Havuz

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

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

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

Think only when the tool call looks unsure: confidence-gated reasoning for small local models. Code, BFCL results and paper.

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

A moddable training framework for pre-training ablations.

Research and shared data contracts for Pick Your AI: component catalogs, compatibility rules, pricing, and evidence for AI stacks.

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

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

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

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

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

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

Jevry, doğal dille verilen web görevlerini yapılandırılmış ve izlenebilir tarayıcı eylemlerine dönüştüren bir Electron masaüstü tarayıcısıdır.

Neden yükseliyor · Üç günde 102 yıldız alması erken ilgiye işaret ediyor; ancak bu benimseme veya kalite kanıtı değil. Son 28 günde 7 commit ve 1 farklı yazar olması, aktivitenin tek geliştiriciyle sınırlı olduğunu gösteriyor.

Research design for a Jev-native agent system:enable more options than jev provided with virtulization and paging, tool integration, externa

BOAR - Adaptive Local Intelligence

Automate ongoing market research with an AI planner, Jules agents, live conversations, and organized GitHub reports.

A free and intelligent app for smooth agentic reading and beyond.

MCP server for Google Scholar: search papers with Scholar operators, year ranges, cited-by and all-versions lookups, plus citations in five

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

Local-first research memory for Codex: checkpoints, progress ledgers, and Markdown/JSON paper notes. Early alpha.

A local evidence workbench for researchers and students: search PDFs and notes, build cited AI context packs, and audit quotations. CLI, bro

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

面向 VC/PE 投资人的 AI 调研工作体系：7 步流水线 × 三方案（A 企业 / B 行业技术 / C 混合）+ 9 项执行规范 + 8 套模板 + 工具脚本 + 5 个真实案例与长期记忆库，让「看公司、看行业、看赛道」从凭经验变成按流程

面向科研工作的开源 Agent Skill 合集：文献引用 · 期刊选刊 · 论文格式 · 学术制图 · 多模型协作

AI agent skills for thinking clearly, making better decisions, and getting things done. Strategy, research, decision-making, planning, risk

Open-source Python toolkit for analysing environmental and IoT data from the DigiTech Smart House.

Pyramis-L3D: hierarchical sparse attention research prototype (code only; weights on Hugging Face)

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

Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus vers

An Omni-Modal, Omni-Discipline AI Scientist

Self-hosted research intelligence for collecting, deduplicating, ranking, searching, and browsing the researchers, topics, and sources you c

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

The LuxAlgo ecosystem as MCP tools: free and keyless.

A workbench for language model research

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

Official research repository for CeloHT, containing research papers, RFCs, technical specifications, architecture, security studies, and evi

Specialist AI agents for Stellaris empire governance, brokered execution, and version-bound native Command research.

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

Stellar MCP server for AI agents: one authenticated gateway to official docs, live ecosystem data, community intel, and tested playbooks.

Experimental autonomous-agent living-room kernel with auditable boundaries.

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

USEL is an open-source CPU-based scientific computing framework for computational physics and quantum research. It provides modular numerica

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

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

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

Overnight experiment: can an AI agent make money, and can you trust what it reports? The agent produces claims; a separate verifier it canno

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

Local-first YouTube outlier research — find the videos that outperform their channels, and learn why