DWIN Research Adoption
io.github.vidvinianinovPublished by GitHub account vidvinianinovv0.1.0Updated Oct 25, 2026
Find, ground, evaluate, and selectively retain AI research through one local-first MCP.
Overview
A local-first MCP server for finding, grounding, evaluating and selectively retaining AI research, with human-approved memory.
- What you can do
- Discover and triage versioned arXiv papers and recover source-bound evidence from them, including local PDF parsing with page and block provenance and exact-text reopening. Register and index a local AI setup (instructions, skills, MCP manifests, policies, scripts, evals) and search it lexically, with optional local embeddings and candidate graph relationships. Reconcile an indexed setup against research to surface observed or gap candidates without editing anything. Run baseline-versus-intervention comparisons under a declared gate and keep durable memory empty until an evaluator receipt and explicit human approval exist. Optionally run a bounded daily scheduler that executes only jobs a 胶囊
- When to use it
- Use it when you want to turn AI research papers into measured, reversible changes to your own AI setup, with evidence provenance and an approval gate before anything becomes durable memory. It suits people who keep a local checkout of their setup and want lexical, source-cited retrieval rather than an autonomous agent that rewrites their system.
- Requirements
- Runs as a local stdio process via npx (Node.js). No API key is required. Network access is deny-by-default, with only official arXiv endpoints and an optional loopback local-model endpoint allowlisted. Optional PDF parsing requires separately provisioning pinned Docling model artifacts (about 1.34 GB). The data directory can be overridden with DWIN_FACTORY_DATA, and DWIN_TOOL_PROFILE=full exposes extra tools. The daily scheduler needs a stable checkout or global install and is macOS-oriented.
Installation
In SourceWeft
- Open DWIN Research Adoption in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
DWIN Research Adoption
Turn AI research into measured setup improvements without letting papers silently rewrite your system.
This repository contains one local MCP entrypoint plus three reusable skills. The workflow keeps five states separate:
- discover a versioned paper;
- recover source-bound evidence;
- propose a narrow change;
- compare baseline and intervention under a declared gate;
- promote a durable memory only after explicit human approval.
The MCP combines seven bounded capsules: Research Radar, Document Intelligence, Evidence Graph, Setup Intelligence, Research Adoption, Memory Graph, and Factory Health. It does not include personal session history, financial data, employer artifacts, or private source corpora.
Install the MCP
Published package: dwin-research-adoption on npm. Official Registry identity: io.github.vidvinianinov/dwin-research-adoption.
Generic MCP client configuration:
No API key is required. The default data directory is private application data; override it with DWIN_FACTORY_DATA when isolation is needed. Network access is deny-by-default. Only official arXiv endpoints and an optional loopback local-model endpoint are allowlisted by the bundled policy.
The default basic profile exposes 38 tools across discovery, PDF evidence, setup inventory, hybrid retrieval, reconciliation, evaluation, and governed Memory. Set DWIN_TOOL_PROFILE=full to expose additional category scans, watches, retrieval experiments, and the pinned demonstration corpus.
Index a local AI setup
Registration is explicit: the package never scans your home directory. From a stable checkout or global installation:
Call setup_sync to classify and index instructions, skills, MCP manifests, capsules, contracts, policies, hooks, steerings, SOPs, scripts, evals, fixtures, evidence, and configuration. setup_search uses FTS5/BM25; setup_reopen verifies exact source text; setup_graph exposes bounded typed relationships; and setup_reconcile returns observed or gap candidates without editing the setup.
For optional semantic recall, call setup_bridge_evidence, explicitly provision the pinned model, and then call evidence_embed:
The embedding cache binds exact text, role, model revision, preprocessing/configuration, runtime, and architecture. BM25 stays the default; vectors and graph edges remain candidate-only.
Parse local research PDFs
The lightweight package does not bundle model weights. Explicitly provision pinned Docling and register one PDF:
Then call document_sync, document_search, and document_reopen. The parser runs locally and returns page/block provenance, hashes, and a private lossless Docling export. Provisioning is intentionally separate because the tested runtime uses about 1.34 GB of model artifacts.
Run the daily local scheduler
The public package includes a bounded daily runner plus a macOS launchd installer. A stable checkout or global installation is required; ephemeral npx paths are rejected.
The scheduled run executes only jobs declared daily in capsule manifests and writes hashed receipts under private application data. It does not publish posts, install research changes, or promote Memory.
Install the skills
Current stable release: v0.2.0. Skill catalog: skills.sh/vidvinianinov/dwin-research-adoption.
Included skills:
triage-ai-research: route a question to an audited arXiv template and produce candidate evidence.adopt-research-into-setup: turn a selected paper into a baseline/intervention experiment.review-evidence-and-memory: verify provenance and promote only accepted, approved lessons.
Reproduce the release checks
npm run demo uses a sanitized offline arXiv fixture and an isolated index of the package itself. It discovers the unified tools, finds papers, builds a typed setup index, reopens exact evidence, reports three explicit gap candidates, runs the baseline/intervention reconciliation case, and verifies that Memory remains empty. npm run audit:release inspects the exact npm file list for secrets, personal paths, employer terms, symlinks, and metadata drift.
The first real research-to-setup result is the memory portability launch case. It includes a negative adoption decision and makes no productivity or token-saving claim.
Product boundary
The default retrieval path is lexical and source-cited. Optional embeddings are local, pinned, hash-cached, and experimental; they do not confer truth or authority. Parsed PDFs and external abstracts are untrusted inputs. Graph edges are candidate relationships. Only evaluator receipts plus a current human approval can authorize durable memory.
The local stdio package is Apache-2.0. A future hosted service may add managed scheduling, organization policy, collaborative approvals, and hosted evaluation while preserving the public contracts.
Security and privacy
See SECURITY.md, Privacy, and Terms. Report vulnerabilities privately rather than opening a public issue.
The dependency-ordered product milestones and exit criteria are in the goal chain.
MCP Registry name: io.github.vidvinianinov/dwin-research-adoption
Source: README.md at commit 257dfa2
Tools
0Version history
1- v0.1.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts