# OpenResearch

> Research agents for researchers — Runs several research agents in parallel on any model you choose.

- Page: https://tesign.com/en/item/openresearch/
- JSON: https://tesign.com/en/item/openresearch/index.json
- Korean Markdown: https://tesign.com/item/openresearch/index.md
- Generated: 2026-09-17 01:56 UTC

## RANKS

- Rising this week #11 · SCIENCE #3 (As of 2026-09-16 21:00 UTC)

## Numbers

- 3,367 stars — checked on GitHub 2026-09-15 19:33 UTC (+160 observed since the check)
- 7-day +506 observed via GH Archive (as of 2026-09-16 21:00 UTC)
- 24h +146 ★ · 30d +506 ★ (as of 2026-09-16 21:00 UTC)
- Star total = the value last checked on GitHub (stars_checked_at) + increases observed via GH Archive since. The 24h · 7d · 30d gains are GH Archive hourly events summed to the reference time (as_of). No score of ours.

## AT A GLANCE

- LICENSE: MIT (permissive) — https://spdx.org/licenses/MIT.html
- USAGE: Use, change and redistribute, commercially too. Keep the notice.
- OPEN SOURCE: YES
- LANGUAGE: Rust
- PLATFORM: macos · linux · windows · cli
- CATEGORY: AI · SCIENCE
- Tags: research · agents · parallel
- SOURCES: GitHub https://github.com/alphaxiv/openresearch
- TRY: https://openresearch.sh/

## ACTIVITY

- Last commit: 2026-09-15 19:32 UTC
- Latest release: v0.2.2 (2026-09-14)
- Contributors: 9
- Open issues (incl. PRs): 28
- Made by: an organization
- Checked on GitHub: 2026-09-15 19:33 UTC

## Signals and evidence

- RISING · +146 ★ / 24h

## TESIGN TAKE

One agent and one worktree per research direction; built for people who run many experiments.

## WHY IT MATTERS

Research handed to an agent runs one thread at a time, so a topic with several branches takes as long as the branches add up to. openresearch runs research agents in parallel and leaves the choice of model to you. It is written in Rust under the MIT license and has its own homepage. The repository description is one line, so supported models and usage have to be read from the docs.

## BUILD FROM THIS

- An internal research tool that splits competitor and market work into branches
- A comparison run that pits one model's output against another's

## WHO IT'S FOR

- Researcher — runs several hypotheses in parallel with a record
- ML engineer — tracks experiment variants in a git-based tree
- Planner — splits competitor and market research into branches

## START IN 5 MINUTES

```
# macOS/Linux CLI (Windows: install from Releases, beta):
$ curl -LsSf https://openresearch.sh/install.sh | sh
$ orx up
# The local dashboard opens at http://127.0.0.1:4791
```

## CAVEATS

- Requires Claude Code, Codex, OpenCode or Cursor to be installed
- Official builds send usage analytics; orx telemetry off disables them
- Windows support is beta and needs Git for Windows

## RECEIPT

- FIRST SEEN BY TESIGN: 2026-09-13 07:43 UTC
- AT SOURCE: 2026-06-07 01:51 UTC
- KEPT: 2026-09-13 11:32 UTC
- Published on TESIGN: 2026-09-13 11:32 UTC
- Text last updated: 2026-09-15 04:36 UTC

## How to read this

- This file was produced by the same build, from the same data, as the tesign.com item page. The text is editorial; the numbers are stored observations.
- null in the JSON means not observed — never zero. The Markdown writes [unconfirmed] for it.
- Star total = the value last checked on GitHub (stars_checked_at) + increases observed via GH Archive since. The 24h · 7d · 30d gains are GH Archive hourly events summed to the reference time (as_of). No score of ours.
- A summary, not legal advice.

[Image] https://tesign.com/img/openresearch-83e080b6be.png