Skip to content
MCP ThesaurusMCP Thesaurus

argon

CommunityIncomplete39/100Claim

npm argonctlstdioMITupdated 2mo ago

Branch, time-travel, merge and undo your MongoDB. Any driver, real mongod, versioned history underneath. Built for AI agents.

SourceWebsite171

What can you do with argon?

Argon β€” Git for MongoDB

Build Status Go Report License: MIT Homebrew npm PyPI

Branch, time-travel, merge and undo your MongoDB. Any driver, real mongod, versioned history underneath. Built for AI agents.

Three ideas, thirty seconds:

  1. A branch is a pointer, not a copy β€” created in milliseconds at any data size.
  2. checkout turns a branch into a real MongoDB database β€” pymongo, mongoose, mongosh, indexes, aggregation, transactions: all real, and every write becomes versioned history.
  3. Nothing is ever lost β€” diff it, merge it, undo it, rewind it, or pin it forever.

Install

brew install argon-lab/tap/argonctl      # macOS
npm install -g argonctl                  # cross-platform

# MongoDB must run as a replica set (one-node is fine):
docker run -d --name argon-mongo -p 27017:27017 mongo:7 --replSet rs0
docker exec argon-mongo mongosh --quiet --eval 'rs.initiate()'

The flow

main ──branch──▢ experiment ──checkout──▢ mongodb://…  ← any driver
                                              β”‚
                     β”Œβ”€β”€ argon diff ───────────  every write captured
                     β–Ό                        β–Ό
        merge (a data PR)          or   undo / discard / rewind
# 0 Β· Bring your data in ("git clone") β€” or: argon projects create myapp
argon import database --uri mongodb://localhost:27017 --database myapp --project myapp

# 1 Β· Branch β€” instant, no copy
argon branches create experiment -p myapp

# 2 Β· Get a real database for it, capture writes
argon checkout -p myapp -b experiment      # prints a connection string
argon watch    -p myapp -b experiment      # keep running while you write

# 3 Β· Review and merge back β€” a data pull request
argon diff          -p myapp -b experiment
argon merge preview -p myapp -b experiment
argon merge apply <plan-id>

# …or rewind instead of merging
argon restore reset -p myapp -b main --time 2026-07-07T09:00:00Z --backup pre-incident

Prefer clicking? argon console serves a local web console (UI + REST API) and opens your browser.

What you get

Command In one line
Branching argon branches create a metadata write β€” instant, zero copy
Real databases argon checkout / argon proxy any driver, real mongod; proxy serves stable mongodb://host/<project>~<branch> URIs
Write capture argon watch change-stream β†’ versioned history, per-actor attribution
Time travel argon time-travel query any historical state, by LSN or timestamp
Undo argon undo --actor <a> revert a range or one writer's changes; append-only, conflict-aware
Restore argon restore preview/reset/branch rewind a branch or fork history; recorded, never destructive
Data PRs argon merge preview/apply three-way merges as reviewable plans; conflicts never silent
Sandboxes argon sandbox create --ttl 1h fork + checkout + TTL in one step β€” disposable agent workspaces
Dataset pins argon pin create / pin sandbox immutable named states that survive GC and resets β€” reproducible evals
Web console argon console local UI + REST API in one command

Storage stays bounded: snapshots + retention-window GC keep state plus a window of history, not every write forever. Details and the consistency model, stated honestly: ARCHITECTURE.md.

For AI agents

claude mcp add argon -- argon mcp        # 13 tools: sandbox, diff, merge, undo, pins
pip install argon-agents                 # LangGraph checkpointer + Mem0, over REST
saver = ArgonCheckpointSaver.from_sandbox(argon, "myapp")   # checkpoint on a disposable branch
saver.merge()                                               # adopt the run β€” or .discard()

argon.create_pin("myapp", "eval-v1")                        # pin the dataset once
run = argon.sandbox_from_pin("myapp", "eval-v1")            # identical state, every eval run

The full agent workflow: docs/AGENTS.md.

Documentation

Quick start install β†’ first merge, step by step
CLI reference every command
Agents sandboxes, pins, MCP, REST API, argon-agents, proxy
Architecture how it works and what it guarantees
Operations deployment, chunk stores (S3/FS), GC, v1β†’v2 migration
Performance every number lives in the reproducible benchmarks β€” none here, by policy

Community

Issues Β· Discussions Β· Contributing Β· argonlabs.tech


Give your MongoDB a time machine. Branch without fear. ⭐