Turns an agent's execution into a reversible, Git-like trace
Tool 
Unclaimed
Are you the maintainer?
Claim this page →Shepherd
Turns an agent's execution into a reversible, Git-like trace
GitHub score unavailable
No votes yet
01 / About
About Shepherd.
02 / Credibility
Derived from GitHub, not voted.
Public-signal score, discounted for bought-star and bot-stargazer patterns — not a user rating. How scores are calculated.
—
Score unavailable
We haven't been able to compute a GitHub credibility score for this tool yet. It'll appear here once the evaluator runs.
03 / Discussion CREDIBILITY-GATED
Discussion · 0
Reading is open to everyone. Only verified humans or builders at GitHub B+ can post or vote — every comment carries its author's credibility.
🔒 Read-only view — verify your identity or
reach GitHub B+ to join the discussion. Get verified
- No comments yet — be the first to start the discussion.
04 / Related
More to explore.
ToolAgenta
Agenta-AI
Evaluate and compare different agent configurations side by side.
B
ToolAmnesia
erasmus
This is a test. Delete me.
Score unavailable 0% recommend · 1 rater
ToolBrainDB
dimknaf
Postgres+pgvector long-term memory (typed entities, graph, decay) with a native Hermes plugin.
C
ToolBrowser Use
browser-use
Control browsers programmatically with LLM agents through a high-level, LLM-friendly API.
A
ToolCaveman
JuliusBrussee
A Claude Code skill that cuts roughly 65% of output tokens via caveman-speak.
C JavaScript
Toolcaveman-code
JuliusBrussee
A TypeScript implementation of the caveman compression engine.
C TypeScript
05 / Build
Build with Shepherd.
Browse the catalogue for frameworks, tools, and blueprints — each scored on real GitHub credibility.
Browse the catalogue