Skip to main content

cloture

CI PyPI Live WASM Playground License: MIT Zero External Crates Zero Python Deps

End the multi-agent debate the millisecond the math proves who won — and catch when your judge panel is 2 correlated votes wearing 9 trench coats.

Try it now with zero install: Live Browser Playground (243 KB / 81 KB gzipped zero-import Rust WebAssembly) — click "Real RewardBench (11 LLMs × 2,985)", paste your own judge CSV privately (zero backend upload), run live Monte Carlo stopping races, or stress-test ActivePPI under adversarial judge inversion.

cloture is a zero-dependency Rust core (cloture-core) + single 2.91 MiB static CLI/MCP binary (cloture) + zero-dependency Python SDK (cloture) + 243 KB zero-import WebAssembly JS/TS SDK (js/cloture.mjs) + C ABI (include/cloture.h) for sub-microsecond anytime-valid consensus stopping, correlated-panel auditing, sequential agent racing, active prediction-powered evaluation, poisoning-resistant fusion, and distributed <1 KB evidence monoids.

Real-world AllenAI RewardBench frontier judge collapse, LOO pruning, and paired racing

  • Zero external Rust crates (Cargo.lock is 15 lines; std only).
  • Zero Python runtime dependencies (import cloture cold-starts in 24.8 ms vs 201 ms NumPy / 849 ms SciPy / 2,075 ms ppi_py).
  • Zero-import 243 KB WebAssembly (81 KB gzipped) running in browsers, Node.js, Deno, Bun, and Cloudflare Workers (js/cloture.mjs).
  • Frontier-beating speed across both batch & streaming: 16.0 ns/step EB-CS batch (25.7× faster than confseq C++, 1.10× faster than expectation offline batch, 297× faster than expectation in Python streaming), 330 ns BettingCS (415× faster than confseq.hedged_cs), 26.0 ms 9×1,000 PanelAudit (55.7× faster than NumPy/SciPy), 668 ns AscdStopper (85.5× faster than NumPy), 11,276× faster paired racing than bayesbench, and 3,294× faster online conformal than online-cp.
  • Built-in JSON-RPC 2.0 MCP server (cloture mcp, 67.6 µs median roundtrip), native --csv auditing (cloture audit --csv), and one-command self-benchmark (cloture bench).
  • Battle-tested across Linux, macOS, Windows & WebAssembly: 282 / 282 tests passing (65 Rust core + 3 Rust CLI + 213 Python/CLI/MCP/adversarial breaker + Node.js WASM suite).

Real-World Frontier Receipt: AllenAI RewardBench (2,985 Items, 11 Models, 23 Strata)

We evaluated cloture directly on official per-item verdicts from allenai/reward-bench-results (zero synthetic data — full report in docs/REAL_WORLD_EVAL.md, reproduce with python3 benchmarks/real_world_rewardbench.py):

  • 7 Frontier Generative LLMs (GPT-4o ×2, GPT-4o-mini, Gemini-1.5-Flash, Llama-3.1-405B/70B, Gemma-2-27B) deliver only 2.21 effective independent votes (95% CI [2.11, 2.31], +4.65 pp Condorcet illusion gap, p = 0.00050, audited in 67.2 ms). Within-family error correlation is φ = 0.504 (GPT-4o pair 0.587) vs. cross-family φ = 0.317.
  • Pruning 8 of 11 frontier models (11 → 3) raises accuracy +3.85 pp (92.03% → 95.88%) at -72.7% lower API cost — beating the single best model (Skywork-Gemma-27B-RM, 94.97%) by +0.90 pp.
  • Real 6-model paired AgentRace: Certified the true winner (GPT-4o 2024-08) on 50 / 50 (100%) shuffled RewardBench streams while saving 80.4% of model evaluations (3,513 vs. 17,910).
  • Real Active-PPI++ (GPT-4o-mini proxy → GPT-4o, 10% audit): 100% anytime coverage across all 2,985 sequential steps (10.46× variance reduction) while eliminating -12.41 pp proxy bias.

