[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-83114":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":16,"stars30d":16,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":17,"rankGlobal":10,"rankLanguage":10,"license":18,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":19,"hasPages":19,"topics":21,"createdAt":10,"pushedAt":10,"updatedAt":22,"readmeContent":23,"aiSummary":24,"trendingCount":15,"starSnapshotCount":15,"syncStatus":25,"lastSyncTime":26,"discoverSource":27},83114,"TuringResearch_plus","meamaturinlove221\u002FTuringResearch_plus","meamaturinlove221","Turn messy research goals into evidence ledgers, method cards, experiment routes, artifact audits, and advisor-ready reports.","",null,"Python",146,5,1,0,89,2.33,"Other",false,"main",[],"2026-06-12 02:04:31","\u003Cp align=\"center\">\n  \u003Cimg src=\".\u002Fassets\u002Fturingresearch_mascot.svg\" width=\"260\" alt=\"TuringResearch mascot\" \u002F>\n\u003C\u002Fp>\n\n\u003Ch1 align=\"center\">TuringResearch\u003C\u002Fh1>\n\n\u003Cp align=\"center\">\n  \u003Cb>A local-first research operating system for AI-assisted scientific iteration.\u003C\u002Fb>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  Turn messy research goals into evidence ledgers, method cards, experiment routes, artifact audits, and advisor-ready reports.\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"#why-turingresearch\">Why\u003C\u002Fa> ·\n  \u003Ca href=\"#what-it-does\">Features\u003C\u002Fa> ·\n  \u003Ca href=\"#architecture\">Architecture\u003C\u002Fa> ·\n  \u003Ca href=\"#quickstart\">Quickstart\u003C\u002Fa> ·\n  \u003Ca href=\"#safety-boundaries\">Safety\u003C\u002Fa> ·\n  \u003Ca href=\".\u002FREADME_CN.md\">中文\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cimg alt=\"Python\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPython-3.11%2B-blue\" \u002F>\n  \u003Cimg alt=\"MCP first\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMCP-first-7C3AED\" \u002F>\n  \u003Cimg alt=\"Local first\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flocal--first-by%20default-16A34A\" \u002F>\n  \u003Cimg alt=\"Dry run\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdry--run-safe%20by%20default-F59E0B\" \u002F>\n  \u003Cimg alt=\"Status\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fstatus-public%20RC-0EA5E9\" \u002F>\n\u003C\u002Fp>\n\n---\n\n## Why TuringResearch\n\nMost AI tools can summarize a paper or draft a plan.\n\nReal research is harder:\n\n- advisor goals change;\n- experiments produce incomplete evidence;\n- artifact bundles get huge and messy;\n- “planned”, “observed”, and “fake demo” results get mixed together;\n- long-running Codex sessions drift away from the original objective;\n- reports need to be honest enough for a mentor, not just polished enough for a README.\n\n**TuringResearch is built for that gap.**\n\nIt helps organize the research loop:\n\n```text\nintent → literature → gap → hypothesis → route → experiment → artifact → report → next sprint\n```\n\n---\n\n## What it does\n\nTuringResearch focuses on research workflow infrastructure:\n\n| Capability | What it helps with |\n|---|---|\n| Research intake | Convert fuzzy goals into constraints, non-goals, blockers, and next actions. |\n| Evidence ledger | Separate observed facts, planned work, fake fixtures, missing papers, and missing experiments. |\n| Literature workflow | Prepare survey plans, method cards, reference maps, and related-work positioning. |\n| Hypothesis planning | Turn gaps into testable hypotheses and route trees. |\n| Experiment runbooks | Compile Codex-ready long-horizon plans with hard gates and fallback branches. |\n| Artifact audit | Track bundles, logs, boards, reports, hashes, missing files, and unsupported claims. |\n| Advisor pack | Produce mentor-facing summaries, architecture diagrams, boundaries, and next-step plans. |\n| Community intake | Accept idea documents and skill proposals without letting unreviewed code into the project. |\n\n---\n\n## Architecture\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Fturingresearch_architecture_overview.svg\" alt=\"TuringResearch Architecture\" width=\"100%\">\n\u003C\u002Fp>\n\nThe repository is intentionally **docs-first, evidence-first, and contract-first**.