.

Built with

creator says: Claude

How we know

Its maker says so. Not something we can check.

Found on

Shared by their makers, 12d ago

Full page → Visit sharpturns.ai ↗

Keep your coding agent. Add recoverable context compression, measure token usage, and find practical guides for reducing AI agent costs.

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Found on

Shared by their makers, 12d ago

Full page → Visit caveman.so ↗

Memtrace gives coding agents shared structural memory: one graph for code, time, and fleet coordination across Claude Code, Cursor, and more.

Built with

creator says: Claude

How we know

Its maker says so. Not something we can check.

Found on

Shared by their makers, 12d ago

Full page → Visit memtrace.io ↗