Menyediakan ledger riset lokal bagi AI agent untuk melacak bukti, memverifikasi klaim, dan mengelola sesi riset melalui workflow yang terstruktur.
Juga dikenal sebagai grainulation/grainulator
- Stars
- 86
- Tools
- —
- Unduhan, 30 hari
- —
- Versi terbaru
- —
- Commit terakhir
- 12 Nov 2026
- Lisensi
- MIT
Apa itu Grainulator MCP?
Menyediakan ledger riset lokal bagi AI agent untuk melacak bukti, memverifikasi klaim, dan mengelola sesi riset melalui workflow yang terstruktur.
Ringkasan dibuat dari README proyek
Tentang Grainulator MCP server
Grainulator menyediakan local research ledger yang dirancang untuk membantu AI agent melacak bukti, memverifikasi klaim, dan mengelola sesi riset yang kompleks. Tool ini berfungsi sebagai workflow terstruktur yang memungkinkan model untuk mempertahankan riwayat temuan, meninjau kembali asumsi, dan mendeteksi konflik dalam penalaran mereka. Sistem ini dibangun untuk para engineer dan peneliti yang membutuhkan cara untuk memastikan pekerjaan berbantuan model mereka tetap berdasar pada sumber yang terdokumentasi.
Pengguna dapat terhubung ke server melalui koneksi MCP menggunakan npx, atau melalui plugin khusus untuk Claude Code dan Codex. Tool ini juga menawarkan command-line interface untuk interaksi langsung. Meskipun ledger utamanya bersifat lokal, research playground dapat dijalankan menggunakan akun provider yang dikonfigurasi secara lokal. Tool ini mengorganisir tugas ke dalam dua kategori berbeda: tindakan otomatis yang dapat dilakukan agent dan tindakan manual yang memerlukan intervensi manusia. Hal ini memastikan alur kerja yang jelas untuk setiap sesi riset tanpa memberlakukan kuota tetap pada jumlah iterasi riset atau jumlah klaim.
Apa yang bisa Anda lakukan dengannya
- 1Mendokumentasikan temuan risetSeorang agent dapat mencatat klaim spesifik beserta tier bukti dan sumbernya untuk menjaga ledger yang persisten.
- 2Memverifikasi integritas risetSistem dapat mengidentifikasi konflik, dukungan yang lemah, dan perspektif yang hilang di dalam data yang telah dikumpulkan.
- 3Mengelola workflow risetSeorang developer dapat menginstruksikan agent untuk menyelidiki sebuah migrasi, mencatat bukti, dan membagi langkah selanjutnya ke dalam daftar otomatis dan manual.
- 4Melanjutkan sesi yang terhentiPeneliti dapat menghentikan sebuah sesi dan membawa konteks tersebut untuk melanjutkan pekerjaan di lain waktu.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Pengecekan otomatis
Berjalan 14 Nov 2026Laporan lengkap →Belum diverifikasi. Sebuah server memerlukan skor 80, tidak ada temuan serius, dan data yang cukup untuk kami periksa. Cara kerja checks · Yang perlu diperbaiki untuk menambah poin
- Source repository terhubung dan dapat dijangkaugrainulation/grainulator is public and reachablegithub.com/grainulation/grainulator ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernyaTidak diperiksa
- Provenance build (atestasi Sigstore)Tidak diperiksa
- Lisensi open source (OSI)MITspdx.org/licenses/MIT.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-11-12github.com/grainulation/grainulator ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerTidak diperiksa
- Tidak ada advisory kritis pada paket atau dependensinyaTidak diperiksa
- Tidak ada instruksi tersembunyi untuk model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersLolos
- Tools yang bersifat destruktif telah diberi labelTidak diperiksa
- Endpoint remote merespons handshake MCPTidak diperiksa
README
Lihat di GitHubWhat it adds
Good models still need a way to keep track of evidence, revisit assumptions, and verify their work. Grainulator gives them that process, with a local ledger that stays with the task as it moves between models and sessions.
| Capability | What it gives you |
|---|---|
| Evidence that stays with the work | Typed claims, sources, evidence tiers, and provenance that survive edits and exports. |
| A check on the answer | Conflict detection, weak-support signals, and explicit gaps to investigate. |
| Clear next actions | Two lists: what the agent can continue automatically, and what needs your input. |
| Sessions you can carry forward | Configurable research, stop/resume, reusable context, and credential-free exports. |
| Verification for your task | A managed command loop that can use a verifier you provide. |
Grainulator works with Claude Code and Codex through plugins. It also provides a command-line tool and an MCP connection for other agents. You do not need to install its components separately.