\n\n---\n\n## What is implemented vs planned\n\nTuringResearch is a public release candidate. The README is conservative by design.\n\n| Status | Meaning |\n|---|---|\n| Implemented | Code\u002Fdocs\u002Ftests exist in this repo. |\n| Partial | Working skeleton or workflow exists, but not full production scope. |\n| Planned | Described as a roadmap item only. |\n| Reference | Inspired by external\u002Fpublic projects; not claimed as TuringResearch output. |\n\nNo section in this README should imply that a planned module has already produced verified scientific results.\n\n---\n\n## Quickstart\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fmeamaturinlove221\u002FTuringResearch_plus.git\ncd TuringResearch_plus\npython -m pip install -e .[dev]\npython -m pytest\n```\n\nOptional local MCP smoke checks:\n\n```bash\npython -m turing_research.mcp_server --manifest\nturingresearch-plus-mcp --health-check\n```\n\nLegacy commands remain available during the rename period:\n\n```bash\npython -m tuling_research.mcp_server --manifest\ntulingresearch-plus-mcp --health-check\n```\n\nDefault tests do not require real API keys or live network access. Default workflows should be safe to run without live API keys.\n\n---\n\n## Example workflows\n\nTypical workflows this project is designed to support:\n\n1. **Paper route planning** — turn a paper set into method cards, gap analysis, and experiment ideas.\n2. **Long-horizon Codex planning** — compile route trees and hard gates into prompts that do not return too early.\n3. **Artifact review** — inspect output bundles and decide whether claims are supported.\n4. **Advisor report generation** — prepare clear reports with scope, evidence, failure modes, and next steps.\n5. **Community idea intake** — let trusted collaborators submit idea\u002Fskill documents without changing code.\n\n---\n\n## Roadmap\n\nNear-term directions:\n\n- stronger artifact audit reports;\n- better evidence ledger workflows;\n- figure\u002Ftable extraction planning;\n- richer advisor-pack generation;\n- cleaner modular repo presentation;\n- friend\u002Fcommunity skill proposal intake;\n- optional live adapters behind explicit gates.\n\nDeferred:\n\n- ARIS-like homepage generation;\n- automatic public release automation;\n- automatic remote execution by default;\n- unverified upstream “academic output” migration.\n\n---\n\n## Contributing\n\nFor implementation work, use maintainer-reviewed branches.\n\nFor idea and skill proposals, use the community intake flow:\n\n```text\ncommunity\u002Fideas\u002F\u003Cgithub-username>\u002F\u003Cidea-title>.md\ncommunity\u002Fskills\u002F\u003Cgithub-username>\u002F\u003Cskill-name>.md\n```\n\nAccepted proposals can later become feature capsules, skills, SOPs, campaign entries, or roadmap tasks.\n\n---\n\n## License\n\nCheck `LICENSE` before reuse. If the license file is not present in your local checkout, treat the project as not yet formally licensed for redistribution.\n\n---\n\n\u003Cp align=\"center\">\n  \u003Cb>TuringResearch makes research iteration clearer, more auditable, and less likely to drift.\u003C\u002Fb>\n\u003C\u002Fp>\n","TuringResearch 是一个本地优先的研究操作系统，旨在通过AI辅助实现科学迭代。它能够将杂乱无章的研究目标转化为证据账本、方法卡片、实验路线图、成果审核和导师可用的报告。项目使用Python编写，支持Python 3.11及以上版本，强调本地优先处理，并默认提供安全的干运行模式。适合需要系统化管理研究过程的科研人员或团队使用，特别是在面对多变的研究目标、复杂的实验数据以及庞大的研究成果时，TuringResearch 提供了一套完整的解决方案来组织从意图到文献回顾、假设测试直至最终报告生成的研究循环。",2,"2026-06-11 04:10:09","CREATED_QUERY"]