Show HN: Meteosource – Hyper-local weather API based on improved ML models
(meteosource.com)
At an affordable price, you will receive accurate and reliable data that you can easily implement into your website or application. We also help you optimise weather-dependent activities.
At an affordable price, you will receive accurate and reliable data that you can easily implement into your website or application. We also help you optimise weather-dependent activities.
Mistral Agents API
(mistral.ai)
Today we announce our new Agents API, a major step forward in making AI more capable, useful, and an active problem-solver.
Today we announce our new Agents API, a major step forward in making AI more capable, useful, and an active problem-solver.
Fast, Simple and Open Firebase Alternative: TrailBase
(github.com/trailbaseio)
Overhaul list API filters to allow for nested, complex expressions. The query parameters changed making this a breaking change. Users will need to update their client libraries.
Overhaul list API filters to allow for nested, complex expressions. The query parameters changed making this a breaking change. Users will need to update their client libraries.
Show HN: GenAI-powered OCR API for PDF receipts/invoices with smart extraction
(visionparser.com)
Welcome to the next level of document automation! Our innovative Receipt and Invoice Parsing API, powered by state-of-the-art Generative AI, gives you a flexible solution that extracts structured data from any receipt format. Experience exceptional accuracy, speed, affordability and customisation for receipt parsing.
Welcome to the next level of document automation! Our innovative Receipt and Invoice Parsing API, powered by state-of-the-art Generative AI, gives you a flexible solution that extracts structured data from any receipt format. Experience exceptional accuracy, speed, affordability and customisation for receipt parsing.
Gemini 2.5 Flash Preview 05-20
(google.dev)
The Gemini API offers different models that are optimized for specific use cases.
The Gemini API offers different models that are optimized for specific use cases.
Terraform MCP Server
(github.com/hashicorp)
The Terraform MCP Server is a Model Context Protocol (MCP) server that provides seamless integration with Terraform Registry APIs, enabling advanced automation and interaction capabilities for Infrastructure as Code (IaC) development.
The Terraform MCP Server is a Model Context Protocol (MCP) server that provides seamless integration with Terraform Registry APIs, enabling advanced automation and interaction capabilities for Infrastructure as Code (IaC) development.
How to Compare Streamable HTTP and SSE HTTP
(framer.website)
The MCP (Model Context Protocol) protocol is a standard protocol used for communication between AI models and tools. As AI applications become increasingly complex and widely deployed, existing communication mechanisms face a number of challenges. Recently, the MCP repository's PR #206 introduced a brand new Streamable HTTP transport layer to replace the original HTTP+SSE transport layer. The two protocols are simply compared as follows:
The MCP (Model Context Protocol) protocol is a standard protocol used for communication between AI models and tools. As AI applications become increasingly complex and widely deployed, existing communication mechanisms face a number of challenges. Recently, the MCP repository's PR #206 introduced a brand new Streamable HTTP transport layer to replace the original HTTP+SSE transport layer. The two protocols are simply compared as follows:
GitHub Models API now available
(github.blog)
You can now use the GitHub Models REST API to programmatically explore and run inference with models hosted on GitHub.
You can now use the GitHub Models REST API to programmatically explore and run inference with models hosted on GitHub.
Updated rate limits for unauthenticated requests
(github.blog)
To provide a secure and dependable experience on GitHub, we’re rolling out updates to rate limits for requests made without authentication.
To provide a secure and dependable experience on GitHub, we’re rolling out updates to rate limits for requests made without authentication.
Simple Agent API: A Minimal Setup for Serving Agents with FastAPI and Postgres
(github.com/agno-agi)
A minimal, open-source setup for serving Agents using FastAPI and Postgres. Built for speed, clarity, and dev happiness.
A minimal, open-source setup for serving Agents using FastAPI and Postgres. Built for speed, clarity, and dev happiness.
IPinfo started offering free unlimited country-level geolocation and ASN details
(ipinfo.io)
Accurate country-level geolocation and ASN details for free. No monthly fees, no credit card required, and unlimited API requests.
Accurate country-level geolocation and ASN details for free. No monthly fees, no credit card required, and unlimited API requests.
Show HN: X402 – an open standard for internet native payments
(x402.org)
Built around the HTTP 402 status code, x402 enables users to pay for resources via API without registration, emails, OAuth, or complex signatures.
Built around the HTTP 402 status code, x402 enables users to pay for resources via API without registration, emails, OAuth, or complex signatures.
Ask HN: Has anyone managed to pass Meta's Access Verification?
(ycombinator.com)
After spending a few months building out a new project that relies on the Instagram Graph API I'm struggling to pass Meta's Access Verification for Tech Providers.
After spending a few months building out a new project that relies on the Instagram Graph API I'm struggling to pass Meta's Access Verification for Tech Providers.
