Anekenonso/FixLoop

FixLoop is an AI bug-fixer with a strict gatekeeper. It refuses to open a PR unless the exact test that failed now passes. The model proposes. Code decides. A recorded stop beats a fabricated PR.

Visit GitHub

Python

1 contributors

MIT License

FeaturedAdvertise to 180K+ monthly visitors

Busbar

Control what AI can do before it acts

Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

ClawBench

a benchmark for personal agents

Momentum

How fast Anekenonso/FixLoop is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Oct 9 – Oct 22, 2026

Stars +0 in 14 days

Forks +0 in 14 days

Merged PRs 0 in 14 days

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Oct 9Oct 11Oct 13Oct 15Oct 17Oct 19Oct 21

Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day	Stars gained	Forks gained
Fri, Oct 9, 2026	+0	+0
Sat, Oct 10, 2026	+0	+0
Sun, Oct 11, 2026	+0	+0
Mon, Oct 12, 2026	+0	+0
Tue, Oct 13, 2026	+0	+0
Wed, Oct 14, 2026	+0	+0
Thu, Oct 15, 2026	+0	+0
Fri, Oct 16, 2026	+0	+0
Sat, Oct 17, 2026	+0	+0
Sun, Oct 18, 2026	+0	+0
Mon, Oct 19, 2026	+0	+0
Tue, Oct 20, 2026	+0	+0
Wed, Oct 21, 2026	+0	+0
Thu, Oct 22, 2026	+0	+0
Total	+0	+0

#1 on the list
Rank that day
Not trending

Social mentions

Recent discussions about this repository across the web

Oct 122 posts
- We tried to break it- 20/20 adversarial attacks caught before git tampering, skips, escapes 0.0% false PR rate across 36 trials on SWE-bench Lite bugs - Flask & Requests Built with: @neatlogs…
  Read full on X, posted by @symplyKen
  @symplyKen · x.com
- We executed FixLoop on GitHub against a public fixture repository. The model resolved the swallowed exception in ' proved exit code 0 via the code gatekeeper, and opened a real PR on GitHub embedded…
  Read full on X, posted by @symplyKen
  @symplyKen · x.com
Oct 113 posts
- Measured results from 36 statistical trials + 3 real historical SWE-bench bug replays (Flask & Requests): False PR rate on gated runs: 0.0% (0 fabricated PRs) Real bug resolve rate: 3/3 (100%) Mean…
  Read full on X, posted by @symplyKen
  @symplyKen · x.com
- I tried to break my own agent: Built an automated 20-row Break Matrix to test deletion, assertion stripping, skips (pytest.skip), path traversal (../../), and oversized diffs. 20/20 attacks caught…
  Read full on X, posted by @symplyKen
  @symplyKen · x.com
- What happens when an ungated agent tries to fix an issue? In our baseline trial on Issue 03, the model submitted a patch that just added a comment, left the test failing, and declared victory.…
  Read full on X, posted by @symplyKen
  @symplyKen · x.com
Oct 101 post
- Agents that fix GitHub issues usually open a pull request whether or not the fix works. I'm building FixLoop for #neatHack: an AI bug-fixer with a strict gatekeeper. It refuses to open a PR unless…
  Read full on X, posted by @symplyKen
  @symplyKen · x.com