jamjet-labs/jamjet
AI Agents & AssistantsAn action‑control plane that lets you write a single safety policy and enforce it across any AI agent framework, with runtime blocking, approval pauses, cost caps, durable audit logs, and replay capabilities.
Features
- Unified policy file for all agents (hooks, guardrails, SDKs, custom runtimes)
- Runtime enforcement to block unsafe tool calls
- Human‑in‑the‑loop approval pauses for risky actions
- Cost capping per agent/run/project
- Durable audit trail that survives crashes and regulator reviews
Recent releases
View all 19 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
20
Forks
5
Languages
Rust
Python
TypeScript
Downloads/week
440
↓33%
NPM Maintainers
1
Contributors
6
TypeScript
Types included ✓
Install & Platforms
Install via
pip
npm
cargo
go
binary
Platforms
linux
macos
windows
arm64
