humanlayer/12-factor-agents
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
26.7k stars · 2k forks · TypeScript
Avoid
Avoid: no human commits in a year, and most questions go unanswered.
Why
- No human commits since September 2025, and only 0 of 8 recent issues got a maintainer reply. (source 1, source 2, source 3, source 4)
- One person wrote 94% of human commits in the last year, and no human has committed in the last 90 days. (source 1, source 2)
What would change this
- A release or merged commit from a maintainer, or replies to recent issues.
- A human commit in the last 90 days, or a second person taking a large share of commits.
Maintenance
CompleteDormant
- Human commits, 30 days
- 0
- Human commits, 90 days
- 0
- Human commits, 365 days
- 0
- Bot share of commits, 365 days
- 0%
- Last commit
- Sep 21, 2025 (1 year ago)
- Last human commit
- Sep 21, 2025 (1 year ago)
- Authors, 90 days
- 0
- Last release
- none found
- Median PR merge time
- 3 hours
Responsiveness: of 8 recent issues, 0% got a maintainer reply. Median first response: n/a.
- No human commits in 365 days, and most issues go unanswered.
Sources: Commits, Releases, Merged pull requests, Issues
People
Complete- Owner
- Organization
- Commits sampled
- 100 since May 8, 2025
- Authors for half of commits
- 1
- Authors for 80% of commits
- 1
- Contributors
- 15
Top committers
- dexhorthy: 94% of commits
- kyu08: 2% of commits
- tofaramususa: 2% of commits
- szepeviktor: 1% of commits
- zyuanlim: 1% of commits
- No human commits in the last 365 days, so shares use the newest 100 commits back to 2025-05-08T04:50:57Z.
Sources: Commits, Contributors
Stars
CompleteOrganic, confidence high
Bursts
- Jul 3, 2025 to Jul 16, 2025: about 3.7k more stars than usual, peak 734 in one day, a spike that tapers off. Outside explanation: a jump in forks.
- Sep 8, 2025 to Sep 10, 2025: about 206 more stars than usual, peak 169 in one day, a spike that tapers off. Outside explanation: a jump in forks.
- Dec 1, 2025 to Dec 5, 2025: about 152 more stars than usual, peak 65 in one day, a shape we can't classify. Outside explanation: a jump in forks.
- May 17, 2026 to Jun 1, 2026: about 2.8k more stars than usual, peak 747 in one day, a spike that tapers off. Outside explanation: a jump in forks, a jump in issues and pull requests.
- Jun 29, 2026 to Jun 30, 2026: about 215 more stars than usual, peak 175 in one day, a spike that tapers off. Outside explanation: a jump in forks.
- Jul 11, 2026 to Jul 11, 2026: about 130 more stars than usual, peak 150 in one day, a spike that tapers off. Outside explanation: a jump in forks.
- Jul 15, 2026 to Jul 23, 2026: about 324 more stars than usual, peak 85 in one day, a shape we can't classify. Outside explanation: a jump in forks.
- Sep 17, 2026 to Sep 18, 2026: about 363 more stars than usual, peak 343 in one day, a spike that tapers off. No outside explanation found, so this burst is unexplained.
- 5 stars GitHub has since removed (tracked since Oct 14, 2026).
Anyone can buy stars for any repo; bursts alone don't prove the owner did.
- The star history looks organic.
Sources: How star history is analyzed
Risk
CompleteFlags
No risk flags.
License
- Now
- Apache-2.0 (OSI-approved)
- A year ago
- Apache-2.0 (OSI-approved)
Packages
No published packages found.
Sources: GitHub: humanlayer/12-factor-agents
Badge
Add this to a README to show the current verdict:
[](https://reporadar.ai/humanlayer/12-factor-agents)Earlier verdicts
- Oct 14, 2026: Avoid
- Oct 14, 2026: Avoid
Computed 8 hours ago · method 2026.10.2