Skip to content

Lucineer/IKKF

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

IKKF: Instant Context-Aware Skill Loading 🥋

You rarely need to rebuild your agent to give it a new ability. IKKF is a skill router that lets your running agents discover and load new tools on-demand, based on the conversation context.


Why This Exists

Bundling dozens of rarely-used tools into every agent deployment creates bloat and slows iteration. IKKF was built to separate skill storage from your core agent logic. Your agent can request the exact code it needs, only when a user's request matches a skill's description.


Quick Start

This is a fork-first, open-source project. You deploy and control your own instance.

  1. Fork this repository to your GitHub account.
  2. Deploy your fork to Cloudflare Workers:
    npm install
    npx wrangler deploy
  3. Add Skills: Drop .js or .ts files into the /skills folder in your fork. Each file must export a default function. Push to deploy.

Your agents can now call your IKKF endpoint to discover and load these skills dynamically. Use npm run dev for local testing.


Core Design

  • On-Demand Loading: Skills are fetched by your agent only when their description matches the user's intent.
  • Edge Runtime: Deploys globally on Cloudflare Workers. Core skill routing logic typically completes in under 100ms.
  • Zero Dependencies: The runtime has no npm dependencies, reducing supply-chain risk.
  • Skill Isolation: Skills run in separate, isolated environments. A broken skill does not crash the router.
  • Live Updates: Add, update, or remove skills by committing to your /skills folder. No agent redeploys needed.
  • Centralized Skills: A single IKKF fleet can serve multiple, different agents.

How It Works

  1. Your agent receives a user message (e.g., "Check the rain tomorrow").
  2. The agent calls your IKKF endpoint with this message.
  3. IKKF evaluates all skills in its /skills folder, matching the message against each skill's description.
  4. IKKF returns the code for the highest-matching skill(s) to your agent.
  5. Your agent executes the returned code.

This is not a proxy or middleware. IKKF only returns the skill's source code to your agent, which then runs it.


One Specific Limitation

Skill files are currently limited to 1KB in size. This enforces focused, single-purpose skills but means you cannot bundle large libraries or complex logic directly into a skill file.


Public Test Instance

You can inspect a live instance: https://the-fleet.casey-digennaro.workers.dev


License

MIT

About

Short for "I Know Kung Fu", instant context-aware skill loading for your agents

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Python 100.0%