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
LayerComponents
CLIinit, setup, peter, train, eval, ide, deploy
Context HubMemory DB, Event Bus, Indexer (port 4360)
Agent HarnessPeter Parker, RL agents, worktree isolation
LearningTraining buffer, policy head (14M params), build evals
PlatformDashboard, auth, cloud agents, team features
MeshSubway P2P for agent coordination

​
Components

​
CLI

The entry point. All commands go through tenet:
CommandPurpose
tenetLaunch Pi with TENET extensions
tenet initScaffold a new project
tenet setupAuto-detect metrics, create agents
tenet peterAgent orchestrator
tenet trainTrain policy head
tenet evalRun evals, check scores
tenet ideTerminal workspace
tenet deployDeploy to platform

​
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:
ComponentFormatLocation
JournalsJSONL.tenet/journal/*.jsonl
Training bufferJSONL.tenet/training-buffer.jsonl
Agent configsTOML.tenet/agents/*.toml
MemorySQLite.tenet/memory.db
Eval resultsJSONL.tenet/eval.jsonl
Policy weightsJSON.tenet/checkpoints/
FlowsYAML.tenet/flows/*.yaml
ConfigJSON.tenet/config.json

​
Platform (Cloud)

Optional hosted services for dashboard, auth, cloud agents, and team features.
APIPurpose
/api/tenet/memory/*Cloud memory sync
/api/tenet/trainRemote training
/api/tenet/policyPolicy inference
/api/tenet/tuplesTuple upload
/api/agents/*Cloud agent management
/api/sessions/*Session tracking

​
Subway Mesh

P2P agent coordination. Agents discover each other, send messages, broadcast events across machines.
AgentRole
Your Pi sessionCoding agent with TENET tools
browser.relayTerminal browser with DOM access
Other sessionsParallel agents on same or different 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