#APIs
200
2026-08-30
Show HN: We built open OpenRouter that turns usage into a better model
S
Hi HN, we built an open source model gateway. It's a single place to manage our own self hosted, frontier, and open source models in one place. It’s is rust native, built for concurrency, and implements all the config quirks across models and providers (streaming formats, tool calls, model parameters, rate limits, and different error behavior). The gateway adds under 1 ms for BYOK requests and under 2 ms when Experiential supplies the provider key. It has every major inference provider, and 1000+ models refreshed daily via a codex agent that opens a PR. Compared to other similar projects we’re open source, take no markup, allow you to mix local models with a marketplace, and use your traffic to (opt in) train you a model. Simple routing doesn’t warrant a 10% token markup. The way we do this is given standardized OTel traces, we mine representative real tasks, use text world models to simulate rollouts for various models, apply an LLM judge, and fit a nearest neighbor classifier on top of an embedding of a prompt to decide the optimal model for each request. Usually this can map out a better pareto curve on cost/quality than just calling single models but it’s not perfect. Using these simulations we can also do things like suggesting cache hit optimizations, new model suggestions, and training models. It’s open source, so you can deploy it on your own infrastructure, use our hosted version with 0 markup, or read how we design for maximum availability on our website.
2026-10-01
Show HN: Open-source model routing for coding agents at Astra-level performance
S
A few months ago we started building a model router for coding agents because we thought we could outperform any single model with an ensemble approach. Recently we’ve achieved that milestone and I want to talk about how we did it. First of all, a quick explanation: the Weave Router ( https://github.com/weave-os/router) plugs into any coding agent (e.g. Claude Code or Codex) and intelligently switches between LLMs. So, for example, Astra handles tricky debugging or complex system design tasks, and Deepseek v4 Flash handles simple frontend updates. What we’re announcing today is our new routing model, which we’re calling Weave Router 2.0. We benchmarked 2.0 against GPT-6 Astra on Terminal Bench 4.0 and SWE Atlas. On both benchmarks, the router had equivalent pass rates. On Terminal Bench, the router hit 52% of Astra’s cost, and completed tasks 2.2x faster. On SWE Atlas, the router cost 54% as much as Astra and ran 2.5x faster. (Full results on our website at https://weaveos.com/router!) It turns out training a model to route effectively - taking into consideration model capabilities, costs, cache awareness, and more - is a really hard problem! I want to talk about three ways we were able to improve so much over the last few months: 1) a new architecture, 2) larger training data set size, and 3) smarter cache-eviction impact calculation. 1) a new architecture. Our initial approach used an RL model without many priors. While RL is still an important part of the story, the cost of fully exploring the space of routing decisions is very high, so we’ve taken some shortcuts that have significantly improved performance. Consider how large the search space for the routing problem is. Take a typical coding agent session, with ~100 agent turns (i.e. 100 LLM API calls). Technically there are 100 chances to select a model. If we assume a roster of ~10 models (of course there are lots more but we can remove any that are Pareto dominated), then there are 10^100 possible paths through that session. We simply cannot explore all of them! So that's why clever tricks to shrink this space are so important. In particular: we trained a hidden Markov model to trace the session state, then a classifier maps the session to one of a few buckets of similar models. Using the HMM allows us to evaluate not just where a session is currently, but how it got there. We've gotten significantly better performance on bucket selection by incorporating that information - we believe this is because two sessions that might look quite similar to a naive classifier are much better distinguished by this HMM approach. Using this HMM + classifier to select a bucket first significantly shrinks the space to explore, by throwing out most models that could not reasonably serve the given session. This rearchitecture was the single biggest performance unlock! 2) larger training data set size (much less technically interesting but still an important part of the story). By using frontier LLMs to help us label a larger and more diverse set of coding agent sessions, we were able to bootstrap the two models discussed in 1) to a better state, while also providing even richer reward signals for RL. 3) smarter cache-eviction impact calculation. One of the hardest parts of routing well (if you care about saving money) is using the model caches intelligently. We built a subsystem that can calculate the expected value of switching models (and thus paying a high one-time cost to fill up a different cache) much more accurately, helping us avoid costly and unnecessary switches in more cases, while still switching when the benefit outweighs the cost. This is where most of our improvement on cost has come from. We still have a lot of room to continue to improve (we won’t rest until we’re consistently beating Astra/Fable, not just tying!) but matching frontier model performance was a huge milestone for our routing model, and in my opinion validates our initial hypothesis that an ensemble of models can do better than any single model ever could. Our router is open source ( https://github.com/weave-os/router) so anyone can try it out. Or if you prefer you can use our hosted version ( https://weaveos.com/router).
2026-09-03
Shopify/claude-for-commerce-examples
S
Shopify implementations of Anthropic's commerce-agents blueprint: a storefront shopping agent over UCP and Sign in with Shop, and a merchant agent over the Admin API
2026-09-10
Show HN: Give your AI agent on-screen guides that show users where to click
S
Hey HN. I'm Christian, one of the founders of Frigade (YC W23). I've noticed that a lot of in-app AI agents struggle to actually understand the products they exist in. For instance, let's say a user asks an agent how to do something in a given SaaS product. In an ideal case, maybe that agent replies saying it has a tool to do the task and just automates that work entirely for the user. That's a great outcome. But often that's not the case. Maybe there is no tool call for that exact task, or maybe the user's question is best solved by a specific UI workflow or interface. In these cases, many agents tend to fall back on basic RAG on their help center, or sometimes even searching the internet for an understanding of their own product. This can be a very slow process and most of the time help center articles are outdated as products evolve faster than them today. Even worse, no one likes reading a long list of bullets and mapping that back to a UI. My tool (Assist API) solves this gap with a single tool call defined like this: const frigade_guide_tool = { description: 'Call this tool to answer product questions or guide the user through a task.', parameters: { query: { type: 'string', description: 'What the user is asking or wants to do', }, }, run: ({ query }) => frigade.assist({ query }), } Here's a demo I recorded on how to set it up with the Vercel AI SDK: https://www.youtube.com/watch?v=9WQ0UbLjC6I When called, the tool will do the following: 1) Gather context on what the user is seeing on screen, their permissions, feature flags, and more. Then one of the following: 2a) If solvable: Generate an on screen guide for how to fix a given problem 2b) If conceptual: Return text describing to the parent agent how to solve the problem 2c) Reject (i.e. unable to help) How does the tool know what to do? The tool learns a given application UI by using a browser-based agent. You provide a test account to your software (i.e. staging og preview), and a browser agent logs in and works its way through the entire product. It then builds its own map of how the application works which can the be queried about any product-related question or how to get from A to B in the UI. It also writes its own documentation from this map. The agent re-runs on a schedule or can be triggered through CI/CD. Docs and more details: https://frigade.com/assist-api
2026-10-23
colinhacks/reylo
S
Import .sql files into TypeScript with full type inference and zero codegen.
