Instruments

Every instrument in your command center

Forty-plus engines across six product pillars. Observability, control, memory, orchestration, extensibility, and team analytics — all over the same trace data, all working on any AI coding tool.


Pillar I — Observability

See every instrument, in real time

The foundation. Everything your AI coding tool is doing, visible the moment it happens — no scrollback hunting, no black boxes, no after-the-fact forensics.

Context Monitor

A live x-ray of the context window

Real-time token gauge, per-file relevance scores, and drop alerts. See what the AI can still see — and re-inject any dropped file with one click.

Process Monitor

Every agent, every sub-process

Real-time agent tree for every spawned process, tool execution, and sub-agent task. Pause, resume, or kill directly from the UI.

Flight Plan

Set the goal. Track the thread.

AI-decomposed step breakdown from a single goal. Steps auto-complete from trace matching. Divergence detection flags plan drift.

Loop Detector

Catch edit thrashing, search spirals, error cascades

Detects three failure patterns in real time: same file edited 5+ times, 8+ consecutive searches without edits, 4+ tool failures in a row. Severity escalates on repeated triggers.

Persistent Terminal

Your terminal, but it remembers

Daemon-backed PTY survives app restarts, view switches, and reboots. Snapshot-based attach restores any historical session state instantly.

Token & Cost Tracking

Real-time spend, ground-truth or estimated

Per-model pricing, live cost gauge, and an explicit confidence badge that distinguishes API-reported usage from heuristic estimates.

Session Replay

Watch any session like a video

Interactive playback with scrubber, speed control (1x/2x/4x/8x), and code/conversation toggle. Share any session with a link — redaction controls included.

Timeline & Activity

Searchable, filterable event stream

Trace-grouped timeline with category filters, sort toggles, and a properties panel for deep trace inspection.

Proactive Alerts

Problems surface before they bite

Stuck developer detection, rabbit hole alerts, budget spikes, context collapse warnings, and repeat tool failures — surfaced the moment patterns emerge.


Pillar II — Control

Define the boundaries, gate the progress

Seeing isn’t enough. Define what the agent can touch, review every plan step before it continues, and rollback to any checkpoint safely. The agent works inside your rules, at OS level.

Scope Boundary

Define allowed files and directories

If the agent goes off-limits, FSWatcher catches the write in ~100ms. Operon reverts the file, pauses the PTY via SIGTSTP, and shows you the diff with approve or reject.

Checkpoint Gates

Review before the agent continues

Between plan steps, review all changes before the agent proceeds. Named git snapshots at each gate let you rollback to any checkpoint with one click.

Intent Monitor

Real-time goal-drift detection

Continuous comparison between declared intent and observed activity from EventPipeline tool events. Heuristic checks (out-of-scope ratio, file count, consecutive errors) fire the moment they diverge.

Confidence Scoring

6-factor risk score on every checkpoint

File count, dependency depth, scope proximity, context pressure, historical success rate, and code complexity — scored and surfaced at every gate before you approve.

Failure Pattern Recognition

Learn from recurring rejections

Auto-detects patterns in checkpoint rejections and scope violations. After N rejections in a directory, suggests scope rules to prevent repeat mistakes.

Rollback & Git Snapshots

Every step is a named git tag

Checkpoint manager creates git tags at each gate. Approve, reject, or rollback to any prior snapshot — full rollback without losing work on other sessions.


Pillar III — Memory & Intelligence

Every session makes the next one smarter

Decisions, patterns, failure modes, peak hours — built from your own sessions, not a generic model. The instruments adapt to how you actually work.

Decision Memory

Architectural decisions, auto-captured

Auto-extracted from conversations via Claude Haiku. Searchable, tagged, and scored by confidence. Never lose the reasoning behind a choice — even across sessions and team members.

Memory Timeline

See how project memory evolves

Chronological memory view with superseded values. Toggle between grid and timeline. Understand what the project remembered, and when it changed its mind.

Memory Conflict Resolver

Detect contradictions, keep the audit trail

Jaccard-similarity detection surfaces memory conflicts in real time. Keep-existing or use-new resolution with a full audit trail of every merge decision.

Auto AGENTS.md

Generated on session end

At session end, Operon writes AGENTS.md to the repo with captured decisions, patterns, and project context. If the file is Operon-generated, it updates in place.

Session DNA

Personal coding intelligence

Peak hours, tool preferences, plan abandonment, failure modes, context exhaustion rate — built from your sessions. The more you fly, the smarter the instruments get.

Pre-flight Intelligence

Know the risk before you start

Complexity assessment, risk signals, codebase alerts, and suggested steps — debounced as you type your goal. A briefing that prevents problems instead of reacting to them.

Prompt Copilot

Quality score + rewrite suggestions

Seven-rule analysis (file refs, action verbs, length, outcome, scope, pronouns, testing) runs on your goal text. Badge + inline suggestions in the New Session dialog.

Prediction Engine

Historical matching for step outcomes

Matches the current step against traces from similar past steps. Returns success probability, likely failure modes, and estimated time. Wired into every checkpoint review.

Cross-Session Intelligence

Difficulty map, approach patterns, cost prediction

Pure SQL aggregation over your session history. Per-directory difficulty map, approach fingerprinting (plan-first / test-first / iterate / explore-first / greenfield), and cost prediction from keyword-similar past sessions.


Pillar IV — Orchestration

Decompose goals, coordinate agents

Enter a goal. Operon decomposes into subtasks, recommends tools per task type, dispatches work, and handles the handoff — including worktrees and remote machines.

Task Decomposition

Enter a goal. Get a plan.

Heuristic goal → subtask DAG based on keyword patterns (add / fix / refactor / migrate / test / document). Tool recommendations per subtask.

Tool Recommendation

Data-driven tool picks

Scores each tool by task-type keyword matching and your historical success rate from the traces table. Claude Code for architecture, Cursor for UI, Aider for quick fixes — from your own data.

Orchestration Manager

Plan lifecycle, end-to-end

Full plan lifecycle: create, start, pause, resume, cancel. Session linking, onSessionEnded advances subtasks, plan cards with progress bars in the Orchestration view.

Worktree Orchestrator

Four modes, zero leakage

In-repo, new-worktree, pooled (warm pool), or remote (SSH). Pool warmth indicator in the New Session dialog. Default-preservation cleanup and reclaim-on-archive — worktrees don’t leak.

SSH Remote Sessions

PTY over SSH, native UX

RemoteSessionBridge drops remote shell output into the same EventBus as local. Remote git (clone / fetch / worktree add / commit) over SSH. Connection pool with DB-backed credentials + injectable ssh2 factory.

Cross-Tool Context Bridge

Seamless handoff between tools

When session A (tool X) ends and session B (tool Y) is active in the same project, Operon surfaces a context bridge panel with cross-tool info. Auto-dismisses after 60s, dismissed IDs persisted.


Pillar V — Extensibility

Wrap any tool, connect any source

One adapter system for every AI tool. One MCP hub for every agent. Skills, automations, webhooks, and issue imports — so Operon slots into the stack you already have.

Universal Adapter System

5 tools × 3 data tracks

Claude Code (hooks), Cursor / Codex / Gemini CLI / Aider (PTY regex + stream JSON). AdapterRegistry auto-detects installed binaries. EventPipeline feeds all tracks into one Trace model.

MCP Hub

Install once, propagate everywhere

Install MCP servers from one place; Operon writes the right config into every agent profile (Claude Code / Cursor / Gemini / Aider). First-write confirmation dialog before touching any config file.

Skills

Skill manifests, per-agent binding

Parse skill manifests, install into agent profiles, bind per-agent. Full RPC CRUD + Settings UI. Browse, install, and remove without leaving Operon.

Automations

Cron + templates + triggers

AutomationEngine runs on cron schedules or trigger events. Pluggable ActionRegistry — custom action adapters hang off the registry. Per-automation status, last run, dry-run preview.

HMAC-verified Webhooks

Inbound triggers from GitHub + Linear

WebhookReceiver verifies HMAC signatures on every inbound webhook. Failed signature = 401, no silent drops. Trigger automations from PR events, issue updates, CI failures.

Issue Import

Linear, GitHub, Jira — one schema

Shared issue schema across three providers. IssueImporter fans out to all sources with per-source failure isolation. IssuePicker wired into the New Session dialog — seed a session with full issue context.

PR Draft Generator

From session traces to PR body

Heuristic body generator: files grouped by section, decisions → rationale block, TODOs → follow-ups list. Copy-to-clipboard or (roadmap) push to GitHub via the integration client.


Pillar VI — Teams & Analytics

The whole team, on the same panel

Cost dashboards, best practice extraction, knowledge sharing, tool benchmarking, diff quality, code impact — team-wide intelligence over the same trace data.

Team Observability

Cost, best practices, knowledge, benchmarks

Four dashboards: per-member cost with weekly trends, best practice extraction (members with ≥70% success rate per tool+category), knowledge sharing from hard directories, and per-tool benchmarking across the team.

Code Impact Tracker

Did the AI’s changes stick?

Per-file snapshots at session end, cross-session churn detection over a 30-day lookback via git diffNameOnly. Detects files AI edited that were later manually modified.

Diff Quality Analyzer

0–100 quality score per diff

Static analysis with 4 heuristic checks (large functions >50 lines, explicit any types, TODO/FIXME comments, commented-out code). Deduction scoring, wired into every completed trace.

Cost Intelligence

Spend, trends, model breakdown

Per-session, per-project, per-developer attribution. Model-tier breakdown (Opus / Sonnet / Haiku). Budget alerts with warning, critical, and exceeded thresholds.

Analytics Dashboard

Six categories, session + project level

Cost intelligence, productivity velocity, code impact heatmaps, session quality KPIs, tool usage distribution, smart alerts — via recharts, scoped to session or project.

Agency Workflow

Project members, PM dashboard, client reports

Multi-tenant project membership with role scoping. PM dashboard with real-time team activity. One-click client reports — sessions, decisions, deliverables.

Admin Audit Log

Full event stream for admins

Filterable by actor, resource, and time range. Shipped with the Superadmin web app — search, suspend, impersonate, feature-flag toggles.

Cloud Sync + Realtime

Outbox pattern, instant fan-out

13 syncable tables with outbox-pattern push/pull, conflict resolution, and Supabase Realtime for instant team sync. RLS enforced on every cloud_* table.


Universal Adapter System

One command center. Any tool.

Operon doesn’t pick winners. All instruments above work identically regardless of which tool you use. The adapter system routes data from any CLI into the same Trace model — via hooks where supported, PTY regex everywhere else.

TRACK 1 — HOOKS

Claude Code

Full hooks API — structured tool names, inputs, outputs, sub-agents, session context. Richest data path.

TRACK 2 — PTY

Cursor

PTY interception with regex patterns. Works with Cursor’s terminal without any config.

TRACK 2 / 3

Codex

PTY + stream JSON parsing for structured output with —output-format stream-json.

TRACK 2 — PTY

Gemini CLI

PTY output regex analysis. ANSI-cleaned, idle-timeout trace completion.

TRACK 2 + git

Aider

PTY + git diff integration. Auto-detects binary, health-checked on session start.

Want to see the full adapter + integrations story? See /integrations.


Every instrument, on every session

Private beta — join the waitlist to get an invite when your slot opens up.

Join the waitlistView pricing