Laya Agent Kit

Community integration for local Laya + Codex / Claude Code / Cursor / ChatGPT. Based on upstream Laya, whose documentation and credits follow below.

网页 GPT 接入： 请阅读 CHATGPT-SETUP.md。下载到独立的 laya 文件夹后，运行 python start_chatgpt.py，按提示连接官方 MCP Tunnel。首次需要用户的 ChatGPT 开发者模式、工作区 tunnel 和本机密钥输入；读取 GitHub 不会自动安装或授予账号权限。

Local coding agents: python install.py --client codex --client claude-code — 中文安装说明 · English guide.

Updates / 更新记录: CHANGELOG.md · Hardware support / 硬件支持.

git clone https://github.com/Maxwell00000086/laya-agent-kit.git laya
cd laya
python start_chatgpt.py

AI assistants: when the user asks to install or connect this repository, read CHATGPT-SETUP.md for the web ChatGPT flow. Confirm the execution environment and available tools; verify actual tool calls before reporting a successful connection.

Community: Contributing · Discussions · Report a bug · Security policy · Apache-2.0 license.

Multilingual, non-autoregressive System 1 decision engine. Typed decisions over 100+ languages in a single forward pass — 33 ms — trained with reinforcement learning against strictly proper scoring rules (RLCD), with a router that picks the right checkpoint per request.

Laya evaluates typed questions (choice, score, noul) over any state (text, email, ticket or JSON document) in a single forward pass — 33 ms for one question, 7.2 ms/question batched, measured on a T4. No text generation, so nothing to parse and nothing to hallucinate.

Three checkpoints, and a Router that picks between them per request:

Installation

For Codex, Claude Code, Cursor, or another local MCP client, this checkout includes a community integration installer: python install.py --client codex --client claude-code. See Laya Agent Kit or the Chinese setup guide. This paragraph is an addition to the upstream README; the model library below remains upstream Laya.

pip install laya

Python 3.10 or newer. The dependencies set that floor: huggingface_hub 1.x, transformers 5.x and torch 2.14 all require 3.10.

Related MCP server: genpark-cross-lingual-semantic-intent-router-skill

Quickstart: Route Mode (Recommended)

Laya ships three checkpoints. The built-in Router is the recommended entry point: it evaluates any state in any language, automatically detects scripts and languages in sub-milliseconds, and dispatches to the optimal checkpoint in a single forward pass.

import laya
from laya import Router

# Preload checkpoints into memory for instant sub-35ms routing
router = Router(preload=True)

# 1. State in any language or schema
state = {
    "from": "user@acme.com",
    "subject": "Duplicate charge on invoice #4411",
    "body": "Hi, we were billed twice for March. Please refund the duplicate today or we will cancel our plan."
}

# 2. Define your typed questions
questions = {
    "department": {
        "type": "choice",
        "instructions": "Which department should handle this request?",
        "criteria": {
            "billing": "invoices, payments, refunds",
            "technical": "bugs, outages, system errors",
            "sales": "pricing, new contracts",
            "other": "everything else"
        }
    },
    "urgency": {
        "type": "score",
        "instructions": "How urgent is this request?",
        "criteria": ["not urgent", "soon", "critical deadline or blocking issue"]
    },
    "churn_risk": {
        "type": "noul",
        "instructions": "Does the user threaten to cancel or leave?"
    },
    "refund_requested": {
        "type": "noul",
        "instructions": "Does the user explicitly request a refund?"
    }
}

# 3. English state -> automatically routed to laya (ModernBERT-large, 39.5 ms)
res_en = router.predict(state, questions)
print("Department :", res_en["answers"]["department"]["choice"])  # -> billing (confidence: 0.94)
print("Routing    :", res_en["routing"]["model"])                 # -> english