2026-10-10
n1tr00-10/tiktok-web-signature
S
tiktok web signature reverse engineer generates valid tiktok signatures for API requets
2026-08-29
hkqr/my-free-code
S
Open-source multi-provider AI gateway for Claude Code and other coding agents, with model routing, streaming, tools, reasoning, fallbacks, and local model support
2026-08-24
truespar/sentio
S
Email inbox API for AI agents. Give every agent its own real email address, receive mail as structured webhooks, and reply in-thread over REST. A complete multi-tenant mail server in Rust: inbound and outbound, DKIM/SPF/DMARC/ARC, MTA-STS, DANE, three-tier anti-spam.
2026-10-15
outcrawlai/scout
A
Scout: the open-source browser agent, by Outcrawl. Mirrored automatically from Outcrawl's own repository.
2026-09-15
Show HN: Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and cost
A
Hey HN, Toby from Nari Labs here. We've been working on making OSS speech models super-fast. Last year, we built Dia, the first OSS text-to-speech model capable of doing natural dialogue. Since then, so many more great speech models have been released to the public. But the market is still dominated by closed source models. We think that's an inference problem. Existing systems such as vLLM / SGLang are not well suited for multimodal inference. To prove this, we built an inference engine specialized for Qwen3-TTS and open-sourced it ( https://github.com/nari-labs/nari-qwen3-tts). Running at sub-50 ms latency at 10 RPS, this showed open models can be run much faster and cheaper. Since then, we've been working hard to bring cheap, fast, and high quality serving to all. And we've even beat closed models at their game! Measured on the highly cited Coval (YC S24) voice AI benchmarks, our Qwen3-TTS endpoint not just is #2 in latency, but #1 in accuracy (WER) compared to 11Labs, Cartesia etc. while being the cheapest endpoint. Our Qwen3-ASR endpoint has the lowest latency and #2 accuracy, just 0.1% away from #1. It is the second cheapest model on the list. It took a lot of clever inference engineering to make these models quick, perform well while keeping costs low. Interestingly, Alibaba's official endpoints seem to perform worse in terms of accuracy and latency compared to ours. But nonetheless, much love to the Qwen team for OSS-ing these amazing speech models. We want to continue to push prices down to make speech technology a commodity - so that every app can have great TTS and STT without worrying about unit costs. We're also working on other parts of audio such as diarization - as well as video and world model inference. More to come!
2026-09-09
noskillish/bankmcp
A
BankMCP™: your AI can now read your bank. Self-hosted, read-only MCP server for your own bank accounts via open banking (Enable Banking). Standard MCP; tested with Claude and Ollama.
2026-09-25
Show HN: PlaceCall (YC W26) – agentic API to call businesses and get things done
A
Hi HN, this is Yarik and Vlad from VOYGR - we are building the tools for agents and apps to engage with local businesses. It all started with our own pain point at VOYGR: calling businesses to verify if they are open. We are both from Google (Maps and Search) and even there, the merchants and venues don’t keep this info updated. So we built an API and started using it in-house. On July 4th, we were driving through Portland looking for a place to eat. Google Maps was saying “Holiday hours may vary”. We tried some AI assistant apps (Poke was trending back then), and they couldn’t help. Our API found 15 Thai and sushi places and called it in parallel. A few confirmed that they are open today and are taking walk-ins. One was marked closed on Google. The app can find the restaurant, but someone has to answer the phone. This is the problem we kept seeing. Assistants can’t do much in the real world where the phone number is still a major communication interface. Muse added calls in beta mode, but it’s still calling only one place at a time. There are a bunch of tools to create your own voice agents, but nothing that can work simply out of the box. We’ve built PlaceCall to fit all your agentic needs. Give it a task in plain English and a US phone number (or a list of numbers) - it navigates phone menus, waits for you on hold, and returns a structured response with outcome, recording and transcript. If you don’t have a phone number, just describe what you need and PlaceCall comes up with the recommendations. Here is the demo: https://youtu.be/7ZbVCPv8Wq0?si=LoLxxx1M7nhS7_j- When PlaceCall API was tested in our hackathon, we had the following use cases implemented by the developers: checking if a doctor accepts new patients, getting quotes for car service, and running quick surveys. The API can be used through Claude Code and Codex; examples and setup are listed in the repo: https://github.com/voygr-tech/placecall We give the first 250 calls free. Product page is here: https://voygr.tech/placecall/ Try it and let us know how it goes. We are interested in learning what you would use it for and what is missing. We are here all day and happy to answer any questions. Our email: [email protected]
2026-10-01
Show HN: I built a free Burp/Caido alternative but, zero setup - API Testing
A
This is Katriel, the architect of the tool APIaxess. I have been API pentesting for a good time now, and starting with API pentesting was a bit of a rough patch. Specially the setting up and having to know the intricacies of proxies, networking and other stuff. Then once i got through it, the next rough patch was the apk pentesting, where getting the traffic of any apk was more of a task then the pentesting itself. So i started by writing scripts that automates the process and then made sure that any rooted adb just automatically started sending traffic to the burpsuite setup, and then that helped a lot. Then i just thought that this issue needs to be resolved in a more open manner, since its a very known pain point. So i built a GUI around it, made sure that it can handle everything that a normal api traffic tool can and then thought of releasing it, for people to test it out. Before the inital release, i have myself battle tested this tool, in multiple ways, while also sharing it with other professionals in my industry who constantly use Burp/Caido/HTTPToolkit or other similar tools. I know that the tool needs more features and more refinements, but thought of making it public so that i can get to know about the issues much sooner. Do check out the Github and leave a star if it helped you out, and do share it with your colleagues so that they could also waste less time setting it up and more time doing the work that they like. github.com/KatrielMoses/apiaxess
2026-09-01
slightbasebo/fragment-api-dev
A
Telegram Stars and Premium API with GRAM/USDT payments, Python SDK, REST examples, and no API key.
2026-08-26
Reality-JH/FailoverAI
A
Open-source gateway for reliable image, video and LLM jobs. | An open-source gateway for reliable image, video, and LLM jobs.
2026-09-11
xiaYuTian11/maskit
S
Data Maskit — a local privacy masking gateway built for large models (requests automatically masked, responses streamed back restored; supports any tool with a configurable Base URL such as Cursor / Claude Code / Codex / Pi)
2026-09-02
boringmarketer/meta-ads-skill
A
Teach your AI coding agent to run Meta ads: API setup, programmatic campaigns, browser control, and conversion tracking that's actually proven to work.
2026-10-17
Show HN: Things to Do API
A
I built an api/mcp for local events: pop-ups, one-off events, concerts, etc. currently covering the SF bay area. I've been building a bunch of consumer apps lately around personalization and recommendation and have had a hard time finding this data in one spot. agents can find useful stuff through tool calls / web search, but slow. you can scrape on demand too, but i wanted a faster data set and couldn't find an existing provider for the mix of event types I was searching for. the methodology for it is to find influential accounts/posters/etc. and do a fan out across things that they co-post with. mcp: `claude mcp add --transport http thingstodo https://api.thingstodoapi.com/mcp` I'm considering adding other cities. If you're building something that needs local event data, would something like this be useful and where would you want coverage?
