Alternatives
Products that do what LLMs suck at writing integration code… for now does
Hi HN! Stefan here from superglue and today I’d like to share a new benchmark we’ve just open sourced: an Agent-API Benchmark, in which we test how well LLMs handle APIs. We gave LLMs API documentation and asked them to write code that makes actual API calls. Things like "create a Stripe customer" or "send a Slack message". We're not testing if they can use SDKs; we're testing if they can write raw HTTP requests (with proper auth, headers, body formatting) that actually work when executed against real API endpoints and can extract relevant information from that response. tl:dr: LLMs suck at…
- 1WW
I spent a few hours last weekend testing whether AI can replace code by executing directly. Built a contact manager where every HTTP request goes to an LLM with three tools: database (SQLite), webResponse (HTML/JSON/JS), and updateMemory (feedback). No routes, no controllers, no business logic. The AI designs schemas on first request, generates UIs from paths alone, and evolves based on natural language feedback. It works—forms submit, data persists, APIs return JSON—but it's catastrophically slow (30-60s per request), absurdly expensive ($0.05/request), and has zero UI…
Nov 2025 · github.com
- 2AT
I recently built a small open-source tool to benchmark different LLM API endpoints — including OpenAI, Claude, and self-hosted models (like llama.cpp). It runs a configurable number of test requests and reports two key metrics: • First-token latency (ms): How long it takes for the first token to appear • Output speed (tokens/sec): Overall output fluency Demo: https://llmapitest.com/ Code: https://github.com/qjr87/llm-api-test The goal is to provide a simple, visual, and reproducible way to evaluate performance across different LLM providers, including…
2025 · llmapitest.com
- 3
- 4AJ
Hey HN, we’re building an open specification that lets agents discover and invoke APIs with natural language, built on the OpenAPI standard. agents.json clearly defines the contract between LLMs and API as a standard that's open, observable, and replicable. Here’s a walkthrough of how it works: https://youtu.be/kby2Wdt2Dtk?si=59xGCDy48Zzwr7ND. There’s 2 parts to this: 1. An agents.json file describes how to link API calls together into outcome-based tools for LLMs. This file sits alongside an OpenAPI file. 2. The agents.json SDK loads agents.json files as tools for an LLM that…
2025 · github.com
- 5
- 6AC
We run superglue, an OSS agentic integration platform. Last week I talked to a founder of another YC startup. She found a use case for our CLI that we hadn't officially launched yet. Her problem: customers wanted to create Opps in Salesforce from inside the chat in her app. We kept seeing this pattern: teams build agents and their users can perfectly describe what they want: "pull these three objects from Salesforce and push to nCino when X condition is true", but translating that into a generalized hard-coded tool the agent can call is a lot of work and does not scale since the logic is…
Apr 2026 · docs.superglue.cloud
- 7BR
Check out this impressive project that enables running LLMs entirely in the browser using WebGPU. Key features: - Zero token costs, no cloud infrastructure required - Complete data privacy through local processing - Simple 3-line code integration - Built on MLC and Transformer.js The benchmarks show smaller models can effectively handle many common tasks. Currently the project roadmap includes: - No-code AI pipeline builder - Browser-based RAG for document chat - Analytics/logging - Model fine-tuning interface
2025 · github.com
- 82C
Single-agent LLMs suck at long-running complex tasks. We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress. How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agents We tested this on a Putnam-level math problem, but the…
Feb 2026 · github.com
- 9IB
Hi! My name is Herve Kom, a computer science student that is interested in learning new things everyday! As one of my graduation project, I have developed a Claude Code -like Coding CLI, but with enhancement for API Testing: - Auto-generate & run tests (unit, e2e, Playwright, CI/CD, etc.) - Say bye-bye to hallucinations with built-in MCP Server to let LLM directly read from API Docs - Adding Agent.md support for better context persistence across your whole codebase - Automatic bug & security scans (logic is kind of basic but works great!) - Vibes, I want it to feel less "enterprise" but…
2025 · github.com
- 10LC
Hey, folks here is a peek into Jujutsu. We at Poozle are working with hundreds of APIs and it has been always frustrating to 1. Search the API in the documentation or ask ChatGPT 2. Then copy it to the postman and understand/test the API 3. Generate code to integrate into the codebase We thought how about having all of this at one place. We currently fine-tuned LLM on public REST APIs to reduce hallucination and then combined it with ChatGPT and Postman. I look forward to feedback, feature requests and discussions!
