Hi HN. We built an API context registry to help coding agents (like Claude Code) generate production-ready API integration code without blowing through token limits.

We build a lot of API integrations. In our experience, most coding agents write basic client calls fine, but consistently stumble on details that make code shippable, like idempotent retries, rate-limiting and Auth token management.

We tried all the existing approaches of injecting context into coding sessions:

- Markdown dumps delivered via MCP (think Context7 or Mintlify Docs MCP) - API behaviour described in prose using AGENTS.md and skills. - OpenAPI specs

However, all of them left the same production-readiness gaps.

So we came up with our own approach that combines prose with typed SDK reference code into a "Context Plugin". You install the plugin into your coding agent and it automatically injects language-specific context whenever the agent works on an API.

Across our benchmarks, Context Plugins boosted one-shot production readiness by up to 34%, allowing Sonnet to match or beat baseline Opus on the same integration tasks. You can read more about our experiments here https://www.apimatic.io/blog/working-api-call-is-not-product...

We have published Context Plugins for 24 APIs for the community to try out, including Slack, Google Maps, and Notion.

We'd love for you to give them a go and share your feedback on our plugins as well as our evaluation methodology.

There is a second post on the front page right now offering a memory you own. Every few weeks we rediscover that the thing people actually keep is a folder of markdown in git, and then we build a registry in front of it.

[flagged]

[flagged]

[flagged]

[dead]