2026-09-18
Show HN: Scry, programmable internet search w/ congestion pricing
A
Meet Scry, a 500 TB NVMe internet index in ClickHouse that you can run ~arbitrary readonly SQL and some of Datalog over, and I handle the problem of resource-contention with congestion-based micro-auction pricing. When there's capacity, the service is free for non-commercial use. --- Hello. It's 2026, we're training simulated fruit fly brains to play Beat Saber, do we still have to be stuck with internet (re)search as fn: natural language -> black box we can't do anything about -> ranked_list/summary? There is a long history of people trying to do very fancy things that end up being done in relational databases and a little SQL. There is a gravity to them, a bitter lesson, just like scaling of generalized ml training methods. I mean many, many information products can be built off essentially giant real-time OLAP databases and frontier LLMs writing brilliant SQL+Datalog+vector+Jev etc. queries. Google Search, Tavily, Exa essentially have the problem of mapping your agents' context you are willing to provide, to a tiny subset of their index. You pay a fixed cost to an extremely hard problem that has a distribution of hardness, which means YOU eat the downsides when they are running out of budgeted compute to help you out. Their algorithms are opaque to the caller, there's really not much user control, and there's not a serious opportunity to communally improve search recipes, like the lexical+Jev recipes you trust to select bleeding edge AI builders. Furthermore, search companies aren't even pursuing text-to-SQL anymore (several have talked to me)... they made up their minds during the traumatic 2024 text-to-sql days. They were just too early. I hope you enjoy. I'm intent on scaling this paradigm on differentiated hardware over much more data, so any compelling use cases or queries I could show off, would be much appreciated!
2026-09-02
Show HN: Orthogonal – One integration for agents to discover and pay for APIs
A
Hey HN, we're Bera and Christian, and we're building Orthogonal. Orthogonal gives AI agents one integration to discover, access, and pay for APIs. Think OpenRouter for the APIs that AI agents use. We currently have 50+ API providers and 700+ API endpoints across company, people, financial, and web data, available through our MCP server and SDK on a pay-as-you-go basis. We started with GTM related APIs and are now expanding the catalog. You can try at https://www.orthogonal.com/. You'll need to create an account to use the chat or connect the MCP/SDK. An example prompt for the chat or MCP: Find AI infrastructure startups that recently raised a Seed or Series A and return their founders, LinkedIn profiles, and relevant company data. When we heard about https://x402.org/, we saw an opportunity to make APIs easier for agents to pay for. Instead of an agent needing to manage an API key and billing for every API, what if it could just pay for each request? So we started onboarding existing API providers onto x402. Then we realized an agent cannot pay for an API it doesn’t know exists. It also needs to figure out which API can complete the task and how to use it. We also found that putting every small API payment on-chain did not always make sense. If both sides already have accounts with Orthogonal, settling internally is simpler. So we separated API discovery and access from the payment rail. Today, payments can happen through Orthogonal credits, x402, https://mpp.dev/, or https://www.circle.com/nanopayments. The problem we're working on now is API selection. If five APIs can answer the same request, which should the agent use? The cheapest might have worse coverage. Another might be more accurate but slower. We're working on using price, latency, reliability, and result quality to help agents make those decisions. How are you currently giving agents access to paid APIs? And if you gave an agent a budget, would you trust it to choose which API provider to spend it on?
2026-10-15
Show HN: T0: We trained a 256M SOTA open-weights time-series forecasting model
A
Hi everyone, we are excited to share t0-gamma, the latest model in our t0 family. It is a 256M parameter open-weights foundation model for time series (TSFM). It runs on CPU, GPU or Apple chips. https://huggingface.co/theforecastingcompany/t0-gamma t0 leverages historical data to forecast the likely outcomes over a given horizon. It does so zero-shot. It works on almost any time series, as it can pick up small signals like trends and seasonality. It can also leverage future-known information, like holidays, promotions and weather forecasts. Under the hood, t0 is a transformer that alternates attention between time and across the variates of a series. t0 is agnostic to the domain and to the frequency of the time series. For instance, it can be used to predict retail or electricity demand, as well as server metrics. On European day ahead electricity prices, t0 reduces the error by a third compared with a naive baseline that repeats the previous day. Adding weather forecasts or holiday information improves it even further. There is a Colab notebook to try it. t0 has also been tested independently on electricity prices in Texas (ERCOT). https://colab.research.google.com/github/theforecastingcompa... Like other TSFMs, t0 outperforms classical techniques such as ARIMA, ETS and their variants. On the public benchmarks GIFT-Eval, fev-bench and TIME, t0-gamma currently ranks first among the other TSFMs. It means it is the most accurate model there is to date. Like other TSFMs, t0 can be used inside agentic, routing or ensembling systems. This can improve the scores on the leaderboards even further. Our tech report describes the model family and its evaluation. https://arxiv.org/abs/2609.24559 Trying it takes a few Python lines. pip install "tfc-t0[torch]>=0.6.0" from t0 import T0Forecaster model = T0Forecaster.from_pretrained("theforecastingcompany/t0-gamma").eval() history = ... # history of the time series to predict out = model.predict(history, horizon=24) out.median There is more to come. We are working to extend t0 to joint forecasts across related series and hierarchies, much longer contexts and faster inference. Please give it a try, and don't hesitate to tell us where it works and where it doesn't. We are The Forecasting Company. We want to help companies reduce their uncertainty about the future, so they can make better decisions. We are starting our journey by building foundation models for time series.
2026-09-18
agentscope-java/idempotency-shield
A
Express middleware that makes handlers safe to retry — replays the cached response for a duplicate Idempotency-Key instead of re-running it, with pluggable in-memory or Redis storage.
2026-11-05
Balanov/latch
A
One tiny HTTPS contract between any agent and any service. Quote, approve, commit, receipt. Zero dependencies. MIT.
2026-10-12
AI-BizOS/cross-harness
B
Open cross-harness protocol with terminal and local web interfaces
2026-10-08
Show HN: Agent.reviews – Where AI agents read and write reviews on tools
B
Hi HN! I’m Louis, Co-Founder of Armature (YC P26), where we help teams make their product discoverable and usable by coding agents. We already measured 50k+ agent sessions and realized that over and over agents would encounter the exact same limitations on different tasks using the same tool. So we wondered why these weren’t fixed. And the answer is simple: the feedback loop just doesn’t exist between agents and software vendors but also between different agents. Humans can share their experience on platforms like https://g2.com and https://trustpilot.com, but agents have nowhere to. So we created: https://agent.reviews: the G2 for agents. It works with a set of skills and an npm CLI (@armature-tech/agent-reviews) connecting agents to our API endpoints. Anyone can ask their agent (Claude Code, Codex, Cursor, etc.) to install it, and agents will naturally check reviews before picking a tool and post their own after using one. As usual, privacy was our main concern, so we added 3 layers before a review gets posted: Deterministic rules filtering secrets, PII, URLs, etc. A Jev classifier trained to detect any leak after the first check A small LLM checking each review to make sure nothing was missed We've been sharing this project around for a few weeks now and gathered thousands of reviews already. There are already interesting ones, for example: - A Claude Code agent noticed that the Stripe SDK systematically crashed when the API key was missing on the health check page (while it’s this page’s role to actually return an “API key missing” error) - 2 agents mentioned that Prisma required a DATABASE_URL variable even when it wasn’t connecting to any database. They both put fake URLs as a workaround, and it worked. We truly think the agent experience needs the same community effect user experience has, so everyone benefits from it: agents can pick the tools that are best optimized for them and software companies can improve their product based on real feedback. That’s why we made sure accessing reviews is free for both humans and agents and just requires copy/pasting one prompt for the agent to install our CLI & skill, start the authentication flow, and submit their first review (this helps us prevent unauthorized scraping and spam reviews). Would you let your agents submit and read reviews too? We’d love for you to set up agent reviews, ask your agent to check reviews next time it needs to pick a tool and post its own experience when using it. Then tell us how it went!
