Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. AI
  4. /
  5. ChatDKG
AI
ChatDKG icon

ChatDKG

by OriginTrail

ChatDKG is OriginTrail's launchpad for building autonomous AI agents that use the OriginTrail Decentralized Knowledge Graph as shared memory. It works with a range of AI agent frameworks.

Web app·Contact for pricing

Visit origintrail.io(opens in a new tab)

About ChatDKG

Key features of ChatDKG

  • Launchpad for creating autonomous AI agents
  • Works with several AI agent frameworks
  • Uses the OriginTrail DKG as collective agent memory
  • Verifiable provenance for published knowledge
  • Three memory layers: Working, Shared Working and Verifiable
  • Context Graphs to scope a project, team or application
  • Edge Node and Core Node roles for joining the network

Who ChatDKG is for

  • Developers building AI agents
  • Teams that want agents to share and build on knowledge
  • Organizations combining supplier or project knowledge
  • Node operators

How to use ChatDKG

  1. 1

    Step 1: Read the ChatDKG page and the DKG docs to choose a node role; most builders start with an Edge Node.

  2. 2

    Step 2: Install the DKG command-line tool with npm and check the version.

  3. 3

    Step 3: Initialize a fresh Edge Node on testnet, then start it and check its status.

  4. 4

    Step 4: Connect your agent runtime or application to the node.

  5. 5

    Step 5: Create a Context Graph for your project and write a small knowledge asset to Working Memory.

  6. 6

    Step 6: Ask your agent to retrieve it, then decide whether to share or publish it.

ChatDKG FAQ

What is ChatDKG?

It is a launchpad for creating autonomous AI agents powered by the OriginTrail Decentralized Knowledge Graph. Agents use the graph as collective memory.

Do I need a funded wallet to start?

The quickstart says Working Memory work needs no funded wallet. Publishing to Verifiable Memory is on-chain and uses gas and TRAC.

What is the difference between an Edge Node and a Core Node?

Most builders start with an Edge Node as their connection to the DKG. Core Nodes provide the infrastructure that stores and serves published knowledge and have extra registration and funding requirements.

Details

Pricing
Contact for pricingThe pages do not list ChatDKG plans. The docs say private and shared working memory carry no on-chain publication fee, while on-chain publication uses gas and TRAC. Compute, storage and model providers can cost money separately.
Type
Web app
Platforms
  • API
  • CLI
Categories
AIDataResearch
Added
Sep 23, 2026

Links

  • Documentationdocs.origintrail.io
OriginTrail iconPublisherOriginTrailOriginTrail develops a decentralized knowledge graph for publishing verifiable information that AI systems can retrieve and use.

Built from public sources

We put this page together from ChatDKG’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with ChatDKG.

Work at ChatDKG? Claim the listing to manage it yourself.

Something wrong here?

Related tools

See more
S2Spark 234KOpenDataArena · FreeSpark-234K is a dataset of 234K scientific reasoning question-answer pairs from OpenDataArena, built from frontier research papers. It is meant for training language models on hard, self-contained science problems.AI · FreeMONET iconMONETJasper · FreeMONET is a dataset of 103.8 million English image-text pairs for training text-to-image models. It was distilled from 2.9 billion raw pairs through safety, domain and duplicate filtering.AI · FreeAWABot World Explorer 500hACVLab · FreeABot World Explorer 500h is a dataset of 30,969 action-conditioned video episodes from ACVLab. Each episode pairs an MP4 with keyboard actions, captions and a COLMAP camera model.AI · Free