← Latest products

LLMs suck at writing integration code… for now

superglue's AI agents connect, migrate and implement enterprise systems. Cloud-hosted or on your own infrastructure. 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.

Open source

2,069 stars · GitHubexternal site

Visit github.comexternal site

Reactions (2)

Similar products

by description similarity

  1. A CLI that writes its own integration code

    docs.superglue.cloud

    Set up AI agents to build and manage superglue tools via the CLI and superglue skill

    Hacker News15 pts

  2. A tool to benchmark LLM APIs (OpenAI

    llmapitest.com

    Claude, local/self-hosted)

    Hacker News55 pts

  3. I wrote an open-source browser alternative for Computer Use for any LLM

    github.com

    Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

    Hacker News180 pts

  4. I Wrote an Open-Source Alternative to OpenAI Operator

    github.com

    For Any LLM

    Hacker News15 pts

  5. Skrun

    github.com

    Deploy any agent skill as an API

    Hacker News62 pts