Everything that shipped
New work across every platform. Open a row for the details, or the title for its own page.
FinBridge
Query Korean and U.S. stock market data through an MCP server for AI agents.
creator says: AI
One's Vibe
30 Aug 2026
TokenTrace
Monitor, analyze, and control your OpenAI, Anthropic, and Gemini API spend in one place.
creator says: AI
One's Vibe
30 Aug 2026
Working Machines
Connects AI agents like Claude and ChatGPT to 1,400+ apps and 15,000+ actions through a secure integration layer.
creator says: AI
One's Vibe
30 Aug 2026
VT Code
Write code in your browser with WebMCP support and an AI-powered terminal coding agent.
creator says: AI
One's Vibe
29 Aug 2026
AI-Assisted Development
Sports intelligence API for AI agents, instantly usable without signup using provided prompts.
creator says: AI
One's Vibe
29 Aug 2026
Code Knowledge Graph MCP Server for AI Agents
Create a live code knowledge graph from GitHub repos accessible to AI agents over MCP.
creator says: AI
One's Vibe
29 Aug 2026
ClearBeez
Validate emails, drop bad data, and boost deliverability with ClearBeez. Real-time API, bulk cleaning, AI risk scoring, and MCP for AI agents.
creator says: AI
One's Vibe
29 Aug 2026
Code Tools Studio
Free browser tools for formatting code, minifying files, testing regex patterns, and merging PDFs.
creator says: AI
One's Vibe
29 Aug 2026
OpenLLM
Route LLM API calls across multiple providers (Anthropic, OpenAI, Kimi, AWS Bedrock) with unified observability.
creator says: AI
One's Vibe
29 Aug 2026
Makra
Makra is an agentic web scraper that serves real-time structured data from the open web at the cost of a vector search.
creator says: AI
One's Vibe
29 Aug 2026
Vybe Collect
Accept payments from AI agents and humans via a catalog with HTTP 402 settlement, no merchant account needed.
creator says: AI
One's Vibe
28 Aug 2026
Dev3000
Captures your web app's complete development timeline - server logs, browser events, console messages, network requests, and automatic screenshots - in a unified, timestamped feed for AI debugging.
Claude Code
Well-known on GitHub
2 Sep 2025
Captures your web app's complete development timeline - server logs, browser events, console messages, network requests, and automatic screenshots - in a unified, timestamped feed for AI debugging.
- 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
- Well-known on GitHub, 2 Sep 2025
CADAM
CADAM is the open source text-to-CAD web application
Claude Code
Well-known on GitHub
1 Sep 2025
Claude Mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Claude Code
Well-known on GitHub
31 Aug 2025
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
- 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
- Well-known on GitHub, 31 Aug 2025
ralph-claude-code
Autonomous AI development loop for Claude Code with intelligent exit detection
Claude Code
Well-known on GitHub
27 Aug 2025
claude-agent-acp
Use Claude Agent SDK from any ACP client
Claude Code
Well-known on GitHub
27 Aug 2025
NeMo Gym
Evaluate and improve models and agents using environments
Claude Code
Well-known on GitHub
25 Aug 2025
Ccpm
Project management skill system for Agents that uses GitHub Issues and Git worktrees for parallel agent execution.
Claude Code
Well-known on GitHub
18 Aug 2025
Project management skill system for Agents that uses GitHub Issues and Git worktrees for parallel agent execution.
- 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
- Well-known on GitHub, 18 Aug 2025
NeuroSploit
NeuroSploit is an advanced, AI-powered penetration testing framework designed to automate and augment various aspects of offensive security operations.
Claude Code
Well-known on GitHub
17 Aug 2025
NeuroSploit is an advanced, AI-powered penetration testing framework designed to automate and augment various aspects of offensive security operations.
- 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
- Well-known on GitHub, 17 Aug 2025
CodeGraphContext
An MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants.
Claude Code
Well-known on GitHub
16 Aug 2025
An MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants.
- 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
- Well-known on GitHub, 16 Aug 2025
MemMachine
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.
Claude Code
Well-known on GitHub
15 Aug 2025
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.
- 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
- Well-known on GitHub, 15 Aug 2025
Youtube Automation Agent
🎬 Open-source, self-hosted AI agent that runs a YouTube channel end to end: researches topics, writes scripts, generates narration, visuals and video, optimizes SEO, and publishes after your approval, then learns from analytics. Works with Gemini, OpenAI, OpenRouter, DeepSeek and more.
Claude Code
Well-known on GitHub
14 Aug 2025
🎬 Open-source, self-hosted AI agent that runs a YouTube channel end to end: researches topics, writes scripts, generates narration, visuals and video, optimizes SEO, and publishes after your approval, then learns from analytics. Works with Gemini, OpenAI, OpenRouter, DeepSeek and more.
- 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
- Well-known on GitHub, 14 Aug 2025
Vision Agents
Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.
Cursor
Well-known on GitHub
11 Aug 2025
Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.
- 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
- Well-known on GitHub, 11 Aug 2025
LLM inference, measured on real GPUs
Claude Code
Claude Code on GitHub
3d ago
Tt Git
A terminal git client in Rust (ratatui) with a GitLens-style commit graph, a lazygit-style status pane, a unified branch list and subprocess plugins.
Claude Code
Claude Code on GitHub
3d ago
A terminal git client in Rust (ratatui) with a GitLens-style commit graph, a lazygit-style status pane, a unified branch list and subprocess plugins.
- 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
- Claude Code on GitHub, 3d ago
Decision Model Guard
Guardrails for decision models: stop text inside the content from steering classifiers, Jev-like models and LLM judges. LLM Guard for decision models.
Claude Code
Claude Code on GitHub
3d ago
Guardrails for decision models: stop text inside the content from steering classifiers, Jev-like models and LLM judges. LLM Guard for decision models.
- 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
- Claude Code on GitHub, 3d ago
Pixelqg App
Tes agents Claude Code deviennent des pix : regarde-les bosser dans un bureau en pixel art. Gratuit et open source.
Claude Code
Claude Code on GitHub
3d ago
Tes agents Claude Code deviennent des pix : regarde-les bosser dans un bureau en pixel art. Gratuit et open source.
- 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
- Claude Code on GitHub, 3d ago
runthrough
Run GitHub Actions workflows locally: an act-style runner written in Rust
Claude Code
Claude Code on GitHub
3d ago
Warmpath: cache-aware LLM routing, live
Cache-aware router for LLM inference, with a live in-browser demo
Claude Code
Claude Code on GitHub
3d ago
SDD with Claude Code
Spec-driven development skills and guide for Claude Code
Claude Code
Claude Code on GitHub
3d ago
Leantokens
Cut the tokens Claude Code, Codex and LLM apps spend: compresses tool output, JSON and logs through a local proxy.
Claude Code
Claude Code on GitHub
3d ago
Cut the tokens Claude Code, Codex and LLM apps spend: compresses tool output, JSON and logs through a local proxy.
- 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
- Claude Code on GitHub, 3d ago
Mezo Agent Toolkit: live testnet console
Let an AI agent read Mezo and pay for those reads in MUSD, with no BTC for gas.
Claude Code
Claude Code on GitHub
3d ago
Dealership It Dashboard
Multi-site IT operations dashboard for a dealership group: tickets, staff changes, device health, domain security and an AI assistant.
Claude Code
Claude Code on GitHub
3d ago
Multi-site IT operations dashboard for a dealership group: tickets, staff changes, device health, domain security and an AI assistant.
- 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
- Claude Code on GitHub, 3d ago
Agent architecture field guide
Interactive guide to AI agent architectures: brains vs hands, state, sandboxes, and more
Claude Code
Claude Code on GitHub
3d ago
Interactive guide to AI agent architectures: brains vs hands, state, sandboxes, and more
- 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
- Claude Code on GitHub, 3d ago
Full page → Visit agent-architecture-field-guide-hyl52.ondigitalocean.app ↗
Job Application Agent
Autonomous job-application agent: Claude Code headless + deterministic Python (scraping, scoring, Playwright form-filling, CV rendering)
Claude Code
Claude Code on GitHub
3d ago
Autonomous job-application agent: Claude Code headless + deterministic Python (scraping, scoring, Playwright form-filling, CV rendering)
- 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
- Claude Code on GitHub, 3d ago
MiniMax H3 Video + Audio
MiniMax-H3 text/image to video with synced audio
tool unknown
Hugging Face Spaces
14d ago
What do these words mean?
- Claude Code
- Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.
- creator says: Cursor
- Dashed: its maker says this tool built it. Their word, which we cannot check.
- tool unknown
- Nothing on the page shows which tool made it.
- Shared by their makers
- Posted by the person who built it, in a community we follow, rather than found by our crawler.
- Today's picks
- Up to fifteen chosen each day, with the things their makers shared themselves first.
- Found
- When it was published, or when we first saw it if the source does not say.
The week in AI-built software
Every Monday: how many projects were built with AI that week, which tools built them, where they came from, and the week's picks.
Read the latest week