Logo
Learn
  • Explore Course
Build
  • Explore Buildathon
  • Project Archive
Hack
Hack Coming Soon
  • Explore IRL Hackhouse
  • How to Qualify
  • Past Events

Frame Zero

Frame0 turns scattered news and datasets into a typed knowledge graph that compounds with every run — built end-to-end on 0G. Every LLM call is signed by the 0G Compute router, every brief is anchored

Videos

Description

The Problem

Crypto analysts, comms teams, and protocol researchers spend most of their week doing the same work manually: skimming Google Alerts, copying paragraphs into Notion, cross-referencing Twitter, posting summaries into Telegram, generating briefs for leadership, and trying to remember which article contained which claim when someone asks, “Are you sure that number is right?”

Three things break:

  1. The work doesn’t compound
    Every week starts from zero. The graph of who-funded-whom, who-regulates-whom, and what-was-said-when exists only in the analyst’s head and scattered documents.

  2. The output isn’t verifiable
    When leadership questions a claim, the analyst has to chase the original article from memory. There’s no signed receipt proving which sources and models generated a brief.

  3. The tools are scattered
    Google Alerts, Notion, Twitter lists, RSS readers, Telegram, Discord — every workflow is fragmented across different tools and contexts.

The crypto-native ecosystem feels this pain even more because information moves fast, sources are unconventional (Twitter threads, governance forums, on-chain events), and compliance expectations are increasing. Existing AI tools only help with summarization; they ignore the compounding layer entirely. Every summary is generated once and forgotten immediately.


Frame0
Transforms fragmented crypto information into a typed knowledge graph that compounds over time, with every inference and artifact anchored to 0G for verifiability.

Users enter a topic. The agent classifies it, creates a persistent watcher, and begins ingesting from selected sources. Every run produces:

  • An editorial brief written in the analyst’s voice

  • A growing typed knowledge graph with evidence-backed relationships

  • Alerts triggered by material changes

  • A signed inference trace for every LLM call

  • A verifiable content hash anchored to 0G Storage

When an alert fires, it pushes to Telegram. When someone questions a claim, users can click directly into the graph to inspect the original evidence and source article. When auditors ask where a number came from, the platform provides the trace ID and 0G Storage root hash.

Frame0 is built on 0G because the primitives required for a verifiable analyst desk already exist:

  • 0G Compute for signed LLM inference

  • 0G Storage for low-cost immutable anchoring

  • 0G Chain for on-chain payments and access control


Knowledge Graph

  • Commission a topic
    A single text input is classified into one of seven entity types:

  • Typed relationships
    Sixteen relationship types are supported, including:

  • Articles as graph nodes
    Every processed article becomes an event:article-* node connected through mentions edges to related entities, ensuring sparse extractions still build navigable graphs.

  • CoinGecko enrichment
    Token and protocol entities include:

    • Live price

    • Market cap

    • 24h / 7d change

    • All-time high


Editorial Agent

  • Per-run briefs
    The system selects relevant articles and generates concise editorial summaries persisted alongside inference trace IDs.

  • 7-day executive briefing
    The last seven days of activity are condensed into an executive-level summary.

  • Chat with your graph
    Users can query their commission directly. Responses are grounded strictly in:

    • Entities

    • Relationships

    • Briefs

    • Uploaded datasets

    The system refuses answers outside available context.


Sources and Ingestion

  • Bring-your-own RSS and YouTube sources
    Sources are attached per commission and merged into a shared ingestion pipeline.

  • Google News fallback
    When user-defined sources return nothing, the system automatically dispatches targeted Google News RSS queries.

  • CSV upload pipeline

    • Up to 20 rows per file

    • Each row passes through the same typed extraction engine

    • SHA-256 hash computed before inference begins

Progress During Hackathon

<p><strong>Editorial Agent Loop (The Core Flow)</strong></p><p>Commission a topic → classify the entity → fetch news from cache, BYO RSS feeds, and Google News fallback → process up to 8 articles → generate editorial briefs → extract typed entities and relationships → persist with provenance → evaluate alerts → deliver notifications to app logs, webhooks, or Telegram.</p><hr><p><strong>Typed Knowledge Graph</strong></p><ul><li><p><strong>7 entity types</strong></p><ul><li><p>Token</p></li><li><p>Protocol</p></li><li><p>Company</p></li><li><p>Person</p></li><li><p>Jurisdiction</p></li><li><p>Event</p></li><li><p>Topic</p></li></ul></li><li><p><strong>Schema-aware relationships</strong><br>Domain/range validation rejects invalid relationships between entity types.</p></li><li><p><strong>Articles as graph nodes</strong><br>Every article becomes an <code data-inline="true" spellcheck="false">event:article-*</code> node connected through <code data-inline="true" spellcheck="false">mentions</code> edges, allowing sparse extractions to still create navigable graphs.</p></li><li><p><strong>CoinGecko enrichment</strong><br>Token and protocol entities include:</p><ul><li><p>Market cap</p></li><li><p>24h / 7d price change</p></li><li><p>All-time high</p></li></ul></li></ul><hr><p><strong>User-Facing Surfaces</strong></p><ul><li><p><code data-inline="true" spellcheck="false">/dashboard</code><br>Live force-directed graph with commissions, entity exploration, and timeline view.</p></li><li><p><code data-inline="true" spellcheck="false">/chat</code><br>Per-commission Q&amp;A grounded only in:</p><ul><li><p>Entities</p></li><li><p>Relationships</p></li><li><p>Briefs</p></li><li><p>Uploaded datasets</p></li></ul><p>Responses include model trace IDs and refuse when data is missing.</p></li><li><p><code data-inline="true" spellcheck="false">/sources</code><br>RSS feeds and YouTube ingestion merged with the global news cache.</p></li><li><p><code data-inline="true" spellcheck="false">/vault</code><br>Unified table of briefs, uploads, and content hashes with anchored-on-0G statistics.</p></li><li><p><code data-inline="true" spellcheck="false">/agent</code><br>Filterable audit log for:</p><ul><li><p>Inference calls</p></li><li><p>Brief generations</p></li><li><p>Alert triggers</p></li><li><p>Upload events</p></li><li><p>Source additions</p></li></ul></li></ul><hr><p><strong>Alerts and Delivery</strong></p><ul><li><p><strong>Delivery channels</strong></p><ul><li><p>In-app logs</p></li><li><p>Webhooks</p></li><li><p>Telegram</p></li></ul></li><li><p><strong>Telegram subscriptions</strong><br>Separate toggles for:</p><ul><li><p>Alerts</p></li><li><p>Brief digests</p></li></ul><p>Digests bundle multiple article updates into a single message.</p></li><li><p><strong>Telegram onboarding bot</strong><br><code data-inline="true" spellcheck="false">@ogtimes_bot</code> onboarding through <code data-inline="true" spellcheck="false">/start</code>.</p></li></ul><hr>

Tech Stack

ReactNextEthersSolidityNode

Fundraising Status

<p>Building this as a frontier in Knowledge Graphs and AI infra on 0g.<br>Applied for a16z and booked calls with clients on exploring the usecase beyond current compass.</p>

Team Leader
Ddaiwik maheshwari
GitHub Link
github

GitHub

https://github.com/daiwikmh/Frame0
Product Category
DeFiAIInfra