10-Second Quickstart

Install

# Python SDK (universal py3-none wheel, zero runtime deps)
pip install cloture

# Single static CLI & MCP binary (SHA-256 verified, rate-limit-free)
curl -fsSL https://raw.githubusercontent.com/pgg898200-ship-it/cloture/main/scripts/install.sh | sh

# Homebrew (macOS & Linux — installs `cloture` binary + `cloture.h`)
brew install pgg898200-ship-it/cloture/cloture

# Or build from source (~18s, zero external crates)
cargo build --release --workspace && ./target/release/cloture bench

1. Stop parallel async LLM/agent rollouts the millisecond consensus is certified

import asyncio
import cloture

# Category-agnostic CITE: works over arbitrary strings, code patches, SQL, or JSON
result = await cloture.consensus(
    spawn_fn=lambda i: call_agent_async(prompt, seed=i),
    delta=0.05,
    max_calls=32,
    concurrency=8,
)
print(result.winner, f"certified in {result.n_samples}/32 calls (cancelled {result.n_cancelled} in-flight)")

# Grey-box ASC-D: pass OpenAI/vLLM logprobs for 40%–92% fewer trajectories
probs = cloture.extract_openai_logprobs(chat_completion, ["A", "B", "C", "D"])
stopper = cloture.AscdStopper(k=4, delta=0.05, max_budget=64)
dec = stopper.update(probs)

2. Audit a correlated multi-agent / LLM-as-a-judge panel

import cloture

# Direct 1-line audit of any CSV, JSONL, or Promptfoo JSON export (zero pandas required!)
res = cloture.audit_csv("judges.csv", gold_col="gold", strata_col="domain")
print(f"{res.report.k_judges} judges -> {res.report.n_eff_kish:.2f} effective votes | prune: {res.prunable_judges()}")

# Or pass integer vote matrices directly (N x K)
report = cloture.audit_panel(votes, gold, n_perms=2000, n_condorcet_sims=2000, n_boot=1000)
print(f"Condorcet gap: {report.condorcet_gap*100:.1f} pp | permutation p={report.permutation_p_value:.5f}")

3. Stream from stdin, audit CSVs from CLI, or attach as an MCP server

# Audit any CSV export straight from the static binary (<26 ms for 9 x 1,000!)
cloture audit --csv judges.csv --gold-col gold --strata-col domain --perms 2000

# Halt an open-ended vote stream the millisecond CITE certifies a winner
printf '42\n42\n42\n42\n42\n42\n42\n42\n42\n42\n' | cloture stop --mode cite --delta 0.05

# Grey-box ASC-D stopping on streamed probability vectors
printf '[0.9,0.05,0.05]\n[0.88,0.07,0.05]\n' | cloture stop --mode ascd --k 3 --delta 0.05

# Run built-in Rust microbenchmarks on your CPU
cloture bench

# Start zero-dependency JSON-RPC 2.0 MCP server over stdio (Claude Code / Cursor / Codex)
claude mcp add cloture -- cloture mcp

Verified Head-to-Head Benchmarks (v0.2.0)

cloture consensus stopping and correlated judge-panel collapse

cloture head-to-head throughput and statistical validity vs PyPI competitors

All numbers below were measured live on Intel Xeon @ 2.30 GHz (2 vCPU), Python 3.12.16, Rust 1.100.0, against real PyPI packages (confseq==0.0.11, ppi-python==0.2.3, expectation==0.6.1, online-cp==0.4.0, bayesbench==0.4.0.dev0, numpy==1.26.4, scipy==1.15.3). Full raw receipts live in benchmarks/results.json; reproduce with PYTHONPATH=python .venv/bin/python benchmarks/run_benchmarks.py.

1. Multi-Agent Consensus Stopping (delta = 0.05, 200 trials/regime)

Regime cloture.AscdStopper (Grey-Box) cloture.CiteStopper (Unbounded) Fixed-64 / Fixed-256 Naive Peeking (p < 0.05)
Easy (K=4, gap 0.45) 21.0 calls (100% acc, 67.2% saved vs 64, 91.8% vs 256) 58.7 calls (100% acc) 64 / 256 (100% acc) 21.0 calls (100% acc)
Medium (K=4, gap 0.25) 38.7 calls (100% acc, 39.5% saved vs 64, 84.9% vs 256) 141.0 calls (100% acc) 64 (99.5%) / 256 (100%) 46.1 calls (100% acc)
Hard (K=4, gap 0.12) 127.5 calls (100% acc, 50.2% saved vs 256; budget=64 lock: 55.4 calls, 99.0% acc) 245.3 calls (98.5% acc) 64 (86.5%) / 256 (98.5%) 118.1 calls (96.0% acc)
Exact-Tie Null (K=4, gap 0.00) 0.0% false cert 0.0% false cert — 28.5% false cert (5.7x violation)
Open-Ended Zipf (K=200, gap 0.30) — (requires known K) 70.9 calls (100% acc, 72.3% saved vs 256) 256 (100% acc) 26.0 calls (100% acc)
Open-Ended Tie Null (K=200) — 0.5% false cert (<= 5%) — 30.5% false cert (6.1x violation)
CPU Latency (K=4 ASC-D) 668 ns Py batch / 684 ns Rust (85.5× faster than NumPy 57.1 µs, 25/25 exact stop parity) 210 ns Py batch / 209 ns Rust — —