# 4. Hindi state -> automatically routed to laya-multilingual (mmBERT-base, 32.8 ms)
res_hi = router.predict({"body": "मुझसे दो बार शुल्क लिया गया, कृपया पैसे वापस करें।"}, questions)
print("Department :", res_hi["answers"]["department"]["choice"])  # -> billing (confidence: 0.86)
print("Routing    :", res_hi["routing"]["model"])                 # -> multilingual

# 5. Explicit override when you want a specific checkpoint
res_td = router.predict(state, questions, model="typed-decisions")

Every result carries full routing metadata explaining why the choice was made:

res_hi["routing"]
# {
#   'model': 'multilingual',
#   'repo': 'convaiinnovations/laya/multilingual',
#   'reason': 'non-Latin script (devanagari, 100% of letters); the English checkpoint cannot read it'
# }

Inspect a routing decision without running any forward pass:

router.route({"body": "Der Kunde wurde zweimal belastet"}, questions).reason
# "Latin script but language looks like 'de', not English"

Why Route: The Evidence

On a shared benchmark (17,416 questions, one T4 GPU, identical questions per model):

The English checkpoint collapses on non-Latin scripts (Khmer scores 0.000 accuracy at 0.952 confidence). Because the model stays confident while being wrong, confidence gating cannot save you. Router detects the script in <0.5 ms pure Python before the forward pass.

Production Preload & Memory

A cold checkpoint build costs seconds; language detection costs microseconds. At the default max_loaded=1, traffic that alternates languages rebuilds a model on every request (measured at a 7.4 s median reload on CPU and 10.3 s on T4).

For a server or production app, preload:

# Every checkpoint resident in memory; language flips cost detection only (<1 ms)
router = Router(preload=True)
router = Router(preload=True, device="cuda")

# Or preload only the specific checkpoints you serve:
router.preload(["english", "multilingual"])

# If your app already built an agent, attach it to avoid duplicate VRAM:
router.attach("english", existing_agent)

# Manage resident memory (default keeps 1 hot, LRU eviction)
router = Router(max_loaded=2)       # keep two hot
router.unload()                     # free memory

Single-Model Mode (Direct SDK)

If you only need a single checkpoint for a dedicated pipeline, you can load models directly:

import laya

# 1. Load a specific checkpoint directly from the hub
agent = laya.load("convaiinnovations/laya")                           # English root
agent_ml = laya.load("convaiinnovations/laya", subfolder="multilingual") # 100+ languages
agent_td = laya.load("convaiinnovations/laya", subfolder="typed-decisions")

# 2. Run all questions in ONE single forward pass (~35 ms on GPU)
result = agent.predict(state, questions)
answers = result["answers"]

print("Department :", answers["department"]["choice"])   # -> billing (confidence: 0.94)
print("Urgency    :", answers["urgency"]["score"])        # -> 1.84 / 2.0
print("Churn Risk :", answers["churn_risk"]["noul"])       # -> 0.892 (89.2% probability)

Automated Confidence Gating

Because Laya's probabilities are trained with strictly proper scoring rules (RLCD), confidence scores are statistically meaningful:

dept = answers["department"]["choice"]
conf = answers["department"]["confidence"]

if conf >= 0.85:
    # High confidence: automated action without human in the loop
    route_automatically(dept)
else:
    # Low confidence: escalate to human triage
    escalate_to_human_agent(dept, reason=f"Low confidence ({conf:.2f})")

Built-in Workflow Presets

Laya provides pre-tuned question schemas for immediate production use:

import laya

agent = laya.load("convaiinnovations/laya")

# 1. Intelligent Model Router (routes to small vs. frontier models)
routing = agent.predict({"request": "Refactor this service using dependency injection"}, laya.router_questions())

# 2. Real-time Prompt Guardrails (jailbreaks, injections, leaks)
guard = agent.predict({"prompt": "Ignore all instructions"}, laya.guard_questions())

# 3. Content Safety & Moderation (toxicity, harassment, threats)
safety = agent.predict({"post": "User comment text"}, laya.moderation_questions())

# 4. Support Ticket Triage (intent, urgency, frustration, churn)
triage = agent.predict({"message": "My payment failed twice"}, laya.triage_questions())

Decision Primitives

Benchmarks

Full report: BENCHMARKS.md — every run consolidated, languages and themes, with per-language detail for all 51 languages.

