jamjet-labs/jamjet
AI Agents & AssistantsA unified safety‑policy engine that blocks unsafe tool calls, enforces human approval, caps costs, and records a durable audit trail across any AI agent framework.
Features
- Blocks disallowed tool invocations at runtime (e.g., delete operations).
- Pauses risky actions for mandatory human approval with persistence.
- Enforces per‑agent, per‑run cost caps to limit spending.
- Generates a tamper‑proof audit trail that survives crashes or regulator review.
Recent releases
View all 13 releases →Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
About
Stars
12
Forks
5
Languages
Rust
Python
TypeScript
Downloads/week
440
↓33%
NPM Maintainers
1
Contributors
6
TypeScript
Types included ✓
Install & Platforms
Install via
pip