2. Correlated-Panel Audit (K=9 judges, N=1,000 items, 2k perms + 2k Condorcet MC + 1k bootstrap)

Metric cloture.audit_panel Vectorized NumPy / SciPy Ref Result
Median Wall-Clock 26.0 ms (14.7 ms binary exact DP) 1,446.7 ms 55.7× faster (max_det_diff = 2.66e-15)
Effective Votes (n_eff) 2.21 Kish (95% CI [2.10, 2.34]) / 2.13 Eigen Identical (1.3e-15 diff) 9 judges behave like 2.2 independent votes
Condorcet Gap & Omnibus p +20.43 pp (94.91% null vs 74.48% actual), p = 0.0005 p = 0.0005 Correlated errors destroy majority lift
LOO Redundant-Judge Pruning Drop 1 judge (#6): +1.52 pp acc, -11.1% cost; Drop 2 (#6,#8): +2.72 pp acc (74.5% -> 77.2%), -22.2% cost Identical Fewer, less-correlated judges win

3. Realized vs. Population Correlated Rollouts (rho = 0.60, 30 prompts x 16 rollouts, delta = 0.05)

Method Null False-Fire (theta = 0, 300 reps) Power (theta = +0.25, same 480-rollout budget)
Naive Pooled Z-test 33.0% (broken) —
Naive Pooled Empirical-Bernstein CS 40.0% (broken) —
Single-Unit Consensus Misfire 17.3% prompt 0 (99.3% of reps have >=1 bad prompt) —
cloture.PopulationCert 0.7% (exact <= 5%; rho_hat = 0.60, ceiling 1.69) 27.3% at 30x16 -> 88.0% at 120x4 (guided by optimal_rollouts)

4. Anytime-Valid Confidence Sequences & Racing vs. Real PyPI Competitors (alpha = 0.05)

Engine / Library Anytime Miscoverage (500 x 1k, p=0.7) Width @200 / @1000 Throughput (ns/step) Notes
cloture.EmpiricalBernsteinCS 1.0% 0.218 / 0.110 16.0 ns Py batch / 29.7 ns Rust / 3.68 µs Py stream 25.7× faster than confseq C++, 1.10× faster than expectation batch, 297× faster than expectation stream
cloture.BettingCS(G=201) 3.6% 0.190 / 0.095 (tightest) 281 ns Rust / 330 ns Py batch / 5.12 µs Py stream 415× faster & tighter than confseq.hedged_cs via active-cell pruning
confseq.predmix_empbern_cs (C++) 1.0% 0.222 / 0.112 410 ns batch-100k 25.7× slower than cloture EB-CS batch
confseq.hedged_cs(201) 0.0% (30 trials) 0.214 / 0.119 137,003 ns batch-1k 415× slower than cloture.BettingCS
expectation.EmpiricalBernsteinCS (Rust) 0.0% (chunk-50) 0.284 / 0.120 17.6 ns single-call final-only / 1,093,127 ns 1-step stream Slower than cloture on both single-call batch (1.10×) and 1-step Py streaming (297×)
Naive CLT / Wald Peeking 53.8% (10.8x violation) 0.127 / 0.057 83.6 ns Invalid under continuous monitoring

Multi-Arm Racing (6 arms, 200 tasks, 1,200 Fixed-N evals):

  • cloture.AgentRace(paired=True): 299.9 evals (75.0% saved), 100.0% accuracy, 0.0% null FWER.
  • cloture.AgentRace(paired=False) (LUCB): 709.0 evals (40.9% saved), 100.0% accuracy, 0.0% null FWER.
  • vs. bayesbench: On a 6-arm 200-task race, cloture.AgentRace(paired=True) finishes in 2.60 ms (306 evals) vs. bayesbench.BayesianRanker 29,274 ms (1,200 evals, 11,276× faster). On exact-tie 0.50 vs 0.50 pairwise nulls (30 trials), bayesbench.compare false-certifies 40.0% vs. cloture.PairedEProcess 0.0%.

