jordan-gibbs/hyperresearch

Health v2 · maintenance only

Adoption not part of the score

3873 stars · 399 forks observed · 2026-10-18

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Hyperresearch is a Python CLI harness that turns Claude Code into a deep research agent running a 16-step adversarially-audited pipeline. It produces cited research reports with full provenance and stores every source in a persistent, searchable markdown-plus-SQLite knowledge vault.

Use cases

• run deep research on a topic from a single prompt
• generate cited research reports with verified sources
• build a persistent searchable research knowledge base
• find open-access copies of paywalled papers
• audit citations for hallucinated quotes and syndicated sources
• resume interrupted research runs
• reuse collected sources across research sessions

When to choose

• you need long-form, citation-audited research reports rather than quick LLM answers
• you use Claude Code and want a disciplined deep-research workflow
• you want research sources accumulated in a reusable knowledge vault
• provenance and source independence matter for your reports

When to avoid

• you need a hosted research product with no local setup
• you don't use Claude Code or LLM agent workflows
• you need real-time data rather than deep multi-source synthesis
• you require independently benchmarked performance - third-party validation is pending

Facets

cli-tool · maturity active

agent-framework rag search-engine llm-inference cli web-scraping markdown artificial-intelligence developer-tools python cli cross-platform deep-research claude-code knowledge-base zettelkasten citation-verification research-agent wiki ai-agents retrieval-augmented-generation command-line natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="jordan-gibbs/hyperresearch")