G
grunion-ai/weave
Open-source, self-hosted work database for people and AI agents, and an alternative to Airtable, Fibery,…
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
- Star count
- 17 ★ · grunion-ai/weave · read from the GitHub search API · (checked 2026-11-13 20:00:50)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-10-28 · last seen 2026-11-14 · seen 19× · listed by 1 sources
- Score
- score 103 · 17 ★ · 1 sources · repo
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: 开源项目. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
grunion-ai/weave;first catalogued 2026-10-28;last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.weave
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
An open-source, self-hosted alternative to Airtable, Fibery, Notion databases, and ClickUp —
built so that AI agents are first-class users, not an afterthought.
Connected tables, relations, workflows, formulas, rollups, and per-entity markdown
documents. One SQLite file. Zero dependencies. No build step. MIT.
For agents ·
Quickstart ·
Comparison ·
Agents & MCP ·
Self-hosting ·
FAQ
## For agents
weave stores structured work (tables, rows, relations, documents) in one SQLite
file, and an agent drives it over MCP, REST or the CLI.
Connect over MCP: node bin/weave.js mcp --data , the same as
weave mcp --data . In Claude Code:
claude mcp add weave -- node /path/to/weave/bin/weave.js mcp --data /path/to/workspace.db
Or build from a file: weave build --dry-run, then again without
--dry-run.
Read AGENTS.md › Using weave first: the primer,
every tool by job, plans with turn budgets, and common errors with their fixes.
## What weave is
weave is a work platform you run yourself: spaces hold tables, tables hold
entities, and entities connect to each other through real bidirectional
relations — with lookups, rollups, formulas, workflow states, automations, and
any number of markdown documents attached to each row.
It is meant to replace the SaaS your work already lives in — Airtable's
bases and grids, ClickUp's tasks and boards, Fibery's connected databases with
documents and automations — running on your laptop or your own server, with no
per-seat bill and no vendor holding the export button.
The difference from every other tool in this category is the second audience.
Work-management tools are built for humans first and APIs second. weave is built
for humans and agents as equals: everything the web UI can do, the REST API,
the CLI, and the built-in MCP server can do too — same engine, same data
file on your disk. A local install needs no account and sends no telemetry. The
hosted instance at https://weave.grunion.ai runs the same code behind a sign-in
door.
Local-first — your workspace is one SQLite file next to your project.
Yours to host — one Node process and one file; run it on a laptop or a
small VPS behind your own TLS and login (see Self-hosting).
Zero dependencies — git clone and run. Storage is Node's built-in
node:sqlite; the only third-party code is vendored and pinned.
Agent-native — an MCP server any stdio client can mount (Claude Code,
Codex CLI, Cursor, Gemini CLI), a scriptable CLI, Table#12 refs
everywhere, and markdown documents addressable as plain URLs
(/e/Task#12/doc.md, .html, .pdf).
Undoable — every entity mutation (edits, creates, deletes, links,
comments) can be stepped back with weave undo, POST /api/undo, or the
weaveundo MCP tool; agents get to make mistakes without making a mess.
Versioned documents — every document field keeps its revisions (one
per editing session), browsable and restorable from the page, weave
doc-revisions / weave doc-restore, or the weavedocrevisions /
weavedocrestore MCP tools.
## Quickstart
Requires Node ≥ 22.16 (Node 24 LTS recommended). There is nothing to build
and nothing to install from npm.
bash
git clone https://github.com/grunion-ai/weave
cd weave
node bin/weave.js serve --port 4400 --data ./my-workspace.db
built so that AI agents are first-class users, not an afterthought.
Connected tables, relations, workflows, formulas, rollups, and per-entity markdown
documents. One SQLite file. Zero dependencies. No build step. MIT.
For agents ·
Quickstart ·
Comparison ·
Agents & MCP ·
Self-hosting ·
FAQ
## For agents
weave stores structured work (tables, rows, relations, documents) in one SQLite
file, and an agent drives it over MCP, REST or the CLI.
Connect over MCP: node bin/weave.js mcp --data , the same as
weave mcp --data . In Claude Code:
claude mcp add weave -- node /path/to/weave/bin/weave.js mcp --data /path/to/workspace.db
Or build from a file: weave build --dry-run, then again without
--dry-run.
Read AGENTS.md › Using weave first: the primer,
every tool by job, plans with turn budgets, and common errors with their fixes.
## What weave is
weave is a work platform you run yourself: spaces hold tables, tables hold
entities, and entities connect to each other through real bidirectional
relations — with lookups, rollups, formulas, workflow states, automations, and
any number of markdown documents attached to each row.
It is meant to replace the SaaS your work already lives in — Airtable's
bases and grids, ClickUp's tasks and boards, Fibery's connected databases with
documents and automations — running on your laptop or your own server, with no
per-seat bill and no vendor holding the export button.
The difference from every other tool in this category is the second audience.
Work-management tools are built for humans first and APIs second. weave is built
for humans and agents as equals: everything the web UI can do, the REST API,
the CLI, and the built-in MCP server can do too — same engine, same data
file on your disk. A local install needs no account and sends no telemetry. The
hosted instance at https://weave.grunion.ai runs the same code behind a sign-in
door.
Local-first — your workspace is one SQLite file next to your project.
Yours to host — one Node process and one file; run it on a laptop or a
small VPS behind your own TLS and login (see Self-hosting).
Zero dependencies — git clone and run. Storage is Node's built-in
node:sqlite; the only third-party code is vendored and pinned.
Agent-native — an MCP server any stdio client can mount (Claude Code,
Codex CLI, Cursor, Gemini CLI), a scriptable CLI, Table#12 refs
everywhere, and markdown documents addressable as plain URLs
(/e/Task#12/doc.md, .html, .pdf).
Undoable — every entity mutation (edits, creates, deletes, links,
comments) can be stepped back with weave undo, POST /api/undo, or the
weaveundo MCP tool; agents get to make mistakes without making a mess.
Versioned documents — every document field keeps its revisions (one
per editing session), browsable and restorable from the page, weave
doc-revisions / weave doc-restore, or the weavedocrevisions /
weavedocrestore MCP tools.
## Quickstart
Requires Node ≥ 22.16 (Node 24 LTS recommended). There is nothing to build
and nothing to install from npm.
bash
git clone https://github.com/grunion-ai/weave
cd weave
node bin/weave.js serve --port 4400 --data ./my-workspace.db
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/grunion-ai-weave/)
- Source
- github · https://github.com/grunion-ai/weave
- Browse by field
- Open source
- Traction
- 17 ★
- added
- today
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.