5. Active-PPI++ vs. ppi-python, Human-Only CS, & Adversarial LLM Judges

Scenario cloture.ActivePPI ppi-python (Peeking every 200) ppi-python (Single Fixed Horizon) Human-Only EB-CS (10%) Naive LLM Judge
Accurate Biased Judge (r=0.92, +0.15 bias, N=4000, 10% audit) 99.0% anytime cov, width 0.146, 6.29× var red, 1.46× eff mult, 0.98 ms batch 71.0% cov (breaks under peeking!), 19.8 ms 96.0% cov, width 0.054 (tighter iff no peeking), 1.03 ms 99.0% anytime cov, width 0.177, 2.10 ms 0.0% cov (+0.15 bias)
Adversarially Inverted Judge (f = 1 - y, N=2000) 99.0% anytime cov (lambda_hat = 0.0000) — 94.0% fixed cov 100.0% anytime cov 0.0% cov

6. SafeFuse Quarantine, AbortCascade, OnlineConformal vs. online-cp, & 712-Byte EvidenceSketch

  • SafeFuse (5 agents, 2 poisoned at t=200, 50 trials): quarantines both poisoned agents on 100% of runs (median 94 steps), 0.0% clean-null FWER (and <= 0.75% even under adversarial heavy-tailed 20*Bern(0.05), Exp(1), and left-skewed {0, 1.05} nulls), reducing cumulative loss by -200.0 vs. uniform averaging (and beating the oracle clean mean by -2.74).
  • AbortCascade (500 cal / 500 test, 50 trials, target recall 0.92): achieves 92.6% mean test recall (vs. naive uncalibrated 0.35 threshold collapsing to 66.1%) while saving 38.2% of failed-episode compute (27.8% total compute).
  • OnlineConformal (4-rate AgACI, abrupt shift at t=1000, target 90%): 59.7 ns/step Rust / 1.97 µs Python — 3,294× faster (Rust) / 99.7× faster (Python) than online-cp SimpleJumper (196.8 µs) and 136× faster than online-cp ConformalRidgeRegressor (269.4 µs). Post-shift coverage recovers to 94.4% vs. online-cp CRR 68.0% and fixed unadapted 33.5%.
  • EvidenceSketch: fixed 712-byte wire format (b"CLTR" + FNV-1a 64-bit checksum), 70.5 ns Rust merge, 0.0 exact diff across 1,000-worker fleet merge (100,000 obs) and exact Leave-One-Out subtraction.

Engines & Module Map

Engine Rust (cloture-core) Python (cloture) CLI / MCP / WASM Mathematical Foundation
1. Consensus Stopping mode::{AscdStopper, CiteStopper, PopulationCert} AscdStopper, CiteStopper, PopulationCert, consensus(), consensus_dist(), extract_openai_logprobs() cloture stop, cloture_mode_stop, cloture_population_cert, js/cloture.mjs Grey-box ASC-D (2026), unbounded Kraft-IUT CITE (2026), deterministic budget lock, unit-level PopulationCert (Nov 2026)
2. Correlated-Panel Audit panel::{PanelAudit, OnlinePanelTracker} audit_panel(), audit_csv(), audit_jsonl(), audit_promptfoo(), OnlinePanelTracker cloture audit [--csv], cloture_audit_panel, js/cloture.mjs Kish & Jacobi Eigenvalue $n_{\text{eff}}$, exact Poisson-Binomial / stratified Condorcet null & permutation test, Krippendorff's $\alpha$, LOO pruning
3. Anytime-Valid CS, Racing & Active-PPI++ betting::*, race::{AgentRace, e_bh_discoveries}, ppi::ActivePPI EmpiricalBernsteinCS, BettingCS, PairedEProcess, AgentRace, race_agents(), e_bh_discoveries(), ActivePPI cloture race, cloture ppi, cloture_agent_race, cloture_active_ppi, js/cloture.mjs Predictable plug-in EB-CS & Active-Cell Hedged ONS Betting CS (JRSS-B 2024), LUCB + paired e-process racing, e-BH (2022), centered affine Active-PPI++
4. Safe Fusion & Abort Cascades fuse::SafeFuse, cascade::{AbortCascade, OnlineConformal} SafeFuse, AbortCascade, OnlineConformal cloture_safe_fuse, js/cloture.mjs Scale-Free BOA + unclamped Fan-inequality quarantine over max(LOO mean, LOO median), Conformal Risk Control (CRC), 4-rate AgACI
5. Distributed Evidence Monoid sketch::EvidenceSketch EvidenceSketch Rust / C / Python / WASM Fixed 712-byte associative, commutative wire monoid with exact LOO subtraction

Honest Scope Boundaries

  • Single-shot fixed-horizon PPI without peeking: If you collect a single static dataset, look once at N, and never monitor sequentially, asymptotic normal ppi-python produces tighter intervals (0.054 vs. 0.146) because it does not pay the finite-sample anytime-valid O(log log t) and bounded-range Fan-inequality price. Use cloture.ActivePPI whenever you stream, peek, stop early, or need worst-case finite-sample protection against biased/adversarial judges.
  • Population vs. unit certificates: AscdStopper and CiteStopper certify the modal answer of a single prompt's rollout distribution. To certify deployment-level superiority across prompts under correlated rollouts, always aggregate unit means in PopulationCert.