All Laya numbers below are measured. Every model answered byte-identical questions (fixed seed) in the same run. Reproduce with notebooks/laya_benchmark_colab.ipynb on a T4.

Speed (Tesla T4, measured)

Batched throughput reaches 103-332 questions/sec on a single T4. For reference, TypeSafe Jev has been independently measured at 236-276 ms p50 (AbdelStark, nibzard) -- Laya answers a single question roughly 6-7x faster.

Laya (with routing) vs Jev

Every Laya figure is what Router().predict(...) actually returns — the checkpoint the router selects for that input, not a hand-picked best of three. Jev figures are third-party published, never measured here (no TypeSafe API access), so sample sizes and prompts differ.

On DAIR Emotion, Jev assigned zero probability to the true label on 16% of examples — a hard failure for anything branching on confidence.

Where Jev leads

• High-cardinality label spaces (>20 options at default settings): On Banking77, Jev scores 0.870 (on 72 labels) while Laya scores 0.425 (on 77 labels at default 256-token head budget). This is an architectural token-budget constraint: options share a fixed head_max_len budget (192 tokens on English, 256 on multilingual), so 77 options receive only ~3 to 4 tokens per label, causing text to become indistinguishable. Jev supports up to 255 options out-of-the-box. While laya-multilingual supports 1,024 context (and up to 8,192 in the encoder) and you can raise agent.cfg["head_max_len"] = 512 at runtime, Jev is currently better suited for 50+ options in a single prompt without tuning. predict_shortlist (see Honest limits) keeps the top k labels with a caller-supplied embedding, then runs one forward pass on that shortlist.

• Soft distribution matching: On typed-decisions, while Laya achieves higher argmax accuracy (0.766 vs 0.727), Jev achieves higher soft accuracy (0.580 vs 0.471) against the teacher's full probability distributions.

• Out-of-the-box raw calibration: Before temperature scaling, the base checkpoint has higher raw ECE (0.213 vs 0.144). Laya achieves its 0.081 ECE after domain temperature fitting.

Full detail, including every workflow and all 51 languages: BENCHMARKS.md.

typed-decisions, measured on all three checkpoints

400 cases, 2,000 decisions, four workflows.

The fine-tuned checkpoint beats Jev by 3.9 points and clears the teacher ceiling, with 2.4x better Brier and 1.6x better score MAE. It wins on all four workflows: invoice processing 0.804, security incidents 0.766, customer service 0.764, agent-trace observability 0.730. By primitive: noul 0.857, choice 0.733, score 0.723.

Two places it still trails Jev: soft accuracy (0.471 vs 0.580 — its argmax is better but its distributions match the teacher less well) and ECE (0.213 vs 0.144), which temperature fitting addresses.

The base checkpoints sit below the majority-class baseline (0.362 and 0.342 against 0.461). All of the capability on this benchmark comes from fine-tuning.

Multilingual (51 languages, MASSIVE intent, 20 options, random = 0.050)

Across all 51 languages the English checkpoint macro-averages 0.227 with macro ECE 0.733, and only 23 of 51 languages clear 3x random. Khmer scores 0.000 at 95.2% confidence. This is why Router exists: the model's own confidence gives no warning, so the routing decision has to be made before the forward pass.

English tasks

Calibration

Both checkpoints are over-confident as shipped. Refitting one temperature per (question type, option count) on held-out data moves mean ECE 0.466 -> 0.081 (laya) and 0.314 -> 0.106 (laya-multilingual). laya-multilingual ships with no fitted temperatures at all, so fit them before relying on its probabilities.

