Skip to content

kyoo-147/Together

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

53 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

Together logo

together

Local Codex operator console for observable AI worker teams.

Chat in Codex. Watch the work in Together. Route, verify, review, and recover locally.

Together is a terminal-native control plane for scoped AI work, live worker output, agent readiness, review gates, and local-first execution history.

Codex stays the preferred integrator. Worker agents stay replaceable, scoped, and observable.

GitHub stars License Last commit Installable skill

Install | Quickstart | How It Works | Governance | Repo Map

Together Monitor and Chat Dock

Product One-Liner

Together is a local-first CLI/TUI control plane that lets developers keep working in Codex while seeing, routing, verifying, and reviewing the AI worker activity behind the scenes.

It is currently a dogfooding-stage operator console:

  • together starts or connects to a local daemon.
  • The terminal UI shows Project, Tasks, Task Monitor, Live Work Feed, Agents, Needs Attention, and Chat Dock.
  • Codex app / skill requests and Together chat requests flow into the same daemon event log.
  • Worker selection is deterministic and observable.
  • Task contracts define scope, allowed files, denied files, deliverables, and success criteria.
  • Verification and approval gates block unsafe or out-of-scope work.
  • Settings, theme presets, status, review, and packaging commands are available from the CLI.

Longer-term, Together aims to become an AI Department Operating System for local and team AI worker workflows. The current product surface is the CLI/TUI operator cockpit.

It is:

  • a terminal-native monitor for Codex-led AI work
  • an agent control plane
  • a work governance layer
  • a verification and review gate
  • a local routing and failover layer
  • a measurement loop for real developer sessions

It is not:

  • another AI assistant
  • a replacement for Codex, Claude, Gemini, Amp, OpenCode, or other workers
  • a generic terminal multiplexer
  • a claim of finished enterprise orchestration

Screenshots

Monitor + Chat Dock

Together main monitor and chat dock

Featured Views

Task Monitor Tasks
Together task monitor view Together tasks view
Task Detail Settings
Together task detail view Together settings view

Analysis Gallery

These mockups and analysis visuals capture the product direction behind the current interface.

Architecture Governance
Together architecture analysis Together governance analysis
Department Flow Operations
Together department flow analysis Together operations artifact analysis
Registry Failover
Together registry analysis Together failover analysis
Hero Concept Ready-State Model
Together hero concept analysis Together ready-state analysis

Production Quickstart

For customers who just want to run Together:

git clone https://github.com/kyoo-147/together_working.git
cd together_working
cargo build -p cli --release
target\release\together.exe

The terminal app auto-starts the local daemon, opens the Monitor + Chat Dock UI, and writes runtime state under .together/.

Useful CLI commands:

target\release\together.exe doctor
target\release\together.exe status --json
target\release\together.exe chat --source codex-app "create a scoped landing page task"
target\release\together.exe proposal confirm <proposal-id>
target\release\together.exe settings set --theme "Ocean Blue"

Windows install/package helpers:

powershell -ExecutionPolicy Bypass -File scripts\install.ps1 -AddToPath
powershell -ExecutionPolicy Bypass -File scripts\package-windows.ps1

Codex skill bridge:

python skills\together\scripts\submit-chat.py "create a scoped task for the landing page"

The older Python scan/report commands remain available as compatibility tools for readiness reports.

Product Principles

Together is built around a simple operating model:

  • Codex is the preferred integrator.
  • Workers are scoped and replaceable.
  • Tasks are small enough to verify.
  • Runtime state is observable.
  • Approval depends on evidence, not trust.

Why this exists:

  • giant contexts grow too expensive
  • one worker should not own every step
  • routing should be explicit
  • verification should not be optional

Install

Install full skill:

npx skills add https://github.com/kyoo-147/together_working

Install only main skill:

npx skills add https://github.com/kyoo-147/together_working --skill "together"

Skill entrypoint stays here:

skills/together/SKILL.md

Quickstart

Scan machine:

python skills/together/scripts/discover-agents.py --format table

Write operator snapshot:

python skills/together/scripts/doctor.py

List changed files:

python scripts/changed-files.py --json

Validate one task:

python scripts/validate-task.py examples/task-contract.example.yaml --mode warn
python scripts/validate-task.py examples/task-contract.example.yaml --mode strict --write-artifacts

Render report:

python skills/together/scripts/render-report.py

Run local release checks:

python scripts/release-check.py

Commands

  • python skills/together/scripts/discover-agents.py --format table
  • python skills/together/scripts/write-registry.py
  • python skills/together/scripts/doctor.py
  • python skills/together/scripts/render-report.py
  • python scripts/validate-json.py
  • python scripts/validate-registry.py
  • python scripts/validate-routing.py
  • python scripts/changed-files.py --json
  • python scripts/validate-task.py examples/task-contract.example.yaml --mode warn
  • python scripts/release-check.py