2023 · loom.com
- 11CA
Hi HN, I've been working with LLMs in production for a while both as a solo dev building apps for clients and working at an AI startup. The one thing that always was a pain was to pay OpenAI/Gemini/Anthropic a few dollars a month just for me to say "test" or have a CI runner validate some UI code. So I built this server called ChunkBack, that mocks the popular llm provider's functionality but allows you to type in a deterministic language: `SAY "cheese"` or `TOOLCALL "tool_name" {} "tool response"` I've had to work in some test environments and give good results for experimenting…
Nov 2025 · github.com
- 12WL
2025 · superglue.ai
- 13OS
Docs.codes generates simple markdowns for open-source libraries that you can add to the context of your LLM assistants, helping them generate better code. Here's a quick walkthrough with pypi/mem0ai as example: https://youtu.be/SKZol8G_tIE LLMs struggle with generating correct code when using lesser-known libraries or dealing with major version changes that happen after their training cutoff. With these markdowns, you can ensure that your LLM chat/coding assistants have up-to-date knowledge of the library's API and usage patterns. We built this using the latest…
2024 · docs.codes
- 14CL
Hi HN! Run it: OPENROUTER_API_KEY="sk" npx bff-eval --demo We built a tool to help people take LLM outputs and easily grade them / eval them to know how good an assistant response is. We've built a number of LLM apps, and while we could ship decent tech demos, we were disappointed with how they'd perform over time. We worked with a few companies who had the same problem, and found out scientifically building prompts and evals is far from a solved problem... writing these things feels more like directing a play than coding. Inspired by Anthropic's constitutional ai concepts, and amazing…
2025 · github.com
- 15AL
Hey HN! After struggling with complex prompt engineering and unreliable parsing, we built L1M, a simple API that lets you extract structured data from unstructured text and images. curl -X POST https://api.l1m.io/structured \ -H "Content-Type: application/json" \ -H "X-Provider-Url: demo" \ -H "X-Provider-Key: demo" \ -H "X-Provider-Model: demo" \ -d '{ "input": "A particularly severe crisis in 1907 led Congress to enact the Federal Reserve Act in 1913", "schema": { "type": "object", "properties": { "items": { "type": "array", "items": { "type": "object", "properties": {…
2025 · l1m.io
- 16AU
Hi HN, I was once given the advice: Don't waste expensive frontier model credits (GPT/Claude/etc.) on bulk work. Send the boring, repetitive, high-volume jobs to a smaller model, and save the expensive prompts for when you actually need frontier-level reasoning. I complained and told my manager that I shouldnt have to think about using certain models for certain coding tasks, and that one model should handle everything. Well, here we are anyway. If anyone needs a place to absolutely abuse an LLM with high-volume tasks, come beat ours up at https://yolo-auto.com. Here are…
Jul 2026 · yolo-auto.com
- 17AA
This repo is the result of a debate about what kind of programming language might be appropriate if humans are no longer the primary authors. Initially the thought was "LLMs can just generate binaries directly" (this was before a more famous person had the same idea). But that on reflection seems like a bad approach because languages exist to capture program semantics that are elided by translation to machine code. The next step was to wonder if an existing "machine readable" program representation can be the target for LLM code generation. It turns out yes. This project is the result of…
Mar 2026 · github.com
- 18IS
Hey HN! For that last 8 months I've been trying to make agents that can hack web applications to find vulnerabilities in them - An AI Security Tester. The system has 29 agents in total, a custom LLM Orchestration framework which works on the task-subtask architecture (old-school but works amazingly for my use case, and is pretty reliable) with custom agent calling mechanism. No Auo-Gen, Langchain and Crew AI - Everything custom built for pentesting. Each test runs in an isolated Kali linux environment (on AWS Fargate), where the agents have full access to the environment to undertake any…
2025
- 19IB
Apr 2026 · github.com
- 20LR
Hi hacker news, My name is Dillion and I'm the creator of llm.report. A few months ago, I was frustrated by the lack of observability into the OpenAI API. All of us are left in the dark about API performance, latency, cost calculation, cost breakdown, and more. I just wanted to know more about how my AI app is performing in production and make data-driven decisions to improve the product. So I ended up just building it myself. There are three parts to the platform: 1. OpenAI API Dashboard (no-code) - Enter your OpenAI key and get access to detailed insights straight from the OpenAI API…
2023 · github.com
- 21PA
Hi HN, I’m experimenting with a small Python library called PicoFlow for building LLM agent workflows using a lightweight DSL. I’ve been using tools like LangChain and CrewAI, and wanted to explore a simpler, more function-oriented way to compose agent logic, closer to normal Python control flow and async functions. PicoFlow focuses on: - composing async functions with operators - minimal core and few concepts to learn - explicit data flow through a shared context - easy embedding into existing services A typical flow looks like: flow = plan >> retrieve >> answer await flow(ctx) Patterns…
Jan 2026
- 22FA
LLM agents rely on tool calls — but tool responses are huge. Gmail, CRMs, and APIs return bloated JSON LLMs choke on large responses You only need 2–3 fields, but frameworks give you zero control Toolflow is an AI-native framework to fix this: * Filter tool responses before they hit the LLM * Context modes: `minimal`, `full`, `custom`, or `ai` * Composable TypeScript tool registry GitHub: [https://github.com/dksingh1997/toolflow](https://github.com/dksingh1997/toolflow) Would love feedback — especially from those building with LLMs in production.
2025 · github.com
- 23GB
Hey HN, We’re excited to share PySpur, an open-source tool that provides a graph-based interface for building, debugging, and evaluating LLM workflows. Why we built this: Before this, we built several LLM-powered applications that collectively served thousands of users. The biggest challenge we faced was ensuring reliability: making sure the workflows were robust enough to handle edge cases and deliver consistent results. In practice, achieving this reliability meant repeatedly: 1. Breaking down complex goals into simpler steps: Composing prompts, tool calls, parsing steps, and branching…
2024 · github.com
- 24IM
Every time I wanted to use LLMs in my existing pipelines the integration was very bloated, complex, and too slow. This is why I created a lightweight library that works just like scikit-learn, the flow generally follows a pipeline-like structure where you “fit” (learn) a skill from sample data or an instruction set, then “predict” (apply the skill) to new data, returning structured results. High-Level Concept Flow Your Data --> Load Skill / Learn Skill --> Create Tasks --> Run Tasks --> Structured Results --> Downstream Steps And the bast part: Every step can be saved and reused as…
2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →