TESIGN
SAVED

EN · KO

  1. TESIGN / RADAR
  2. OpenResearch

OpenResearch

Research agents for researchers

WHO USES ITResearcher · ML engineer · Planner

Runs several research agents in parallel on any model you choose.

★ 3.4k▲ +506 / 7dDaily star increases over 14 days. Hollow bars mean no data. The last day may be partial.2026-09-03 no data2026-09-04 no data2026-09-05 no data2026-09-06 no data2026-09-07 no data2026-09-08 no data2026-09-09 no data2026-09-10 +102026-09-11 +572026-09-12 +1062026-09-13 +592026-09-14 +112026-09-15 +1322026-09-16 +131largest one-day increase in the 14 days+132last 14 days · stars per dayhollow = no data

3,367 stars · checked on GitHub GitHub check 30 h late · incl. +160 observed via GH Archive since then · 7-day +506 observed via GH Archive (as of )

RANKS Rising this week #11 SCIENCE #3

RISING +146 ★ / 24h

OpenResearch landing page: 'Autoresearch on your machine' on white, with Windows (beta) and macOS download buttons.

TESIGN TAKE

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

TRY

AT A GLANCE

LICENSE
MIT
USAGE
Use, change and redistribute, commercially too. Keep the notice.
LANGUAGE
Rust
PLATFORM
macos · linux · windows · cli
ACTIVITY
last commit 1 day ago () · latest release v0.2.2 () · 124 releases
COMMUNITY
9 contributors · 28 open issues (incl. PRs) · made by: an organization
SOURCES
GitHub
OPEN SOURCE
YES
FIRST SEEN
CATEGORY
AI · SCIENCE

A summary, not legal advice.

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
AT SOURCE
KEPT
STAR DELTA
+146 ★ / 24h
CREATED → FIRST SEEN
98d
WHEN FIRST SEEN
1,716 ★
SOURCES
GitHub

The same facts in machine-readable form — View as Markdown · JSON

SIMILAR TOOLS

Up to five from AI by ★ total: edited entries first, then repository cards; this entry is highlighted. Drawn from the same stored snapshot as the rankings — a comparison, not a recommendation.

IMAGENAME★ TOTAL▲ 7dLICENSEPLATFORMLAST PUSH
ECC README banner: headline 'The operating system for AI agent harnesses', harness chips, and skill, agent and command lists.
eccSkills, memory and security for agents★ 259k▲ +832MITpermissivewindows · macos · linux · cli
Hermes Agent landing: blue background, the headline 'The agent that grows with you' and an engraving-style winged figure.
Hermes AgentSelf-improving personal agent★ 246k▲ +375MITpermissivelinux · macos · windows · android · cli
DeepSeek Harness landing: blue background, the headline 'Everything is a plugin' and a quick-start box with the npx command.
DeepSeek HarnessPlugin agent harness for developers★ 225k▲ +1,356MITpermissiveweb · cli
OpenResearch landing page: 'Autoresearch on your machine' on white, with Windows (beta) and macOS download buttons.
OpenResearchResearch agents for researchersTHIS ENTRY★ 3.4k▲ +506MITpermissivemacos · linux · windows · cli
mattpocock/skillsCARD★ 261k▲ +872MITpermissive—

ALSO WORTH SEEING

OpenHunterAILocal AI red-team workspaceOpenHunterAI's homepage, labelled "AUTHORIZED EXTERNAL SECURITY TESTING," listing its five-stage process from scope verification to reporting.Self-host
★ 165▲ +15 / 7d
An alpha-stage local workspace that runs attacker-style security assessments — strictly against public targets you own or are authorized to test.MartinLoopExecution-control CLI for coding agentsMartinLoop's homepage headline: "Watch your AI burn $5.20. Then watch MartinLoop close the loop for $2.30."
★ 130▲ +21 / 7d
Wraps a coding agent with a spend cap and a verifier, so "I'm done" comes with an evidence-backed receipt instead of just a claim.Spec KitSpec-first process for coding agentsSpec Kit docs landing page — the headline 'Build with a spec, fix a bug, or assess an idea' and the uv tool install specify-cli commandInstall to use
★ 137k▲ +560 / 7d
Makes your coding agent write the spec first, then plan, build and verify against it.HindsightNarrative map for YouTube viewersHindsight landing page: thousands of video dots grouped into issue clusters, with a central search box for a topic, creator or YouTube link.Use in the browser
★ 0▲ 1 HN
Remembers 49,411 videos, maps 22,904 by issue, traces how a YouTuber's argument changed.

TIMELINE

  1. Repository created
  2. FIRST SEEN BY TESIGN