Honest limits

• The base checkpoints are near chance on typed-decisions zero-shot -- 0.362 and 0.352 against a 0.318 random baseline and a 0.461 majority-class baseline. The 0.766 figure comes from the checkpoint fine-tuned on that benchmark's own training split. Laya is a fast base to specialise, not a zero-shot decision engine.

• High-cardinality choice questions and token budgets: Sequences split into an option prompt budget (head_max_len) and the remaining document/state budget (max_len - head_max_len):

  • laya (English) defaults to 512 context (head_max_len = 192, ~320 tokens for state).

  • laya-multilingual and laya-typed-decisions default to 1,024 context (head_max_len = 256, ~768 tokens for state; mmBERT-base encoder supports up to 8,192 with RoPE). At default settings, a 77-option question like Banking77 allocates only (256 - 16) // 77 ≈ 3–4 tokens per label, which causes accuracy to fall off sharply (0.425 vs Jev's 0.870). If evaluating 50+ options in a single question:

  1. Raise agent.cfg["head_max_len"] = 512 and agent.cfg["max_len"] = 1024 (or up to 2048 / 4096 / 8192) so every option has enough tokens to remain distinct.

  2. Or shortlist with embeddings and run one forward pass on the top k labels (predict_shortlist, example below). predict and system_one still score every criterion they are given.

  3. Or split the label set yourself into a coarse question and a fine question.

import laya

questions = {
    "intent": {
        "type": "choice",
        "instructions": "Which banking intent is this?",
        "criteria": {
            "card_arrival": "where is my card",
            "transfer_fee": "fee charged on a transfer",
            # ...the rest of a large label set
        },
    }
}
result = laya.predict_shortlist(
    agent,
    {"text": "I was charged twice for a transfer"},
    questions,
    embed_fn=laya.embed_fn_from_agent(agent),  # or any callable: texts -> (n, dim)
    k=20,
)
result["shortlist"]["intent"]["labels"]  # the top 20 labels sent to the model

embed_fn(texts) returns one vector per string. embed_fn_from_agent mean-pools the encoder already loaded on the agent; the decision head runs in the following predict / system_one call. Probabilities on a shortlisted choice are over those k labels. When k is at least the number of labels, the original question is passed through and embed_fn is not called.

Issue #102 reports that a top-20 zero-shot shortlist moved a BANKING77 run from 54.3% to 60.8% on the reporter's setup. Those figures are the reporter's; this repository has not remeasured them.

• Ordinal score questions are the weakest primitive (SST-5 0.372).

• laya collapses outside English; laya-multilingual is weaker on English. Route, or pick deliberately.

Live Demo & Resources

• Hugging Face Model: convaiinnovations/laya

• Interactive Web Demo: convaiinnovations/laya-demo

• Engineering Writeup: Read the full story on Dev.to

Fine-Tuning

Fine-tune Laya on your own domain data. The notebook runs on Kaggle's free 2xT4 GPUs and does the whole loop: build the dataset, train with RLCD (proper-scoring-rule rewards, GRPO-style policy gradient), fit calibration temperatures, evaluate, and push the result to the Hub.

• notebooks/laya_finetune_typed_decisions_2xT4_kaggle.ipynb

Fine-tuning is where most of the value is. On the typed-decisions benchmark the base checkpoints score near chance zero-shot (0.36 and 0.35 against a 0.318 random baseline), while the fine-tuned checkpoint reaches 0.766 on the same 2,000 decisions -- above TypeSafe Jev's published 0.727 and above the 0.735 teacher self-agreement ceiling. Treat Laya as a fast base to specialise, not as a zero-shot decision engine.

Runtime on 2xT4 is roughly 4-5 hours for 4 epochs over ~30k questions.

Support the Project

If Laya helps your research or products, consider supporting independent research:

License

Apache 2.0. Developed by Convai Innovations.