Updated September 2026

Roadmap

What we're building next, what's planned, and what already shipped. Everything here is tracked in the open on GitHub.

Current release

v0.12.1stable

In progress

1active now

Planned initiatives

3+ 4 future

Tracked issues

9open on GitHub

01 — Now & Next

Active work

In order. Everything else waits on these.

◐ In Progress

Advanced Workflow Control Flow

Make workflows expressive enough for real test/fix and approval-driven automation — multi-node loop bodies, branching on approvals, and a real expression evaluator.

Multi-node loop bodies (compose plan → implement → validate per iteration)
Conditional branching on approval and reject outcomes
Semantic completion signals — agents finish when done, not by token-matching
Real expression evaluator powering when:, loop_until:, and condition: clauses

workflowscontrol-flow

#1333

02 — Planned

Committed, not yet scheduled

Order reflects priority, not sequence.

Planned

Eval System

A built-in evaluation framework to measure and improve workflow quality — test cases, correctness scoring, and reliability testing.

WORKFLOW.eval.yaml — define test inputs and expected outputs inline
Step-level and output-level correctness scoring
Reliability testing across multiple runs
Eval score badges on published plugins and the planned archon.diy listing
archon workflow eval <name> — run evals from the CLI

qualitytestingevals

Planned

Local LLM Support

Connect Archon to local inference servers and OpenAI-compatible API proxies — bring your own model.

OpenAI-compatible baseURL configuration
Runtime workflow variables for dispatch-time model selection
Bundled workflows respect DEFAULT_AI_ASSISTANT instead of locking a provider

providerslocalmulti-model

#1449

Planned

Workflow Execution Reliability

Eliminate silent-success failure modes — workflows must never report completion while shipping nothing.

Audit and harden every workflow resumption and cache path
Defensive handling of provider error patterns (Codex turn.failed, Claude stop-sequence success)
Invariant checks before state restore — refuse to auto-resume failed runs into fresh requests

reliabilityworkflows

#1378

03 — Future

On the horizon

Exploring. Scope will change.

Additional Model Providers

Pluggable provider SDKs beyond Claude and Codex — Copilot, Hermes — plus per-dispatch model selection.

providers

Multi-Repo Workspace Support

Branch-aware sync and unambiguous webhook routing. One remote stays one project; parallel checkouts use worktrees.

isolation · git#1192 #1319 #1347 #1281

Enterprise GitHub Auth

GitHub App with per-installation tokens and secure secret resolution for org and team setups.

auth · enterprise#1385

Production-Ready Deployment

Reliable Docker, Pi and VPS support, Cloudflare Tunnel, hardened Windows execution.

deployment · docker#1452

04 — Shipped

Already in your hands

Full changelog

v0.11.0Shipped

Plugin Marketplace

Install workflow packs and forge plugins straight from GitHub. GitHub is the registry; an archon.diy listing of published plugins is planned.

One-command install: archon plugin add owner/repo[/path][@tag]

Installed packs pinned to one commit, with update, remove and copy

archon-plugin.json manifest in your own repository — no submission PR

Planned: an archon.diy listing of repositories that publish plugins

communitymarketplaceoss

v0.5.0Shipped

Persistent Project Orchestrator

One stateful conversation per codebase that retains context across runs, with project-first navigation and observable subagent activity.

Persistent orchestrator session bound to each project

Project memory carried across runs and restarts

Projects-first navigation in the Web UI

Live SDK lifecycle events (subagent + hook activity) streamed to the UI

orchestratorwebmemory

v0.3Shipped

Pi Agent Provider

Run Archon workflows with Pi — an open-source, multi-model coding agent. Breaks the Claude Code / Codex lock-in and opens Archon to GPT, Gemini, Qwen, DeepSeek, and more.

Pi coding agent as a first-class Archon provider

Supports any model Pi runs on — GPT-5, Claude, Gemini 2.x, Qwen Coder, DeepSeek V3

Optional access to Pi's ~540-package extension ecosystem

Skills, structured output, session resume, and tool restrictions all supported

providerspimulti-model

v0.3Shipped

Hooks, Commands & Quality Gates

Fine-grained workflow control with hooks, reusable commands, loop nodes, approval gates, and script nodes.

Pre/post hooks on any workflow node

Reusable commands library (share logic across workflows)

Loop nodes with configurable iterations

Approval nodes for human-in-the-loop checkpoints

Script nodes for custom automation logic

hookscommandsquality

v0.2.13Shipped

Streamlined Setup & Binary Install

Getting started with Archon should take under 5 minutes. A fully self-contained binary, one-line installers, and a first-run wizard that auto-detects your AI provider.

Fully self-contained binary distribution (no Node/Bun required)

One-line install: curl/irm scripts for macOS, Linux, Windows

Homebrew formula

Interactive first-run setup wizard

Auto-detection of Claude and Codex credentials

dxinstallonboarding

v0.2Shipped

Adapters & Deployment

Trigger Archon workflows from any surface — Slack, Telegram, GitHub, Web UI, Discord — and deploy anywhere.

Official adapters: Slack, Telegram, GitHub, Web

Community adapters: Discord, GitLab, Gitea

Docker & cloud deployment guides

Windows native support

adaptersdeploymentintegrations

v0.1Shipped

Core CLI & DAG Engine

The foundation — YAML-defined workflows, DAG execution with dependency resolution, and git worktree isolation per run.

YAML workflow definition language

DAG orchestration with full dependency resolution

Git worktree isolation — no conflicts between runs

Multi-provider support (Claude Code SDK, Codex)

coreclidag

Have a feature request?

Everything on this page started as an issue. Open one, or upvote what matters to you.

Browse issues Open an issue