Skip to content
ADE Index

Agent Runner vs OpenRig vs Thrum

Up to four tools, row by row. We do not guess: a cell we have not verified says so.

How they differ

Pick this if…

Paraphrased from each maker’s own description. Select a line for the quote.

Sourced for OpenRig and Thrum, not yet for Agent Runner: Price (OpenRig: ; Thrum: · )

Sourced for OpenRig, not yet for Agent Runner and Thrum: Agents it runs (, ), Editors and systems (, , )

None of these tools has a sourced value yet for: model providers, bring your own key.

Dotted values open their quote. A capability not shown is not yet sourced; the tool may still have it.

About these tools

Agent Runner

OpenRig

Thrum

How to read the Index score

At a glance

Index score out of 100

Agent RunnerNot enough data yetOpenRig19Thrum15

Mindshare HN mentions, 90 days

Agent Runner0OpenRig5Thrum3

Adoption GitHub stars, not scored

Agent RunnerNot yet verifiedOpenRig8.9kThrumNo public repository

Release days last 90 days

Agent Runner8OpenRig44ThrumNot yet verified

Lowest monthly plan billed monthly, lower is cheaper

Agent RunnerNot yet verifiedOpenRigNot yet verifiedThrum$15.00/month

Platforms listed surfaces

Agent RunnerNot yet verifiedOpenRig3ThrumNot yet verified

Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only. After activation, the score is 80% mindshare plus 20% of the greater of mindshare and the vote score. GitHub stars do not affect the Index score. Mindshare uses a log scale; votes use the square-root curve and a 100-vote floor. Ranks use unrounded scores. Mindshare and adoption bars are log-scaled; the others are linear within this comparison. How the score is built

3 of 4
Agent RunnerAgent orchestrator
OpenRigMike Schwarz · Agent orchestrator
ThrumAgent orchestrator
Interface
OpenRig interface
thrum interface shown on the official site
What it is
Unattended coding-agent runs with worktrees, test gates and merges
Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.
Cross-tool messaging for Claude Code, Codex, Cursor and other coding agents
Category
Agent orchestrator
Agent orchestrator
Agent orchestrator
Pricing
Starts at (billing shown)
Not yet verified
Not yet verified
Lowest monthly plan
Not yet verified
Not yet verified
Free tier
Not yet verified
Plans
Not yet verified
  • Open-source softwareFree
Bring your own key
Not yet verified
Not yet verified
Not yet verified
Runs on
Linux
Not yet verified
Yes
Not yet verified
Windows
Not yet verified
Yes
Not yet verified
macOS
Not yet verified
Yes
Not yet verified
Models and agents
Model providers
Not yet verified
Not yet verified
Not yet verified
Models
Not yet verified
Not yet verified
Not yet verified
Drives these agents
Not yet verified
Claude CodeCodex
Not yet verified
Source and activity
Source
Not yet verified
GitHub stars
Not yet verified
No public repository
Release days, last 90 days
8
44Most
Not yet verified
Release days per week
Not yet verified
Latest release, any channel
v0.42.1 18 Nov 2026
v0.7.18 17 Nov 2026
Not yet verified
Index score
Score and rank
Not enough data yet
19 #75 Score 19.5; ranked on the unrounded score
15 #92 Score 15.1; ranked on the unrounded score
Mindshare
00 Hacker News mentions in the last 90 days
195 Hacker News mentions in the last 90 days
153 Hacker News mentions in the last 90 days
Adoption, not scored
Not yet verified
748,885 stars, read 18 Nov 2026
No public repository
Votes
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
Rank history
Not ranked
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch Agent Runner vs OpenRig vs Thrum on YouTube

More comparisons

Build your own