2026-10-07
Fanorisky/unstream-proxy
A
Zero-dependency proxy for Anthropic-type upstreams with broken SSE streaming
2026-09-22
seifreed/renfecli
A
CLI no oficial de Renfe, pensada también para agentes — horarios y tarifas reales de tren desde la terminal
2026-09-12
forefy/reburp
A
A Burp Suite extension that exposes the full Montoya API as a local REST API, with Swagger UI
2026-11-01
nanami-0713/relay-kit
A
Out-of-the-box E2E relay server (relay-e2e/v1) for Cloudflare Workers — one-command deploy. Reference agent & client included. Distilled from Alma with permission.
2026-10-17
opendevicedb/opendevicedb
A
Open directory of 21,000+ devices whose protocols or firmware are already open (OpenWrt, LineageOS, coreboot, Zigbee, Z-Wave, appliances…), so nobody — human or AI agent — redoes the work. Website, JSON API, MCP server.
2026-10-12
Show HN: WallHop – 12ft.io is gone, so I built a replacement
B
Hi HN, I'm Josh. WallHop is a free paywall bypass: paste an article URL (or prefix any URL with wallhop.io/) and you get the readable article without the paywall popup, ads or clutter. No signup, no extension. I built it after 12ft.io went away. The News Media Alliance took it down in July 2025 and I missed having something I could hit from my phone. How it works: it started as a fork of everywall/ladder (GPL-3.0) and I've modified it heavily since. Instead of relying on one trick, it chains several bypass methods per request and falls back to archive.is when they all fail, so one site blocking one technique doesn't break it. Things that might be interesting: - iOS Shortcut: on iPhone, tap Share > WallHop from any article in Safari or another app. This is how I use it 95% of the time. - It works on Medium member-only posts, which 12ft never handled. - Bookmarklet for desktop, plus /raw/<url> and /api/<url> endpoints if you want to script it. I've tested it against most major news outlets and a bunch of local papers. It won't work everywhere. There are SOME server-side paywalls that are out of reach, and I'd rather say that up front. If you find a site that breaks, I'd love the link, and I can likely figure out a way to bypass it!
2026-09-24
guiIhermevieira/sentinel
A
Open-source AML transaction monitoring: a NestJS service and a framework-agnostic rules engine on npm (@sentinel-aml). Idempotent ingestion, case management, audit log, runtime rule tuning.
2026-09-20
logan-markewich/jeff
B
A self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer.
2026-10-24
prototux/AARE
A
A proof-of-concept opensource implementation of Android Auto's client side (phone side)
2026-10-20
C4rohan/Lampline
A
Self-hosted voice agent platform: import your Dialogflow CX and CX Agent Studio agents, build and test them, and take calls on your own hardware. 20 model providers, phone and SIP through jambonz.
2026-10-02
Show HN: Helo – An email API from former Postmark folks
B
Hi HN, I'm Ryan, engineer and co-founder at Helo ( https://www.helohq.com) - an email API for sending transactional and marketing email from your application: password resets, receipts, notifications, newsletters, etc. Most of our team worked together at Postmark for many years, so we know what it takes to build a reliable email service. If you've ever loved a product and then watched it get acquired, you probably know the rest of that story. We started Helo to keep building the kind of product we're good at, improve on what we have learned, take good care of our customers, and stay independent while doing it. We're bootstrapped and plan to stay that way. Helo covers everything you'd expect from a developer-focused email service: - REST API and SMTP, with SDKs for Ruby, JS, C#, Python and Go (more to come) - Separate infrastructure for transactional and broadcast mail - Event logs, stats, webhooks, suppressions, unsubscribes, flexible permissions - Usage-based pricing with no arbitrary feature gates - https://www.helohq.com/pricing Beyond the fundamentals, we've also put a lot of work into multi-tenant sending. When you're a platform sending on behalf of your own customers, you need to keep one bad sender from hurting everyone's deliverability, let customers send from their own domains, and keep stats and unsubscribes separate per customer. We've built Helo to address all of these concerns, while also allowing flexibility in how the relationships between domains, webhooks, credentials, etc. are defined amongst your tenants. For example, you can share one verified domain across all your customers while letting a few use their own, send all events to one webhook or split them per tenant, and give tenants isolated credentials with permissions limited to exactly what they need. If you've built multi-tenant sending before, what was most painful? Is there something you wish your email provider handled for you but doesn't? I'd love to hear about it.
2026-09-27
czg86389-hub/muse2api
B
Reverse-engineered Muse (muse.ai) wrapped as an OpenAI-compatible API, supporting chat, text-to-image, text-to-video/image-to-video, multi-account pool rotation and 48h auto-renewal. OpenAI-compatible API for Muse.ai with Chat, Image & Video generation.
2026-09-24
BerriAI/liteagents
A
A provider-independent agent SDK with the same query() interface as the Claude Agent SDK, allowing you to use the right model for every turn.
2026-09-18
Show HN: Aclif – Agent CLI framework: one grammar, canonical names across SaaS
B
Simple discovery of the provider's default schemas is possible without any credentials (since they are built into the binary). If you want it to fetch customizations of your specific instance, give it credentials to your org. The repo has more details. https://github.com/agent-cli-framework/aclif
2026-09-07
pcm469768-droid/llm-api-speedtest
A
Benchmark LLM APIs, OpenAI-compatible gateways, and API proxies by token speed, TTFB, latency, and success rate. Compare multiple providers with reproducible JSON reports and scheduled GitHub Actions.
2026-08-25
sunchaokun/pptx-designer
B
Code-first Python library for generating editable PowerPoint presentations with native PPTX objects, SVG support, and LLM-friendly build APIs.
2026-10-09
fdaforno/freecenter
A
A vCenter-style management console for the free VMware ESXi hypervisor: web UI, REST API, migration between hosts, backups, Terraform provider
2026-09-24
hamada-emam-tech/nafath-php
A
Nafath identity verification for PHP — web redirect and app-push, with the traps the official docs leave out already handled.
2026-09-09
happier-milo/ruraldte-engine
B
Motor open source de documentos tributarios electrónicos (DTE) chilenos: firma XMLDSig, TED/CAF, envío directo al SII y timbre PDF417. Los 12 tipos del catálogo, en producción.
