Skip to main content
TENET is a collection of components that work together to create a learning system for AI agents.

​
System Overview

Your Project → Context Hub → Agents → Eval → Training → Policy Head → better agents tomorrow

​
Components

​
CLI

The entry point. All commands go through tenet:

​
Context Hub

The central coordination daemon. Runs locally on port 4360.
  • Memory database — SQLite with indexed memories, semantic embeddings, graph edges
  • Event bus — MAP (Multiplayer Agent Protocol) events for agent coordination
  • Periodic indexer — Indexes journal entries every 60s, code headers every 5 min
  • API server — REST endpoints for memory, events, context, eval

​
Agent Harness

Autonomous improvement agents that run in isolated git worktrees. The loop:
1

Eval before

Measure the baseline metric (coverage, quality, speed)
2

Agent changes code

In an isolated worktree — main branch is never touched
3

Eval after

Measure again. Did the metric improve?
4

Keep or revert

Score improved → advance branch, create PR. Regressed → git reset --hard
5

Record tuple

(state, action, reward) → training buffer. Policy head learns.

​
Storage Layer

Everything is files in your repo:

​
Platform (Cloud)

Optional hosted services for dashboard, auth, cloud agents, and team features.

​
Subway Mesh

P2P agent coordination. Agents discover each other, send messages, broadcast events across machines.

​
Data Flow

1

Session produces data

Agent sessions write journal entries and training tuples
2

Hub indexes everything

Context Hub indexes journals, code headers, embeddings
3

Policy head trains

Training buffer feeds the policy head — learns what works
4

Peter Parker orchestrates

Picks best next experiment based on policy predictions
5

Agents improve overnight

Run in worktrees, eval-gated, auto-PR on improvement