RepoAlerts
SponsorGet alerts

billion-token-one-task/Deepgraph

Agent

Get alerts like thisView on GitHubWebsiteShare on X

Can I trust it?

No red flags in our checks.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 9 days ago.

  • Licence OK

    MIT: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

Research agent that harvests arXiv papers, builds an evidence graph of claims and contradictions, finds open questions via SQL-based detectors, and runs budgeted computational experiments to issue auditable verdicts. Part of the JouleBeat project; a web UI runs on localhost…

Who it's for

Researchers and developers running computational literature-driven experiments with LLM APIs and Python 3.12

How to use it

Install

pip install -r requirements.txt

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up billion-token-one-task/Deepgraph in my project. Follow its README: https://github.com/billion-token-one-task/Deepgraph. Explain each step and check it is safe before running anything.

Star curve

1.1KFrom 5 to 1,128 stars between 29 Sept 2026 and 3 Nov 2026.

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![billion-token-one-task/Deepgraph on RepoAlerts](https://repoalerts.com/badge/billion-token-one-task/Deepgraph.svg)](https://repoalerts.com/repo/billion-token-one-task/Deepgraph?ref=badge)
Share on X
  • weir36/deep-research-langgraph

    Multi-agent research assistant built with LangGraph that splits a research question into a plan, runs parallel web search and Python computation steps, and writes a report with numbered citations. It

    AgentAI agentsPython · 35 stars · +35 this week · 1 day old

  • yzlin286-wq/Deepscient

    A research workbench running on the DeepSeek Harness runtime that structures scientific work into 12 stages and 55 checkable gates, with 36 research tools, 98 skills, and an auditable evidence chain w

    AppAI agentsJavaScript · 733 stars · +578 this week · 13 days old

  • Gen-Verse/DiscoveryRSI

    A Python harness for recursive, hypothesis-centred research workflows in life science. It runs multi-agent hypothesis development, records revision lineage and evidence, compiles selected investigatio

    AI agentsPython · 144 stars · +6 this week · 19 days old

  • MUSE-AI-Lab/SurveyGraph

    Python system that generates academic survey papers by building a methods-entity knowledge graph (MEKG) from collected papers, linking methods via follow-on, competition and shared-resource relations,

    Models & inferencePython · 251 stars · +251 this week · 7 days old

  • YuhuaJiang2002/HarnessMM

    Research implementation of HarnessMM, which reuses decisions an agent already made: a slow model call records future tool actions in a decision graph, and guarded checks on tool results decide whether

    AgentAI agentsPython · 74 stars · +72 this week · 8 days old

  • zensers/zensers

    Automated industry research platform that turns a research request into a structured report through multi-agent data collection, section-level writing and review, audit checks, and export to DOCX, PPT

    AgentAI agentsPython · 114 stars · 15 days old