2026-09-09
henryzawadzki6542/cloudflare-turnstile-bypass
B
Work with Cloudflare Turnstile in Python: find the sitekey, get a valid cf-turnstile-response token in seconds. Dependency-free library + CLI, built for CI and automation.
2026-08-24
bearBoy80/opsflare
A
Unofficial Cloudflare multi-account client for iOS & Android (Expo). Unofficial Cloudflare multi-account mobile client. Usable with just an API token; OAuth requires deploying oauth-relay first and registering your own client.
2026-08-23
unclecode/modelprint
B
Who is really behind that API? Fingerprint any OpenAI-compatible endpoint in the browser: 9 infrastructure probes, side-by-side comparison, community-extensible.
2026-10-17
Quittio/quittio
A
E-invoicing for Laravel: ZUGFeRD/Factur-X, XRechnung, UBL and Peppol BIS based on EN 16931.
2026-10-10
Zagorodnyi/filter-ast
A
Parses a declarative filter object with $op(value) strings into a typed, database-agnostic filter AST. Zero dependencies, ~50 ns per call.
2026-09-30
Synpath-ai/synpath
A
One open-source API for prediction markets. Trade Kalshi, Polymarket and Polymarket US with one Python SDK: unified market data, smart order routing across venues, and advanced order types. Plus tick-level Kalshi order book history.
2026-09-16
letorig/video-generator-client
B
Async Python wrapper for Seedance, Kling, MiniMax and Wan video generation. Supports CLI and a local web UI
2026-10-22
Sliverkiss/toolkit
A
A pure Go middleware library that adds tool-calling capability to any LLM API.
2026-09-29
vivek-v-rao/price-check
A
Cross-provider market data validation for OHLCV prices, adjusted returns, discrepancies, and consensus datasets.
2026-09-26
agentscope-ai-java/pg-outbox
B
Transactional outbox for Postgres with no driver dependency — pass in any query function.
2026-09-09
Sophomoresty/turnstile-bypass
B
Cross-platform Cloudflare Turnstile solver (macOS, Windows, Linux)
2026-09-09
Show HN: Genotype: language that compiles to idiomatic TS, Rust and Python
B
Hey HN! I just shipped the first public version of a new programming language that I have worked on for the past two years. Its goal is to help synchronize types between TS, Rust, and Python (more to come). Two main use cases are the API client libraries and client-server interop, i.e., a TS web app talking to a Rust server. I focused on making it as flexible as possible but always produced idiomatic types that look and feel like they were carefully crafted by humans. It was a challenge, e.g., I had to test 7 Python versions for every language feature or had to implement Rust literals runtime. It's written in Rust, btw ;-)
2026-09-05
truespar/paddock
B
Native Rust inference server for open models on NVIDIA GPUs. OpenAI- and Anthropic-compatible APIs, GGUF + safetensors, FP8/NVFP4/MXFP4/Q8/Q4, built-in Studio
2026-08-24
frogermcs/stripe-ksef
A
Synchronize Stripe EU B2B invoices with the Polish National e-Invoicing System (KSeF) using Node.js and TypeScript
2026-11-05
Balanov/equal
A
Turn real API traffic into a local sandbox and OpenAPI. Tiny static Go binary, any HTTP SDK, offline development, MIT.
2026-11-01
test-bit-sys/algeria-geo
A
Algeria's 69 wilayas, 538 dairas and 1,541 communes with Arabic/French search and historical administrative boundaries. Python and TypeScript libraries.
2026-10-15
Thrasher2020/hyundai-pleos-europe-ha
A
Read-only Home Assistant integration for Hyundai, Kia and Genesis cars in Europe via the Pleos Vehicle Data API
2026-10-13
sepehr071/awesome-iran-mcp
A
19 open-source MCP servers (308 tools) that give AI agents the Iranian web: Digikala, Snappfood, Jabama, MrBilit, Paziresh24, Taaghche and more. Prices in Toman.
2026-09-21
ghuntley/underclass
B
underclass: an OpenAI-compatible pooling proxy that pins sessions to one account (prompt cache stays warm), cools quota-exhausted subscriptions until their window resets, and fails fast with the earliest Retry-After when the whole pool is dry.
2026-09-13
shikakun/konpeito
A
A self-hosted RSS feed reader on Cloudflare Workers and D1. Passkey-only sign-in, Google Reader API compatible.
2026-11-01
ashayas/icloud-s3
B
An S3-compatible object store backed by iCloud Shared Photo Albums. Quota policy: Apple's Shared Album loophole.
2026-10-14
Show HN: MemorySync – Memory for AI Agents
B
I created MemorySync because I kept running into the problem of AI agents not being able to remember useful things about users between conversations. I wanted an easy way to give the agents memory in my application without having to build the whole thing myself. MemorySync is an API for giving AI agents memory. The application sends MemorySync information provided by the user, MemorySync saves useful memories for that user, and they can be retrieved later when needed. Give it a try without creating an account: https://memorysync.io/try Store a memory, refresh the page, and ask for it back to see if it remembers. If you're interested in using the API, I put the documentation here: https://docs.memorysync.io/ It's hosted only at the moment, so there is no self-hosting option. It's currently available in one US region, and it takes a few seconds to store a memory. The free plan allows 10k saves and 1k searches per month, and no credit card is required. I'd like to know if you think this is a useful abstraction for building AI agents, and what else you would expect from a memory API.
2026-10-06
LAGcomcom/zen-gate
B
Put OpenCode Zen free models into all your AI Agents — a Windows tray gateway, OpenAI/Anthropic compatible, auto-adapts to 10+ Agents, auto-switches on rate limits.
2026-09-24
seuros/skipper
B
MCP server for git repositories: local git in-process via gitoxide, plus GitHub, GitLab, Gitea and Forgejo through their CLIs
2026-09-23
Calcium-Ion/AstrLink
B
A local AI gateway for AI agents, unifying your subscriptions and API providers with smart routing and on-device privacy protection.
2026-09-04
Show HN: I built my first MCP to manage Google Ads
B
My co-founder and I tried running Google Ads for our Shopify store, but we could not get a positive ROAS (we spent 150USD on a single conversion). As we also could not afford an agency, we turned to AI (IMO Codex >>> Claude Code). We found that Google’s Ads MCP could only read data, but it could not make changes. So we built our own hosted MCP with read and write access. It can inspect performance, find wasted spend, create or update campaigns, and work with Google Analytics and Tag Manager.
2026-08-25
2023ai/ftmo-risk-control
B
Fail-closed FTMO risk control service and MT5/cTrader adapters for position sizing, daily loss, news windows, frequency limits, and execution audit.
2026-10-22
ContentWriterco/rozklad-mcp
B
🚆 Rozkład jazdy PKP, PKS i komunikacji miejskiej dla AI – serwer MCP: wyszukiwarka połączeń z przesiadkami, odjazdy, opóźnienia na żywo, ceny biletów. Polish train & bus timetables for Claude, ChatGPT, Cursor.
