Skip to content
v0.3.0 · Apache-2.0 · local-first

Ultra-fast, non-autoregressive encoder engine for structured intent and choice classification.

LLMs generate text. Tachyone produces calibrated decisions.
3.83 ms p50 latency · non-generative (no hallucinated labels) · calibrated confidence · local-first on consumer GPUs.

Get started View on GitHub

Tachyone answers atomic typed questions — choice, score, and noul — in a single forward pass and returns probabilities plus calibrated confidence. It speaks the exact TypeSafe Jev /v1/systemone wire protocol, so an existing Jev client can be repointed at a Tachyone server with no code changes.

3.83 msp50 fast path (CUDA graphs, RTX 3060, mmBERT, batch=1)
85.3%multilingual overall accuracy
95.6%Spanish (es) overall accuracy
0.0044fast-path probability parity Δ (0 top-label flips)

Why Tachyone

  • Sub-5 ms speed

    Per-shape CUDA graphs with bf16-resident weights, wired behind TACHYONE_FAST=1. Graceful fallback on CPU/MPS: the fast path never changes the response shape.

  • Permutation-equivariant choice head

    A dedicated low-rank bilinear residual (r=32) on top of the cosine baseline, so option order never biases the answer and the number of options is free (1–255).

  • Native multilingual

    An mmBERT-based checkpoint (LoRA rank 64) trained and calibrated per language for pt, es, fr, de, it, and nl, with automatic script/language routing.

  • Calibrated confidence

    Strictly proper scoring (RLCD) plus per-(primitive, language) temperature scaling, with per-language ECE reported. The ECE ≤ 0.05 target is met for two of the six multilingual languages (pt 0.024 and es 0.038); de/fr/it/nl remain above it (worst nl 0.104).

  • Decisions, not text

    LLMs generate text. Tachyone produces calibrated decisions. Head-to-head against a small local model, against Jev, and against open System One scorers — with the numbers and the method notes: Compare.

  • Local-first, drop-in

    Base install runs offline with no API key. Same /v1/systemone contract as Jev; extensions (router control, hooks, predict_batch, MCP, LangChain) are additive only.

  • Portable runtimes

    Encoder, ONNX, and an optional LLM backend behind the same seam; the wire never depends on which engine answers.

Quickstart

Not yet on PyPI

Tachyone is distributed from source for now. Install directly from GitHub (requires git and Python 3.12).

git clone https://github.com/munod/tachyone
cd tachyone
uv sync
uv run tachyone --predict --preset triage --backend fake "refund please"

git clone https://github.com/munod/tachyone
cd tachyone
pip install .
tachyone --predict --preset triage --backend fake "refund please"

# Requires tachyone installed (see the uv / pip tabs)
from tachyone import TachyoneClient
from tachyone.primitives import ChoiceQuestion

client = TachyoneClient("http://127.0.0.1:8000")
result = client.system_one(
    "I need a refund for a duplicate charge.",
    {"team": ChoiceQuestion(
        instructions="Which team should handle this request?",
        criteria={"billing": "payments and refunds", "technical": "bugs and outages",
                  "sales": "pricing and upgrades", "other": "general questions"},
    )},
)
ans = result.answers["team"]
print(ans.choice, ans.confidence, ans.probabilities)

git clone https://github.com/munod/tachyone
cd tachyone
uv sync --extra serve
uv run tachyone-serve

curl -s http://127.0.0.1:8000/v1/systemone \
  -H "Content-Type: application/json" \
  -d '{"state":"hello","model":"tachyone-latest",
       "questions":{"q":{"type":"noul","instructions":"Is this a greeting?"}}}'

Benchmarks

Measured on a single RTX 3060 12GB (full tables and reproduction commands in the benchmark report).

Overall accuracy by language — multilingual checkpoint

es95.6%
pt88.5%
it88.0%
fr87.1%
de86.3%
nl66.3%

Held-out synthetic split; temperature fitted per (primitive, language). Calibrated ECE is in-sample. Multilingual LoRA at rank 64.

p50 latency — stock forward vs CUDA-graph fast path

stock10.27 ms
fast3.83 ms

mmBERT + checkpoints/multi, batch=1. 2.68× p50 speedup; p95 11.05 → 4.12 ms.

How it compares

Mirrors the canonical table in overview.md.

Jev Laya Needle Tachyone
Wire contract /v1/systemone (hosted) /v1/systemone (self-hosted) Own tool/embedding API Jev-exact, self-hosted
Hosted dependency Required None None (device engine) None in core
LLM backend — No (encoder only) No Yes (optional)
Encoder backend Own model Yes Yes (2-bit) Yes (ModernBERT/mmBERT + LoRA)
ONNX backend No Yes Yes Yes (onnx extra)
MCP / LangChain No Yes No Yes
Multilingual Yes Yes (mmBERT) Partial Yes (100+ routed, 6 trained)
Fast path Proprietary No Quantized CUDA graphs (fast extra)
Extension model n/a Router, hooks Grammar, telemetry Router, hooks, batch (additive)
License Proprietary service Apache-2.0 Open Apache-2.0

Start here