Status basis: pypi_downloads_30d momentum fell to 0 per 3d from 477 (<= 40% of the prior window)
- Cooling pypi_downloads_30d momentum fell to 0 per 3d from 477 (<= 40% of the prior window)
- Cooling pypi_downloads_30d momentum fell to 0 per 3d from 477 (<= 40% of the prior window)
- Cooling pypi_downloads_30d momentum fell to 0 per 3d from 477 (<= 40% of the prior window)
- Accelerating pypi_downloads_30d gained 477 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Reactivated pypi_downloads_30d did not move for 7d, then gained 477 in the last 3d
- Cooling pypi_downloads_30d momentum fell to 0 per 3d from 477 (<= 40% of the prior window)
- Accelerating pypi_downloads_30d gained 477 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Reactivated pypi_downloads_30d did not move for 7d, then gained 477 in the last 3d
- Accelerating pypi_downloads_30d gained 477 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Reactivated pypi_downloads_30d did not move for 7d, then gained 477 in the last 3d
- Accelerating pypi_downloads_30d gained 477 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- first observed Kanon started keeping permanent history for this agent
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | — | unknown | — |
| Bring your own key | — | unknown | — |
| Autonomy level | 2 | inferred | 3 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | — | unknown | — |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
It closes the loop between automated research, synthesis, and knowledge retention, creating a repeatable workflow for deep domain work.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“Agents collect, search, and synthesize web research”— description
“A tier-adaptive 16-step pipeline takes one prompt”— readme
“persistent, searchable vault, so each session starts smarter”— readme
“Hyperresearch turns Claude Code into a deep research agent”— readme
FAQ
What is hyperresearch?
hyperresearch automates cross-site research by collecting, synthesizing, and storing web information into a persistent, searchable knowledge base for teams that need to build reusable domain expertise.
What does hyperresearch do?
Automate gathering and organizing information from multiple websites into a reusable, structured knowledge base for ongoing research.
Why does hyperresearch matter?
It closes the loop between automated research, synthesis, and knowledge retention, creating a repeatable workflow for deep domain work.
Is hyperresearch open source?
Yes — hyperresearch is open source.
How popular is hyperresearch?
As tracked by KanonAgent: 192 upvotes (first indexed 2026-09-11).
When did hyperresearch take off?
KanonAgent flagged hyperresearch as breaking out on 2026-09-12 on GitHub (at 603 stars/day that moment). The breakout log is append-only: https://kanonagent.com/rising
What are the best hyperresearch alternatives?
Similar AI agents tracked by KanonAgent: Stealth Venture, taste-skill, archify, open-design, deer-flow, ruflo.