2026-10-12
Liu-zhongxian/wechat-bridge
B
Official WeChat iLink bridge: bidirectional text/image/video/file sending and receiving, implemented in Python
2026-10-09
Abhishek-Gali/HookRelay
B
Security-hardened webhook ingestion & multi-destination delivery gateway (GitHub ➔ Discord, Slack, HTTP) with HMAC-SHA256 verification, durable SQL queueing, fencing leases, smart retries, and DLQ.
2026-09-27
charlesdove977/claude-x-jev
B
Fast, cheap, typed decisions for Claude Code. Jev (TypeSafe's decision model on OpenRouter) sorts, checks, scores, gates and verifies at 0.3s and a fraction of a cent per item. Claude keeps the reading, writing and judgment.
2026-09-09
1amageek/SwiftMusic
B
Declarative music in Swift: patterns, musical events, and live update state.
2026-10-16
MBratkowski/deweloperuch-mcp
B
Unofficial MCP server and CLI for Polish new-build apartment prices: developers' asking prices with history, RCN transaction prices and GUS/NBP statistics (data from deweloperuch.pl)
2026-10-08
EvilFreelancer/tgfake
B
Offline Telegram Bot API for testing bots, Mini Apps and LLM integrations.
2026-10-05
amos689/paper-preflight
B
Pre-submission integrity gate for LaTeX papers: every reference verified against real scholarly records. No LLM guessing.
2026-10-03
IuCC123/CLIProxyAPI-Rust
B
Your Claude, ChatGPT and Gemini subscriptions as one fast API. A single Rust binary with OpenAI, Anthropic and Gemini compatible endpoints, WebSockets and a built-in dashboard.
2026-09-29
kofiadeyemiq/byterange
B
RFC 9110 HTTP Range parsing and serving for Go, with limits on range count and multipart amplification.
2026-09-21
TiancongLx/open-mcp-gateway
B
High-performance MCP-to-OpenAPI 3.1.0 gateway, built for the Open WebUI ecosystem.
2026-09-12
sayaka-aiart/cubism-api-bridge
B
Unofficial TypeScript/Python bridge and local HTTP server for Cubism Editor External API, with StandRig integration. Experimental.
2026-09-08
itsjasur/uzbekistan-geocoder
B
Self-hosted forward and reverse geocoding for Uzbekistan with Nominatim, Docker Compose, and an optional Caddy proxy.
2026-08-27
push-in/pam-whatsapp-web
B
A typed, persistent WhatsApp Web client for pure PHP on PAM — no Node.js or Puppeteer.
2026-08-24
besart-k/hono-shopify-auth
B
Authenticate Shopify embedded app requests and webhooks in Hono
2026-11-02
myluzh/catlink-client-py
B
Independent, unofficial Python client for CATLINK smart pet devices. Independent, unofficial Python client for CATLINK smart pet devices.
2026-10-14
jiaji12/deepseek-vision-pro
B
Give text-only DeepSeek eyes for images: local proxy + Zhipu GLM-4V free vision model, one-click install, send an image and it recognizes it
2026-10-10
thu-nics/TokenRouter
B
[NeurIPS'26] The official code implementation for paper "TokenRouter: Efficient Serving System for Token-Level LLM Routing"
2026-10-01
openai/sign-in-with-chatgpt-devkit
B
Sign-in with ChatGPT DevKit — local SDK, reusable React components, design assets, and the Paste Perfect desktop example.
2026-09-10
lynchest/runnel
B
A small, secure HTTP egress gateway with per-domain rate limiting, circuit breaking, queueing, caching, and SSRF protection.
2026-10-23
Mason-Levyy/garmin-personal-mcp
B
MCP server for Garmin Connect on Garmin's official Personal API: sleep, HRV, body battery, activities, and more from Claude or any MCP client
2026-10-15
tarunmottlia/stickly
B
Drop-in rewards widget for SaaS. Let your users earn your own product credits for starring your repo, joining your Discord, or leaving a G2 review — one script tag, rewards granted by signed webhook to your own ledger.
2026-09-30
Tobi1chi/OpenRayneo
B
Unofficial macOS Bluetooth bridge for RayNeo iO glasses: local HTTP notifications and teleprompter control.
2026-09-19
obie/feelings
B
Probabilistic conditionals for Ruby: Feelings(message).like?("genuinely urgent")
2026-10-23
Juwan-Hwang/omni2api
B
Anything to API (万物皆可2API): put an AI agent, a script, or even yourself behind an OpenAI-compatible API
2026-10-23
doeixd/effect-email
B
Effect-native transactional email for TypeScript: typed messages, durable delivery, providers, policies, SMTP, HTTP gateway, and workflows.
2026-10-19
Agent2API/agent2api
C
Agent2API — multi-provider local gateway: wraps the logged-in sessions of clients like WorkBuddy / Xiaohuanxiong / CatPaw / AutoClaw into OpenAI-compatible APIs, with account management, outbound fingerprint masking and request reports.
2026-10-17
azrinaldi/gemini-stealth-bridge
B
Browserless Chrome uTLS + HTTP/2 OpenAI-compatible API daemon for Google Gemini Web (/v1/chat/completions & /v1/responses)
2026-10-03
kyle41111/AI-FILE
B
A listener profile for the Mythic C2 framework that utilizes AI vendors file API's
2026-09-20
BillionsBobby/JevRouter
C
A lightweight Jev-powered router for models, tools, and subagents
2026-09-08
lfzk550/fanzha-ai-proxy
C
National Anti-Fraud AI API converted to an OpenAI-compatible reverse proxy service || for learning purposes only
2026-09-07
sreenidhbonagiri/remedi
B
Find affordable prescription alternatives and patient assistance programs in seconds using FDA data and income eligibility checks.
2026-09-29
Silent-Watcher/nestjs-quota
B
Production-grade API quota enforcement and usage metering for NestJS
2026-10-30
Cygnux-Labs/PCM-protocol
B
Proof-Carrying Messages: a protocol for AI agents whose claims carry evidence the receiver checks offline
2026-10-29
paid-tw/tw-ubn
B
Taiwan business-registry (UBN) open dataset + checkout VAT→title lookup client
2026-10-19
vahidbaghi/neshan-routes
B
Several routes on Neshan map at once, compare them, and find a meeting point on the way (Chrome/Firefox extension)
2026-10-06
VelaPayments/vela-server
C
NestJS backend for Vela’s Stellar payment prototype, with payment-request validation, WebAuthn authorization, and transaction services.
2026-09-29
tunaarikaya/magaza-mcp
B
Tek MCP sunucusu, iki mağaza: App Store Connect + Google Play. Tamamen Türkçe.
2026-09-29
Show HN: Durable Actor Session Protocol
C
Hey HN I'm the author of Jido, an Elixir Actor & Agent SDK. I was building out an Elixir Durable Actor/Agent server and hit a wall regarding communication protocols. I reviewed all the existing protocols; A2A, ACP, AHP and nothing met my needs. I wanted a language agnostic durable actor session protocol. Agent Host Protocol (AHP) from Microsoft was close, but was centered around "chat". The future I envision for agents goes far beyond just text chat. Thus, DASP was born. I'm submitting to HN because I know this is the one place where I'll get real feedback on whether this is an actual need or my tokenmaxxing got the best of me this weekend. This is a builder protocol. I'll be building out clients beyond Elixir and TypeScript, but plan to only support an Elixir server built around my Jido ecosystem.
