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

给 DeepSeek Harness 用的科研文献库插件：搜论文、带出处、审批入库、把笔记线索交给同会话其他插件。Academic research library for DSH — search, cite, approve imports, hand off notes.

LaTeX and Typst editor with live collaboration and AI agents. Open-source IDE and Overleaf alternative for Mac, Windows and Linux.

Hyperresearch, Claude Code ve OpenAI Codex için web kaynaklarını toplayıp denetleyen ve araştırma sonuçlarını kalıcı, aranabilir bir vault içinde biriktiren bir deep research agent iş akışı sağlar.

Neden yükseliyor · 171 günde 3.644 yıldıza ulaşması ve son 28 günde 40 commit ile 10 farklı yazar etkinliği, ilginin yanı sıra kayda değer geliştirme hareketliliğine işaret ediyor. Claude Code ve Codex için hazır araştırma pipeline'ı, kaynak denetimi ve kalıcı vault özellikleri bu ilgiyi açıklayabilir. README'deki DeepResearch-Bench liderliği ise bağımsız üçüncü taraf doğrulaması bekleyen, dahili pilot ve projeksiyon olarak sunuluyor.

Unified research workspace for humans & agents — PDF Q&A with citations, Vault, writing. 为人与 Agent 协作的科研工作台；补齐 Zotero 时代的人机上下文断点。

OpenScience, bilimsel araştırma görevlerini planlayıp literatür taraması, kod çalıştırma ve sonuç raporlamayı tek bir AI workbench içinde birleştirir.

Neden yükseliyor · 86 günlük bir repoda 3.645 yıldız ve son 28 günde 434 commit dikkat çekici; bilimsel araştırma agent'ı fikri de güncel AI ilgisiyle örtüşüyor. README'de Y Combinator desteği belirtiliyor. Ancak aktivite yalnızca 5 farklı yazardan geldiği için büyümenin geniş katkıcı topluluğuna dayandığı söylenemez.

Holdings exposure, what-if scenarios, cost and capacity, backtest checks, and published research.

FOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads li

An optimized handwritten digit recognition model delivering exceptional accuracy, high-speed performance, and compatibility with low-end har

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

Open-source, AI-native research workbench for literature search, reading, knowledge management & academic writing. Connects papers, notes an

Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.

Open-source personalized scientific discovery feed powered by arXiv, OpenAlex, PubMed and more.

The open-source agent harness, ready out of the box and customizable in depth. Tools, context, durable execution, permissions and recovery f

MCP server for Lacuna, a research map for machine learning: search directions, papers, authors, venues, and AI-generated research proposals.

Epistemological database for agent and human efforts, beliefs, and findings.

Follow RSI: human-reviewed progress in recursive self-improvement, with a Harness evolution evidence base.

🎓 AI 科研论文写作助手 - 30 个 Prompt 模板覆盖论文写作全流程。支持中英文翻译、润色、文献综述、投稿回复、基金申请等。

Let Claude Code, Codex, OpenCode, Pi and other agents run DeepSeek Harness (dsh) sessions in parallel: research batches, material gathering,

PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.

A collection of AI agent skills and plugins for Hermes Agent — research, creative, productivity, devops, and more. Each skill is self-contai

Free, open-source desktop viewer for exploring your own DICOM and NIfTI images. Local viewing with GPU rendering, linked MPR and optional MC

Open-source research workspace for connecting sources, evidence, notes and ideas. Built for academic research with Zotero integration. Avail

Native Claude Code, Codex and Pi adaptations of IdeaScientist for automatic, evidence-grounded research ideation.

An agent skill for Codex, Claude Code and other clients: open-ended research as the exploration of a labyrinth, with a map of what is proved

🎓 Claude Code skill — AI prompt library for academic paper writing, polishing, reviewing, translating and submitting to SCI/IEEE/Nature/TRO

BOAR - Adaptive Local Intelligence

The LuxAlgo ecosystem as MCP tools: free and keyless.

A moddable training framework for pre-training ablations.

Open-source research workspace: search academic papers, upload PDFs, inline citations with on-PDF highlights, reader-mode Q&A, and get citat

A workbench for language model research

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

Lev: Thinking Fast and Deep with Looped Decision Models. One checkpoint, multiple depths: System 1.5 decision models that think in loops, no

Search the web and primary sources, read full pages, and check every citation. MCP server for Claude, Cursor, Codex and more. Runs on your m

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.

Independent research on Claude Code internals, Claude Agent SDK, and related tooling.

An Omni-Modal, Omni-Discipline AI Scientist

A persistent, reviewed multi-agent runtime for long-horizon research and engineering.

RHO: Evolving Agents in the Dark — Retrospective Harness Optimization via Self-Preference. Improving LLM agents from unlabeled past trajecto

Zotero MCP server: search, citations, add by DOI, safe writes, semantic search and PDF page images for Claude, ChatGPT and any MCP client. T

开源研究管道 —— 文献综述、新颖性生成、引用验证与对抗性审查 | Open-source research pipeline — literature review, novelty generation, citation verification, and adversar

AI-operable research workspace for Zotero, Obsidian, and NotebookLM. Use any two, or all three, through CLI, MCP, REST, and dashboard.

Implementation of LatentMoE,Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts (Elango et al., NVIDIA 2026) — in Pytorch.

Make your coding agent justify architecture with real sources before it builds.

Industry and company research domain pack for DeepSeek Harness: methodology skills, industry chain mapping, public-source policy/news tracki

Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements and source grounding.

Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人，也不是无人监管的自动发论文机器，而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。

Perplexity AI search, reasoning, research, and compute - MCP server, dashboard, and multi-IDE auto-config for VS Code.

Generalizing ARIS from 科研 to 研究 — same five-step loop (plan · draft · adversarial review · iterate · persist) applied beyond academic resear

Practical guide and toolkit for physicists and mathematicians using Claude Code — built from months on a real research project