Havuz

让 AI 与人类一起攻克真正的科学难题 —— 12 阶段 55 门 · 36 工具 · 98 条技能 · 证据链与可复现

Trace changed experiment results to the numbers, claims and figures in your LaTeX paper. Offline bilingual review, safe numeric patches and

The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayab

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augment

从选题到可复现发布：十个可独立安装的科研 agent skill —— 顶会/期刊论文、科研绘图、基金 proposal 撰写、方法迭代到 SOTA、冷审与代码数据发布。Ten installable agent skills for research: scientific f

42 AI agent skills for literature review, academic writing, citation verification, conference submission, rebuttal, publication, and present

Autoresearch agents that improve your benchmark: independent re-measurement, enforced budgets, results as pull requests

Personal finance agent that decides whether an expense is safe — pay in full, split, use installments, or wait — from a 90-day balance forec

Find which script, notebook, data, command, or AI agent produced a file — locally, with evidence and honest uncertainty.

Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, b

A state machine protocol for running controlled ML experiments with coding agents.

VeriRepro: Evidence-grounded reproduction for computational papers.

PaperBench High-Difficulty and Expanded Tasks: paper reproduction beyond machine learning. 93 tasks in 12 research areas, run in domain-nati

Static reproducibility checks, experiment replay, and verification for ML pipelines.

An auditable and reproducible evaluation suite for LeWM-compatible latent world models, with official-compatible and difficulty-controlled p

面向学生和研究者的 AI 论文教练：自动生成结构化解读、复现 指导、七问回答与可追踪历史记录。

Reproduction package for "Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity" — ten agent arms across AppWorld an

llama.cpp speculative decoding measured on one RTX 3090, Qwen3.6-35B-A3B UD-Q4_K_XL, commit 3737e4137. Published figures are re-derived from

Elbi gives your data agent a verified fact store.

Build system for AI coding-agent context. Generate deterministic, explainable context artifacts for Claude, Codex, Cursor, and MCP.

Research Software Engineering skills for AI coding agents

A scientific-method runtime for AI agents: hypotheses, experiments, evidence, provenance, reproducibility, and auditable conclusions.

High quality README generation for reproducible research projects in R.

AMBER (sealed-in-amber historical replay evaluation): real-event replay, physical sealing, pre-registered scoring — method spec; cases priva

ALGAL is a programming language for agents. Programs pause for approvals, survive restarts, replay from recorded effects, and improve throug

Caveman prompting, measured. A two-channel evaluation framework for prompt compression and LLM token efficiency: what input vs output compre

Convert scientific papers into executable, reproducible codebases

Catch local LLMs spilling into the CPU. One run shows GPU placement, prefill, decode, memory, power and a verdict.

Big Research：独立第三方 AI 辅助科研插件。研究者主导问题、方法与判断，支持 Codex 和 Claude Code，提供证据追踪、本地 MCP 和交互视图。

A curated bundle of 38 Claude Skills for quantitative, qualitative, experimental & mixed-methods research in business, finance & social scie

Deterministic symbolic codes for embedding vectors. Byte-identical across CPUs and languages, content-addressed, diffable and verifiable. C

Reproducible artifact manifests, sandbox-output verification, and evidence-bundle validation for artifact-heavy workflows.

PromptLedger, prompt şablonlarını fingerprint ile sürümleyip aday yanıtları karşılaştıran ve sonuçları tekrarlanabilir raporlara dönüştüren bir Python aracı ile Go CLI sunuyor.

Neden yükseliyor · 25 günlük bir repo için 35 yıldız dikkat çekiyor; ancak son 28 günde yalnızca 1 commit ve 1 farklı yazar var. Bu nedenle ilginin kalıcı benimsemeye dönüştüğünü gösteren yeterli aktivite kanıtı henüz yok.