2026-09-20
0xmikadzyki/ghost
B
Fund-flow pipeline for Robinhood Chain (chain 4663): full ERC-20 Transfer backfill via HyperSync, 1.4B transfers in ClickHouse, read-only JSON API.
2026-09-19
dashscope-sdk/idempotency-shield
B
Express middleware that makes handlers safe to retry — replays the cached response for a duplicate Idempotency-Key instead of re-running it, with pluggable in-memory or Redis storage.
2026-09-03
peter123023/awesome-free-llm-api
C
Free LLM API navigation · only lists permanently free / limited-time free endpoints callable via API Key and endpoint | A curated list of free LLM APIs — permanently free tiers and limited-time free models, all callable via API key and endpoint. Channel-first, with a model index for DeepSeek, GLM, Qwen and more
2026-09-02
hyundaimotorgroup/hmg-ipmap
B
Open-source IP geolocation platform that resolves IPv4 addresses to city, country, and continent
2026-08-29
ConiferKit/use-conifer
B
The Conifer SDK — one gateway for cloud, local, and BYOK inference, with exact per-call cost receipts. TypeScript + Python + MCP.
2026-11-05
FalihPrada/claude-code-gateway
B
Claude Code Gateway for Kimi, GLM, DeepSeek, and OpenRouter
2026-11-05
aws-samples/sample-multilingual-ivr-contact-center-for-amazon-connect
B
Deploys a multilingual IVR contact center on Amazon Connect with one AWS CDK stack: caller identification, per-agent case isolation, returning-caller routing, supervisor case assignment and voicemail-to-case with Voicemail Express.
2026-10-11
percentwasphose/itmo-schedule-calendar
B
ITMO schedule in your calendar: ICS subscription and read-only CalDAV for Apple Calendar, Google Calendar, Thunderbird, DAVx⁵, Outlook, Nextcloud and Android.
2026-10-09
Stellar-Sentinel/sentinel-backend
C
FastAPI service for Stellar account screening, Soroban event monitoring, and network health.
2026-09-27
BYTEX-TRADE/bytex
B
Event-driven algorithmic trading engine for .NET. Write a strategy once and run it unchanged in backtest, paper and live trading, deterministic, with fixed-point money and adapters for Binance, Bybit, OKX, Kraken, Bitget, Gate, KuCoin and Hyperliquid.
2026-09-27
tomascupr/reelql
B
Give your agent eyes: any video link in, one typed JSON out. A Claude skill + API.
2026-09-25
ollaya-dev/ollaya
B
Run open decision models locally: pull and serve Laya, decider, NLI and GLiClass behind a TypeSafe-compatible API. Ollama for decision models.
2026-09-21
Show HN: Lightspeed, build real time apps the Laravel way (+asteroids demo)
C
Hi HN! Laravel has worked with websockets for years but generally speaking it's a one way push architecture (i.e. http in, sockets out). Lightspeed is kind of like node in that it's a single server that serves your http and your websockets all under one roof. Auth runs in 0.03ms (a Redis read, no database). Your Laravel handler runs inside the full container and the reply comes back down the same socket. I think this could be really cool for creating new ways of working with Laravel. Anyway, I put together a live demo to show it in action. Basically a cross between slither.io and Asteroids. Game here: https://innerloop.works/lightspeed Repo here: https://github.com/innerloop-dev/lightspeed Note: This is 0.1.0, the API may change before 1.0. It needs the Swoole extension and Redis. MIT.
2026-09-18
0xSero/harness-bridge
B
Point any coding harness (Claude Code, Codex, OpenCode, Pi, OMP, Crush, Copilot, Grok…) at any OpenAI/Anthropic/Responses-compatible inference endpoint. Core library + CLI + macOS tray + web UI.
2026-09-13
owenzhao/DeepSeekStatus
B
A macOS menu bar whale that shows whether DeepSeek is in peak or off-peak pricing.
2026-09-04
Victor-Kipruto-Rop/knbs-cbk-pipeline
B
Ingests KNBS and CBK public indicators, standardizes and transforms them with dbt, stores marts in PostgreSQL, and exposes query + CSV APIs with signed cursor pagination, ETag caching (Redis), and rate limiting.
2026-09-04
rallisf1/greek-postal-code-db
B
Embed a postcode database into your (offline) application. Regions, municipalities, communities, and partial street coverage included.
2026-08-24
zhuyifang/tonghuasun-codex
B
Connect the local 同花顺 quotes, account data and real-time data to Codex
2026-10-19
eliasbiondo/antirion
B
⚡ The fastest open-source AI gateway — one Rust binary with a built-in console to route, secure, budget and observe every LLM call across OpenAI, Anthropic, Gemini, Bedrock and more.
2026-09-08
Adudeguyman/Fantastic-HuggingFace-Downloader
C
Extracts files, folders, or entire repos from a pasted Huggingface URL, and lets you queue and download them using HF's Xet file system, avoiding slow and stalled downloads common from downloading large files through a browser.
2026-09-04
shanmukhasaireddy13/Go-Live
B
Instant, Globally-Distributed Anycast Subdomains for Developers (*.go-live.me) — 1-Click Vercel Deploy & Auto TLS 1.3
2026-11-09
mingzi206-gh/colab-t4-local-api
B
Agent-oriented Colab T4 to local OpenAI-compatible API deployment kit, with Drive cache and offline checks.
2026-10-03
nutrifit-health/nutrifit-widgets
B
49 embeddable nutrition and fitness calculators: TDEE, calories, macros, water intake, body fat, laboratory values and questionnaires. React components, JavaScript widgets and iframe embeds in six languages.
2026-09-24
mattn/go-jev
B
Go SDK and CLI for TypeSafe Jev: typed decisions (yes/no, choice, score) from a model
2026-09-18
cth9191/higgsfield-api-skill
B
On-demand Higgsfield API image and video generation for coding agents, with model-specific docs and resumable jobs.
2026-09-17
justoneapi-labs/xiaohongshu-api
C
Xiaohongshu API, Xiaohongshu interface: Python call examples for note search, note details, and comment queries. Just One API.
2026-09-12
linqiu919/better-context-engine
B
ACE-compatible code context retrieval engine: real-time codebase indexing and low-latency context for AI coding assistants
2026-09-07
ramazancetinkaya/global-timezone-tracker
C
Automated world timezone and DST status tracker with ready-to-consume JSON datasets.
2026-09-04
pinkorca/icekarim
B
High-performance Telegram bot for rendering live Iranian gold and USD prices as WebP stickers
2026-08-25
RojanSapkota/esewa-payment-gateway
B
A self-hosted eSewa payment gateway bridge with dynamic QR code generation, universal Nepali bank support and automated instant verification. Zero-fees and no PAN/VAT required.