Show HN: Ductape – Build back end integrations once, reuse them anywhere
(ductape.app)
Ductape empowers developers to create reusable components, integrate third-party apps, and build complex, scalable, and monitored systems in code—all in hours, not weeks.
Ductape empowers developers to create reusable components, integrate third-party apps, and build complex, scalable, and monitored systems in code—all in hours, not weeks.
Google Gemini has the worst LLM API
(venki.dev)
And yet these models hide behind the poorest developer experience in the market.
And yet these models hide behind the poorest developer experience in the market.
Windows has trouble finding Win32 resource if it contains an accented character
(microsoft.com)
Maurice Kayser reported an issue with Win32 API loading of PE resources containing lowercase letters.
Maurice Kayser reported an issue with Win32 API loading of PE resources containing lowercase letters.
Easily turn any gRPC service into an MCP server
(redpanda.com)
Modern SaaS companies spend a lot of time designing, building, and maintaining APIs across SDKs, CLI tools, and now, LLM integrations. With the rise of the Model Context Protocol (MCP), AI-native interfaces like Claude or Cursor are becoming real API consumers.
Modern SaaS companies spend a lot of time designing, building, and maintaining APIs across SDKs, CLI tools, and now, LLM integrations. With the rise of the Model Context Protocol (MCP), AI-native interfaces like Claude or Cursor are becoming real API consumers.
Ask HN: Why does OpenAI require an ID to use their image API?
(ycombinator.com)
I was hoping to try out the “Open”AI image generation API in their Playground but it asked me to give them a copy of my ID for verification?
I was hoping to try out the “Open”AI image generation API in their Playground but it asked me to give them a copy of my ID for verification?
Show HN: Real-time 4/20 cannabis sales dashboard using Estuary and Tinybird
(headset.io)
Real-time cannabis intelligence from the industry's most trusted data partner.
Real-time cannabis intelligence from the industry's most trusted data partner.
Show HN: AgentAPI – HTTP API for Claude Code, Goose, Aider, and Codex
(github.com/coder)
Control Claude Code, Goose, Aider, and Codex with an HTTP API.
Control Claude Code, Goose, Aider, and Codex with an HTTP API.
The Impact of MCP and LLMs on Software Development – A Practical Example
(wundergraph.com)
Model Context Protocol sounds fancy, but what can you actually do with it? In this post I'll show you how to use MCP to one shot real tasks like exploring an API schema, writing GraphQL queries, or configuring a router. There is no deep domain knowledge required, no hype, just practical examples.
Model Context Protocol sounds fancy, but what can you actually do with it? In this post I'll show you how to use MCP to one shot real tasks like exploring an API schema, writing GraphQL queries, or configuring a router. There is no deep domain knowledge required, no hype, just practical examples.
WordPress Feature API
(github.com/Automattic)
The WordPress Feature API is a system for exposing WordPress functionality in a standardized, discoverable way for both server and client-side use.
The WordPress Feature API is a system for exposing WordPress functionality in a standardized, discoverable way for both server and client-side use.
Meilisearch – search engine API bringing AI-powered hybrid search
(github.com/meilisearch)
⚡ A lightning-fast search engine that fits effortlessly into your apps, websites, and workflow 🔍
⚡ A lightning-fast search engine that fits effortlessly into your apps, websites, and workflow 🔍
Ask HN: Why don't we have a functional DSL for data+embedding+API pipelines?
(ycombinator.com)
I’ve been working on a pretty common problem: <p><pre> - I have structured data in JSONL files (in.jsonl, out.jsonl) - I match lines by a key - I transform them into (text, embedding) pairs - I optionally filter/map them - I batch them (into chunks of 50) - I push each batch into an external system (e.g. vector DB, Chroma) </pre> That’s it. Sounds trivial.
I’ve been working on a pretty common problem: <p><pre> - I have structured data in JSONL files (in.jsonl, out.jsonl) - I match lines by a key - I transform them into (text, embedding) pairs - I optionally filter/map them - I batch them (into chunks of 50) - I push each batch into an external system (e.g. vector DB, Chroma) </pre> That’s it. Sounds trivial.
Use the Gemini API with OpenAI Fallback in TypeScript
(sometechblog.com)
If you want to use Gemini’s public API, but at the same time have a safe fallback in case you have exhausted the rate limits, you can use the OpenAI TS/JS library and a few helper functions. In my particular case I needed a type-safe solution for a chartmaker app with a fallback since Gemini’s gemini-2.5-pro-exp-03-25 model is restricted to 20 request/min.
If you want to use Gemini’s public API, but at the same time have a safe fallback in case you have exhausted the rate limits, you can use the OpenAI TS/JS library and a few helper functions. In my particular case I needed a type-safe solution for a chartmaker app with a fallback since Gemini’s gemini-2.5-pro-exp-03-25 model is restricted to 20 request/min.