Parcha-ai/agentrun

AgentRun is an open-source platform that supercharges your agents. It adds self-improvement, durable execution and a control plane on top of your favorite agent harness. Your agents become smarter, more fault tolerant and use fewer tokens with every run.

460 stars · 36 forks · JavaScript

Quick update: star history is from the full report of Nov 8, 2026.

At risk

No human commits in a year.

Why

No human commits in the last year. (source 1, source 2, source 3, source 4)

What would change this

A release or merged commit from a maintainer.
Partly checked: maintenance (Commit counts are estimated: the commit sample stops before the window start, so GitHub's totals were scaled by the sampled bot share.; Authors in the last 90 days are counted from the sampled commits only.; No human commit appears in the sampled history, so the last human commit date is unknown.; Most commits in the last year come from bots.; Only 3 recent issues can be checked for a response, too few to measure response time.; 69 pull requests are open and nobody has committed in a year.)
Partly checked: people (No human commits in the last 365 days, so shares use the newest 100 commits back to 2025-11-12T02:40:18.674Z.; Only 0 human commits were found, too few to judge who maintains the project.)

Maintenance

Partial

Dormant

Human commits, 30 days: 0
Human commits, 90 days: 0
Human commits, 365 days: 0
Bot share of commits, 365 days: 100%
Last commit: Nov 12, 2026 (11 hours ago)
Last human commit: none found
Authors, 90 days: 0
Last release: Nov 6, 2026 (5 days ago)
Median PR merge time: 2 hours

Too few recent issues to measure responsiveness.

Commit counts are estimated: the commit sample stops before the window start, so GitHub's totals were scaled by the sampled bot share.
Authors in the last 90 days are counted from the sampled commits only.
No human commit appears in the sampled history, so the last human commit date is unknown.
Most commits in the last year come from bots.
Only 3 recent issues can be checked for a response, too few to measure response time.
69 pull requests are open and nobody has committed in a year.

Sources: Commits, Releases, Merged pull requests, Issues

People

Partial

Owner: Organization
Commits sampled: 0 since Nov 12, 2025
Authors for half of commits: 0
Authors for 80% of commits: 0
Contributors: 4

No human commits in the last 365 days, so shares use the newest 100 commits back to 2025-11-12T02:40:18.674Z.
Only 0 human commits were found, too few to judge who maintains the project.

Sources: Commits, Contributors

Stars

Complete

Not enough data, confidence medium

Bars show stars gained each week. Red bars overlap a burst.

Anyone can buy stars for any repo; bursts alone don't prove the owner did.

Not enough star history yet to judge the star count.
Star history from the full report of Nov 8, 2026; this update did not re-read it.

Sources: How star history is analyzed

Risk

Complete

Flags

No risk flags.

License

Now: Apache-2.0 (OSI-approved)
A year ago: Not known

Packages

No published packages found.

Sources: GitHub: Parcha-ai/agentrun

Compare

Weighing Parcha-ai/agentrun against an alternative? See both side by side.

Badge

Add this to a README to show the current verdict:

[![RepoRadar](https://reporadar.ai/Parcha-ai/agentrun/badge.svg)](https://reporadar.ai/Parcha-ai/agentrun)

Follow

Get told when this verdict changes. Add the feed to any feed reader: you get one entry per change, not one per refresh.

https://reporadar.ai/Parcha-ai/agentrun/feed.xml

Open the feed

See all

Mathux/TEMOS 457 stars
visinf/1-stage-wseg 385 stars
fatangare/LogcatViewer 296 stars
vixues/LeAgent 242 stars
newideas99/open-dungeon 241 stars
joeseesun/qiaomu-app-review-insights 231 stars

Earlier verdicts

Nov 12, 2026: At risk
Nov 11, 2026: At risk
Nov 10, 2026: At risk
Nov 9, 2026: At risk
Nov 8, 2026: At risk

Computed 11 hours ago · method 2026.10.2

Why