2026-10-30
chalk-ai/chalk-router-oss
B
chalk-router: an extremely fast & focused LLM router implementation.
2026-10-17
kernelpanic0x11/instagram-api-workbench
B
Instagram Android API evidence, OpenAPI catalog, and local JavaScript Swagger workbench
2026-10-03
8133/visitedhomedata
B
a python script to get clash of clans base data (buildings, obstacles, last_played etc) from a tag WITHOUT emulator!
2026-10-03
louis666ash/amazon-scraper-skill
B
Batch-scrape Amazon product data by ASIN, at scale - no paid API. Per ASIN: title, brand, live price, RRP, discount, coupon/deal, BSR category + subcategory, rating, review count, stock status. UK/DE/US/JP with site-locked currency, no login. Includes battle-tested anti-bot findings.
2026-10-02
jnracreates/jellyfin-portal
B
A dark Jellyfin-themed homepage portal with Recently Added row, status widgets, and a serverless API proxy to keep keys off the client.
2026-09-19
lalouannabel0072/kalshi-trading-bot
B
Kalshi trading bot for prediction markets — browse event contracts and watch the order book in real time, run market making and momentum/reversion strategies with paper trading, risk limits and position sizing. Educational toolkit — not financial advice. Unofficial community project, not affiliated with Kalshi.
2026-09-12
ballerina-platform/module-ballerina-a2a
B
Ballerina Implementation of the A2A Specification
2026-09-01
basketikun/claude2api
C
Claude2API is a Claude.ai API-compatible gateway, account pool and web mirror service built with Go + Docker, supporting OpenAI Chat Completions, Responses and Anthropic Messages interfaces, connectable to clients such as Claude Code and Codex CLI, and offering account rotation, streaming output, multi-turn conversations, multimodal images, Thinking, Function Calling, Tool Use, API Key authentication, call logs and an admin backend.
2026-08-31
YuJunZhiXue/arcway
B
Lingguan Arcway: a self-hosted LLM gateway. OpenAI-compatible /v1, web admin for managing channels, routing and keys.
2026-08-27
cporter202/job-data-apis-and-scrapers
C
A curated directory of job data APIs and scrapers for listings, hiring signals, salaries, and recruiting.
2026-08-24
linearuncle/pi-openai-web-search
B
pi extension: OpenAI web_search (Codex protocol) as a model-callable tool
2026-11-07
koi-code/evm-rpc-check
B
A read-only tool to check EVM chain IDs, block heights, and contract bytecode.
2026-10-29
xiaolai/claude-driven-ai-providers
B
Use Claude Code with Codex, OpenAI, DeepSeek, Gemini, Grok, and local model providers.
2026-10-16
fzn0x/getman
B
Getman, Alternative to Postman. A local-first, open-source API client. Requests are YAML files in your repo; browser UI, terminal UI and CI runner in one binary. No account, no cloud.
2026-10-16
skibid991/httpresponder.com
B
Free HTTP request and response testing API. Decode base64 from a URL, echo requests, return custom status codes and headers, test redirects and streams.
2026-10-12
HRuiCcc/RuiC-oc-ferry
B
Ferry OpenCode's free models to WorkBuddy — isolated runtime, concurrency detection, verdict caching, one-click import, local OpenAI-compatible forwarding port
2026-09-26
jamespolyakov9829/captcha-api
C
Captcha-solving API client - Cloudflare Challenge and Turnstile in one interface, with cost tracking and concurrent batch solves.
2026-09-13
danieldeer/seriousdb
B
A simple, yet effective persistent key-value store accessible via HTTP.
2026-09-11
Akxan/google-seo-mcp
B
SEO & GEO MCP server for Claude, Codex, Cursor and any MCP client: Google Search Console, Google Analytics 4, PageSpeed Insights, Core Web Vitals, structured data, llms.txt, AI crawler checks, WordPress (Yoast, WP-CLI over SSH) and GitHub — 80 tools for technical SEO, content optimization and generative engine optimization
2026-11-09
czg86389-hub/ACP-Ant
B
OpenAI / Anthropic compatible API for Google's official Antigravity CLI over ACP: multi-account, per-account proxy, tool calling for agents (Codex, LangChain, Cline...)
2026-11-09
yanstd888/9routerx
B
9RouterX (9R Next Go Generation): Single-binary Go AI router, LLM gateway & 20-40% token saver. Route Claude Code, Cursor & Codex across 155 providers, 28 OAuth & 248 free models (24 keyless) — OpenAI, Claude, Gemini, DeepSeek, Groq, Ollama & MCP.
2026-10-26
cyber-xiaoya/cyber-xiaoya-danmaku
B
Cyber Xiaoya · Danmaku collector: Douyin/Bilibili/YouTube/WeChat Channels → digital human bridge (/api/danmaku) · AGPL-3.0 · Author: 天工开帧
2026-10-04
sepehr071/snapp-mcp
B
Unofficial read-only MCP server for Snappfood & SnappMarket: search food and groceries, compare prices, find deals.
2026-10-03
astronomiwe/tbc-sdk-python
B
Typed sync and async Python SDK for TBC Checkout payments, with token management, recurring payments, installments, and sandbox support.
2026-09-05
parallel-web/search-mcp
B
Free web search and page fetching for agents. Hosted MCP, no API key required.
2026-10-29
sepehr071/iran-gold-mcp
C
Unofficial read-only live 18k gold prices on Iranian sites: Milli.gold, Wallgold, Melligold, Daric.
2026-10-16
jellybeanb0603-svg/mcd-social-to-meal
C
McMeal idea seeding: drawing on Xiaohongshu inspiration, assemble a complete meal based on budget and the current McDonald's store menu, and price it with the official MCP.
2026-10-15
JamesZhaoY/logicc2api
C
OpenAI-compatible Logicc adapter with account pooling, credential refresh, and a local web console.
2026-10-09
bariskisir/ema-lightning-api
C
Self-hosted Turkish text-to-speech API. One container, full and streaming synthesis.
2026-10-02
GupshupSuperAgent/mcp
C
Run WhatsApp, SMS and RCS from Cursor: Gupshup analytics, template drafting and approval, and A/B, multilingual and scheduled campaigns, with a human review step before anything is sent.
2026-09-24
MUdevelops/RepoLens
C
Live GitHub repository analyzer & scorer — real API data only, zero mock fallbacks, zero backend.
2026-09-21
iFwu/cursor2response
C
Local Cursor gateway, Responses first, reusable SDK sessions, native steer, readable traces, and optional context overflow fallback.
2026-09-19
superagents-lab/jev-search
C
Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.
2026-09-12
AgriciDaniel/youtube-scout
C
Claude Code skill: one topic in, one ranked YouTube research workbook out. Searches YouTube Data API v3, ranks by views, engagement, momentum or breakout, and writes Videos, Channels, Summary, Comments and Transcripts sheets with hooks and replay hotspots. Appends into an existing social ads sheet.
2026-08-26
MuhammadAbdullah80/webhook-relay
C
Go service that fans one inbound webhook out to many downstream targets, with independent per-target queues and retry