Quick start
Requires Node.js 24+. Node 25 is the development default.
Upgrading from 1.x? Follow the migration checklist to update the plugin and keep your existing research data.
git clone --branch v2.2.0 https://github.com/grainulation/grainulator.git
cd grainulator
npm ci --ignore-scripts
node bin/grainulator.js doctor
To use Grainulator inside your agent, follow the Claude Code or Codex setup guide. The website shows a saved example of an evidence check. It does not send your question to a model.
The local research playground remains available through node bin/grainulator.js preview. It runs models using a provider account you configure locally.
Distribution: v2.2.0 is a GitHub release, not an npm registry release. For a separate local installation, follow the archive installation guide.
Other agents: connect through MCP
Add an MCP server that runs this command, with your project's absolute path:
npx -y github:grainulation/grainulator#v2.2.0 mcp --dir /absolute/path/to/project
Antigravity installs the full plugin. See the agent setup guide for Antigravity, Cursor and other MCP agents.
For the full Claude Code or Codex plugin, use the agent setup guide. Codex needs a project folder; the guide shows how to set it. CLI and direct MCP access remain available to other hosts.
Put it to work
With Grainulator connected, give your agent the outcome you need:
Use Grainulator to investigate whether we should migrate this service. Record the evidence, challenge the assumptions, implement the agreed changes, and verify them. Keep the remaining next steps split into Auto and Manual.
The work follows a simple cycle:
- Record findings with their sources and evidence tiers.
- Check for conflicts, weak support, and missing perspectives.
- Act on the gaps that matter, then verify the requested result.
- Continue from the saved ledger or export the session to another workflow.
There are no fixed claim-count or research-pass quotas. Auto lists work the agent can continue within your authorization. Manual lists decisions, access, or actions that need you. When you ask only for next steps, those two lists are the entire response.
node bin/grainulator.js init --dir ./sprints/migration \
--question 'Should we migrate this service?' \
--audience engineers --constraints 'Preserve existing user data' \
--done 'A verified plan with remaining risks documented'
node bin/grainulator.js add --dir ./sprints/migration \
--id r001 --type constraint --topic migration \
--content 'Existing user data must remain readable.' --evidence stated
node bin/grainulator.js compile --dir ./sprints/migration
The equivalent MCP tool is add_claim on the grainulator server. See the tool reference for evidence, memory, export, analytics, and orchestration operations.
Explore the docs
| Guide | Start here for… |
|---|---|
| Installation | Tagged source, isolated archives, and verified build identity. |
| Upgrading from 1.x | Host updates, renamed tools, existing data, and retired setup instructions. |
| Agent setup | Use Grainulator with Claude Code, Codex, or another agent. |
| Research sessions | Models, feature controls, credentials, export, and resume. |
| Tools | The canonical CLI and MCP interface. |
| Execution adapters | Attaching a model command and a task-specific verifier. |
| Architecture | The workspace layout and internal modules. |
| Evaluation | What has been measured and what remains unproven. |
| Contributing | Development setup, tests, and changes to the project. |
Verification and limits
CI checks Node 24 and 25, isolated package installation, plugin contracts, Rust runtime conformance, lint, and the static playground in a browser. Native host and live-provider acceptance have separate verification guides.
The compiler checks the structure and support recorded in the ledger; it does not establish that a source is true. Evaluations do not establish a general accuracy or efficiency gain, and per-pass limits are not a whole-session spending cap. Keep those distinctions when interpreting results.
npm test
npm run test:install
npm run lint
Browser and runtime prerequisites are in CONTRIBUTING.md. The offline node bin/grainulator.js demo exercises the adapter/verifier protocol without a provider account.
Pertanyaan tentang Grainulator MCP
Apakah Grainulator memverifikasi apakah sebuah sumber itu benar?
Tidak, compiler hanya memeriksa struktur dan dukungan yang tercatat dalam ledger, namun tidak menetapkan kebenaran dari sebuah sumber.
Bisakah saya menggunakan Grainulator dengan Claude Code?
Ya, Grainulator dapat digunakan dengan Claude Code melalui plugin.