Thin wrappers:

  • bin/together-scan
  • bin/together-report
  • bin/together-doctor
  • bin/together-validate

How It Works

Together architecture overview

Known Providers
↓
Installed CLIs
↓
Ready Agents
↓
Departments
↓
Routing
↓
Verification
↓
Report
↓
Output

Stage meaning:

  • Known Providers: curated ecosystem Together understands
  • Installed CLIs: commands found on current machine
  • Ready Agents: installed workers passing lightweight checks
  • Departments: planning, research, vision, engineering, review, verification, fallback
  • Routing: readiness-first and capability-aware
  • Verification: scope, quality, and acceptance checks before merge
  • Report: operator-readable snapshot

Registry / Ready-State Model

Together registry and ready-state model

Three layers matter:

  • Known Providers is ecosystem coverage, not local installation
  • Installed CLIs is machine state
  • Ready Agents is machine state plus health readiness

Health checks stay cheap:

  • command exists
  • help/version runs
  • obvious auth/config failure detected
  • permission-denied state detected

Governance Model

Together work governance and control

Together assumes workers need boundaries.

Rules:

  • agent cannot do everything
  • agent works only inside assigned scope
  • review checks output quality
  • verification checks contract and scope
  • Codex decides merge and integration

Task contract fields:

  • task id
  • scope
  • allowed files
  • denied files
  • deliverables
  • success criteria
  • reviewer required
  • verification required

Permission model:

  • Observer
  • Researcher
  • Implementer
  • Reviewer
  • Integrator

Codex defaults to Integrator.

What the current CLI/TUI product enforces now:

  • task contract validation
  • git diff changed-file capture
  • scope guard
  • file policy validation
  • verification artifacts
  • quality gate
  • review and approval gate state
  • daemon-owned settings and status
  • proposal confirmation before mutation
  • PTY-backed worker execution path
  • degraded-agent fallback

What it does not do yet:

  • distributed scheduling
  • full enterprise RBAC or centralized audit
  • adaptive routing trained on long execution history
  • automatic agent sandboxing beyond local process/worktree boundaries
  • automatic commit or PR creation

Department Workflow

Together department pipeline

Request
↓
Planning
↓
Research
↓
Vision
↓
Engineering
↓
Review
↓
Verification
↓
Integration
↓
Output

Failover / Degraded Mode

Together failover and degraded mode

When a preferred worker fails:

  • mark degraded
  • start cooldown
  • route to healthy fallback worker
  • probe recovery later
  • return to preferred worker when healthy again

Examples

Committed, scrubbed examples:

  • examples/agent-registry.json
  • examples/agent-report.md
  • examples/last-known-good.json
  • examples/runtime-state.json
  • examples/providers.override.example.json
  • examples/task-contract.example.yaml
  • examples/tasks/*

These are examples, not live runtime outputs.

Repo Map

skills/      installable skill entrypoint and compatibility scripts
docs/        product and system docs
examples/    committed sample outputs and templates
tests/       lightweight validation tests
bin/         thin wrappers around current Python scripts
commands/    operational command guides
src/         reusable Python helpers for validation and reporting
.github/     CI workflow
assets/      brand and screenshot notes
agents/      worker-specific guidance

Generated Files Policy

Generated runtime output stays local and ignored:

  • .together/cache/*
  • .together/reports/*
  • .together/runtime-state.json

Committed templates:

  • .together/providers.override.example.json
  • examples/*

Documentation

Roadmap

Near-term:

  • dogfood the Monitor + Chat Dock UI in real developer sessions
  • improve benchmark and telemetry capture for task latency, fallback, verification, and retries
  • polish review, diff, settings, and compact terminal views
  • strengthen Codex skill/app bridge documentation
  • expand provider adapter tests and readiness diagnostics

Later:

  • team policy templates
  • CI and PR integration
  • richer execution history and adaptive routing
  • optional sandbox profiles
  • multi-machine worker pools

Limits

  • registry is curated, not exhaustive
  • capability hints are routing hints, not benchmark claims
  • failover is lightweight cooldown state, not a distributed scheduler
  • Together manages workers. It does not replace them.

License

MIT

About

🍠 Why use one giant context when small contexts do trick? -- Route tasks to the right worker instead of growing context forever -- Give each worker only what they need

Resources

License

Contributing

Stars

0 stars

Watchers

0 watching

Forks

Packages

 
 
 

Contributors

Languages