gertjandewilde
What leaving Spectral looked like at Apideck for API linting
AI Agent API Grader
Apideck CLI – An AI-agent interface with much lower context consumption than MCP
The fix that worked for us was giving agents a CLI instead. ~80 tokens in the system prompt, progressive discovery through --help, and permission enforcement baked into the binary rather than prompts.
The post covers the benchmarks (Scalekit's 75-run comparison showed 4-32x token overhead for MCP vs CLI), the architecture, and an honest section on where CLIs fall short (streaming, delegated auth, distribution).
Designing APIs for AI Agents
Understanding the Security Landscape of MCP
Show HN: Describer – An Open-Source Tool for Codebase Understanding via Gemini
https://github.com/apideck-libraries/describer
Analyze codebases using AI - generate architectural overviews, documentation, explanations, bug reports and more Would love to hear your thoughts, feedback, and ideas for improvement!
Would love to hear your thoughts, feedback, and ideas for improvement!
Describer – An Open-Source Tool for Codebase Understanding via Gemini
Redefining Our SDKs Developer Experience
GPT-4 Demo – A showcase of GPT-4 resources, apps and use cases
One single API to build CRM, Accounting, HRIS, and ATS Integrations
Show HN: GPT-3 apps and use cases (gpt3demo.com)
In case you want to go the open-source route you have this handy overview https://www.btw.so/open-source-alternatives
I agree some categories are indeed thin, which is one of the reasons why we made the submission so potentially valuable tools can get listed.
SaaS Blocks 2.0 – tools for building a SaaS app
Boosting spec-driven API development
Show HN: Quicker OAuth and integration settings for SaaS products
Show HN: Open-source and paid apps to Build a SaaS product in 2021
The Cost of Cross-Border Data Flows
Show HN: GPT-3 market map with 180+ apps and use cases
The test automation is where the real magic happens.