Skip to content
Jeju
AI Agents & Assistants
A local‑first agent harness that lets developers define, bound, run, and evaluate agents via a single config manifest.
Go
·
Latest v0.6.0 · 4h ago
Security brief →
Features
-
Config‑defined behavior with prompts and skills stored alongside the manifest
-
Strict execution boundaries (workspace, tools, permissions, timeouts)
-
Effect‑level inspection recorded in an append‑only `trajectory.jsonl`
-
Portable agent bundles for reuse or higher‑level AI invocation
No immediate action
v0.6.0
Feature
·
Output schema validation
No immediate action
v0.5.0
New feature
·
Pareto search + team trajectories + cache tracking
No immediate action
v0.3.0
Mixed
·
Trajectory log refactor + evolve example + commit planner
No immediate action
v0.2.0
Feature
·
final‑only run output mode
No immediate action
v0.1.1
Bugfix
·
API rate‑limit fix
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
Languages
Go
·
Shell
·
Python
Install & Platforms
Install via
shell-script
go
Search tools, categories, lists, and users
Use ↑↓ to navigate, Enter to open, Esc to close
No results for ""
⌘K to open
↑↓ navigate
⏎ open
