Skip to content

Agent Tool Registry

A versioned registry and selection API for agent tools. Instead of showing a model every tool, it returns a small, permission-checked, semantically ranked shortlist per request.

Role: Creator
Period: 2026 – now
Status: active
Type: Open source
Stack: Python · FastAPI · SQLite · Local embeddings (bge-small)

The problem

Model accuracy drops once more than about 15–20 tools are visible at once. Real agent platforms have hundreds.

The solution

Register tools once, then ask /advise for a shortlist per request:

Registry (SQLite, versioned)
  └─ Retrieval index (cosine over local embeddings)
       └─ Selection pipeline (permissions → shortcut → router → candidates)
            └─ Execution & feedback (arg validation, confirmation gate, audit, usage stats)

Versioned tools: they are never mutated in place, and the full history is kept.
Permission checks first, before any ranking.
Gated, audited execution, with outcome capture that feeds back into ranking.
Runs fully locally: local embedding model, no API keys.