HN Showcase
Back to browse
GitHub Repository

Give an LLM safe, auditable tools for your existing app.

3 starsRust

Appctl LLM tools for apps you have

by esubaalew·May 7, 2026·1 point·1 comment
Visit ProjectView on HN

AI Analysis

●●SolidShip ItBig Brain

Auto-generates typed MCP tools from OpenAPI or DB schemas without custom code.

Strengths
  • •Wire-protocol parsing means zero code changes to existing apps.
  • •Local audit history tracks every tool call and argument for debugging.
  • •Supports diverse sources like Django, Rails, and PostgREST out of the box.
Weaknesses
  • •Zero stars and forks suggests early stage with unproven stability.
  • •Competes directly with established MCP servers and LangChain tools.
Target Audience

Backend developers and AI engineers building internal agents

Similar To

LangChain · Semantic Kernel · MCP Registry

Post Description

appctl(Appcontrol) uses your exising openai docs or your db and makes MCP tools. U can then connect your favorite LLM and chat either on terminal or web. The idea in mind is to expose actions we make inside any website of our own llm based so that we can ask AI to even submit a new record in our system.

Similar Projects

Developer Tools●●Solid

Turn any OpenAPI spec into agent-callable skills

It extracts focused, executable operations from giant OpenAPI files (the GitHub REST YAML is shown) to shrink context and avoid sidecar adapter sprawl — a pragmatic answer to token bloat and brittle ad-hoc integrations. Useful and concrete: if it actually generates tidy, updateable skill units and runtime hooks it saves a lot of maintenance. That said, the idea competes with existing LangChain/openai-function patterns; the repo will need clear runtime, versioning, and update strategies to feel like more than a nicer converter.

Solve My ProblemNiche Gem
yz-yu
104mo ago