Prune 100 tool schemas to top candidates in 0.4ms offline, or direct-dispatch with calibrated confidence.
Test real TurboQuant vector search in your browser. Type an intent or choose an example query below.
// Loading snippet...
Agents that pass entire MCP catalogs into each prompt burn thousands of redundant tokens every turn. Adjust the sliders below to calculate your savings.
Prompt tokens avoided
Direct LLM invoice savings
Beyond token cost, schema pruning eliminates LLM context confusion: the Gorilla BFCL benchmark proves top-1 selection accuracy increases from 86.1% to 100% when noise distractors are pruned out.
Evaluated on the Gorilla BFCL v3 multiple-tool dataset across 100 tool schemas and subtle distractor intents.
| Engine | Backend | Distractor Top-1 | 100-Tool Top-5 Prune | Search Latency | Network |
|---|---|---|---|---|---|
| TypeSafe (Jev) | Cloud System One | 100.0% | 100.0% | 258 ms | Cloud API |
| TurboQuant (WASM) | JS WASM (turboquant-search) | 86.7% | 85.0% | 14 ms | Offline |
| TurboQuant (Python) | Rust SIMD (turbovec) | 85.0% | 82.5% | 0.023 ms | Offline |
| TurboQuant (Pure JS) | Pure JS / Python Fallback | 83.3% | 82.5% | 0.4 ms | Offline |
Three simple stages to eliminate agent prompt bloat and achieve deterministic sub-millisecond execution.
Tool criteria and query tokens are hashed and rotated using a diagonal Rademacher matrix and the Fast Walsh-Hadamard Transform in O(d log d), eliminating data-dependent training overhead.
Vectors are quantized to 2-bit discrete intervals, while residual error vectors are captured with 1-bit Johnson-Lindenstrauss random signs. Preserves high cosine fidelity with tiny memory footprints.
When confidence clears your threshold, dispatch deterministic tool handlers directly in under 160ms. If ambiguous, forward only top-5 candidates to the LLM prompt.
Explore active schemas and add custom tool definitions