Install npm install -g jfl # package name during migration
Package name is jfl during migration. CLI commands work as both jfl and tenet.
Initialize New project: This runs init → setup → launch in one command. Creates the workspace, configures agents for your stack, deploys CI workflows, and opens your editor.
Existing project: cd your-project tenet init tenet setup
init creates the context layer. setup analyzes your codebase and creates personalized RL agents.What gets created your-project/ ├── .jfl/ │ ├── config.json # Project config │ ├── journal/ # Session journals (JSONL) │ └── agents/ # Agent configs (TOML) ├── eval/ # Eval scripts for your stack ├── knowledge/ # VISION, THESIS, NARRATIVE ├── CLAUDE.md # Agent instructions └── AGENTS.md # Pi agent instructions
Run your first agent test-coverage Metric: coverage_percent (maximize) code-quality Metric: quality_score (maximize)
Run one round:
tenet peter agent test-coverage --rounds 1
Baseline: 0.1276 Round 1 +0.0031 KEPT 48 tests added Coverage: 12.7% → 13.1%
Check health [ok] Context Hub (port 4360) [ok] Memory: 349 entries, 349 embedded [ok] Agents: 5 configured All checks passed.
What’s next
How it works The RL learning loop, eval system, and agent architecture.
Agent configuration TOML config reference — metrics, scope, eval scripts.
Memory system How TENET remembers and learns from history.
Peter Parker The nightly orchestrator that runs your agents.
