How fast Balanov/uncut 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
Nov 1 – Nov 4, 2026
Stars +236in 4 days
0100200300
207
Forks +14in 4 days
0246
5
Merged PRs 0in 4 days
01
Trendshift Trendingwhere the repository ranked each day it made the top 25
Not in the Trendshift top 25 in this period
Nov 1Nov 2Nov 3Nov 4
The left and right arrow keys step from day to day; Home and End go to the first and the last
Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day
Stars gained
Forks gained
Merged PRs
Sun, Nov 1, 2026
+0
+0
0
Mon, Nov 2, 2026
+207
+5
0
Tue, Nov 3, 2026
+20
+5
0
Wed, Nov 4, 2026
+9
+4
0
Total
+236
+14
0
1#1 on the list
7Rank that day
Not trending
Social mentions
Recent discussions about this repository across the web
1 post
"no silent cuts" is what made me stop. half of harness pain is not knowing what got dropped from context. uncut: one 7 MB static binary, four tools, plain stdin/stdout.
Found a coding agent harness whose feature list is mostly things it refuses to do. No compaction. No sliding window. No retries. If the provider cuts the answer at its output limit, it exits with an…
Uncut is built for running coding agents unattended, not for interactive coding: CI and automation. It can fix failing tests, review PRs, or write changelogs inside a CI job or container, and its…
UNCUT sends the whole conversation to the model on every call and never trims file or command output. If the reply hits the output limit, it exits with an error. Headless coding agent harness, one 7…
open-source find: UNCUT, a tiny headless coding agent harness. one 7 MB Go binary, four tools, stdin/stdout. it never summarizes or trims context, and if the model's output gets cut off it errors out…
The agent harness you can fork. A working agent loop with compaction, sessions, approvals, a terminal REPL, a local dashboard and ACP, where every tool, skill, hook and policy is a file you can change. Build your own internal or coding agent on any model.
Ghost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude Code or Codex, with none of their dependencies or model constraints.
