How fast erensrtky/cogit 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 3 – Nov 13, 2026
Stars +114in 11 days
02040
36
Forks +17in 11 days
024
4
Merged PRs 3in 11 days
0123
3
Trendshift Trendingwhere the repository ranked each day it made the top 25
Not in the Trendshift top 25 in this period
Nov 3Nov 5Nov 7Nov 9Nov 11Nov 13
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
Tue, Nov 3, 2026
+0
+1
0
Wed, Nov 4, 2026
+0
+1
0
Thu, Nov 5, 2026
+0
+0
0
Fri, Nov 6, 2026
+10
+3
0
Sat, Nov 7, 2026
+24
+3
0
Sun, Nov 8, 2026
+11
+3
0
Mon, Nov 9, 2026
+3
+1
0
Tue, Nov 10, 2026
+8
+1
3
Wed, Nov 11, 2026
+10
+0
0
Thu, Nov 12, 2026
+36
+4
0
Fri, Nov 13, 2026
+12
+0
0
Total
+114
+17
3
1#1 on the list
7Rank that day
Not trending
Social mentions
Recent discussions about this repository across the web
1 post
Opened a file an agent rewrote Tuesday and couldn't say why it dropped the retry queue. The chat was gone, the commit said "refactor". Tried cogit: Claude Code hooks save each prompt as a thought…
Your commit messages were always lies. "fix stuff" hid a two-hour argument with an agent. This one saves every prompt as a thought commit, and any line walks back to the message behind it. Blame used…
✨ Cross-agent skills that help coding agents use Entire context from Checkpoints, sessions, and git history to search past work, explain code, and hand off sessions.
🧠 The memory layer for your Git repository. Turn retained agent sessions, checkpoint history, docs, code structure, and durable facts into something you and your coding agents can actually query.
Give Claude Code a memory that evolves with your codebase. Hooks automatically capture sessions, the Claude Agent SDK extracts key decisions and lessons, and an LLM compiler organizes everything into structured, cross-referenced knowledge articles - inspired by Karpathy's LLM Knowledge Base architecture.
📜 Entire CLI hooks into your Git workflow to capture AI agent sessions as you work. Sessions are indexed alongside commits, creating a searchable record of how code was written in your repo.
jevmem saves the decisions, rules and failed approaches from your Claude Code chats to JEVMEM.md in your repo, and brings the relevant ones back next session.