Documentation & Agent Discovery

License

Licensed under the MIT License (LICENSE / NOTICE).

Metadata

Release files for cloture 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for cloture 0.2.0
File Actions
cloture-0.2.0-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details for cloture-0.2.0-py3-none-win_amd64.whl
cloture-0.2.0-py3-none-manylinux_2_28_x86_64.whl Python 3 none Linux glibc 2.28+ x86-64 Details for cloture-0.2.0-py3-none-manylinux_2_28_x86_64.whl
cloture-0.2.0-py3-none-manylinux_2_28_aarch64.whl Python 3 none Linux glibc 2.28+ ARM64 Details for cloture-0.2.0-py3-none-manylinux_2_28_aarch64.whl
cloture-0.2.0-py3-none-macosx_11_0_x86_64.whl Python 3 none macOS 11.0+ x86-64 Details for cloture-0.2.0-py3-none-macosx_11_0_x86_64.whl
cloture-0.2.0-py3-none-macosx_11_0_arm64.whl Python 3 none macOS 11.0+ ARM64 Details for cloture-0.2.0-py3-none-macosx_11_0_arm64.whl

Total release size: 3.6 MB

Release files / cloture-0.2.0-py3-none-win_amd64.whl

Download URL cloture-0.2.0-py3-none-win_amd64.whl
Size 282.6 kB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
855df8f1b8aeeaf8d20e54c658f6bd18b61088291970d4964f96b1954aeb60f0
BLAKE2b-256 checksum
How to use checksums
543bfb287167b12d9fa39627e6ee35e3da9609dd0a10b6a13556f7f04baaced3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 22, 2026.

Transparency log

Release files / cloture-0.2.0-py3-none-manylinux_2_28_x86_64.whl

Download URL cloture-0.2.0-py3-none-manylinux_2_28_x86_64.whl
Size 1.4 MB
Tags Linux glibc 2.28+ x86-64 Python 3
SHA-256 checksum
How to use checksums
c8810e13a883c884bd9484545dad7121a12311bebfd5d09f24c598620fbbbf05
BLAKE2b-256 checksum
How to use checksums
30006c7531e842522b62bc30bb86802b969b4ccee49782fd8149e5e1de9ac52c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 22, 2026.

Transparency log

Release files / cloture-0.2.0-py3-none-manylinux_2_28_aarch64.whl

Download URL cloture-0.2.0-py3-none-manylinux_2_28_aarch64.whl
Size 1.2 MB
Tags Linux glibc 2.28+ ARM64 Python 3
SHA-256 checksum
How to use checksums
26a382a787f98607f626bd968e06f757a167ad4f4976299c829fd983bf58ae5e
BLAKE2b-256 checksum
How to use checksums
379c79b3359a8fa4daa9f91190a3dbc8a0776b2cbe41016cef82031198267d7e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 22, 2026.

Transparency log

Release files / cloture-0.2.0-py3-none-macosx_11_0_x86_64.whl

Download URL cloture-0.2.0-py3-none-macosx_11_0_x86_64.whl
Size 381.7 kB
Tags Python 3 macOS 11.0+ x86-64
SHA-256 checksum
How to use checksums
89907363e9e230f3ac6285e1e2ca8333eec007b167ec17ab15854e6e2ca4b8ae
BLAKE2b-256 checksum
How to use checksums
3f1e9d6d6672f8ad7df7788734b029691876d6aea62a1ea0b7e15c33f37aa235
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 22, 2026.

Transparency log

Release files / cloture-0.2.0-py3-none-macosx_11_0_arm64.whl

Download URL cloture-0.2.0-py3-none-macosx_11_0_arm64.whl
Size 370.5 kB
Tags Python 3 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
4e49dcd1a7add690602563485ded7e2602079fc67f2bb1ca01e4a85051a35ba1
BLAKE2b-256 checksum
How to use checksums
75c4a6d34e038c1128c0c4d59defb87521701387af43e7ddd71d8b0180072927
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 22, 2026.

Transparency log

Security for cloture 0.2.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 5 files in this release have been uploaded with provenance metadata.

Select from 5 files

Attestation for cloture-0.2.0-py3-none-win_amd64.whl

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 22, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.2.0 This release

5 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page