Python · MIT
brandynfisher/ToolReplay
Audit AI agent tool-call transcripts: hash-chain sealing, deterministic replay, and scope overreach checks. Dependency-free Python CLI.
★ 53
Stars
6 forks · 1 open issues
—
Growth · stale
We stopped seeing this repository in its topic's top results, so its star count is frozen at the date it was last read. Subtracting from a frozen number would read as zero growth, which would be false, so no rate is shown.
15.7
Momentum / 100
see the breakdown below
55d ago
Created
last push 54d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | — — no measurable rate |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 10.7 | last push 54d ago; decays to zero at 180 days |
| Scale | 15 | 5.0 | 53 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 15.7 | capped at 35 because growth is unmeasured |
Detail
| Topics | ai-agentsauditclideterminismhash-chainjsonlpermissionspythonreplayscopesecuritytool-call |
| Matched on | AI Agents (ai-agents) Dev Tools (cli) Security (security) |
| Short window | +0 stars over 8 days = 0.0/day |
| Long window | +-131 stars over 26 days = -5.0/day |
| Lifetime average | 1.02 stars/day over 52 days |
| First seen here | 2026-10-11 |
| Last read | 11d ago |