Wallfacer

Full autonomy when you trust it. Full control when you don't.

| !Task board | |:--:| | Task board: coordinate parallel agent execution |

| !Plan mode | |:--:| | Plan mode: design before you build |

Why Wallfacer

Every AI coding tool today pins you to one interaction mode. Chat-based tools are fast but lose structure at scale. Spec-driven tools add discipline but slow you down on day one. Task boards help you coordinate but don't understand your architecture. Wallfacer connects all of these into a continuous workflow.

Adaptive abstraction. Chat for greenfield exploration, specs for complex systems (a recursive tree of markdown specs that agents read, iterate on, break down, and dispatch as tasks), tasks for parallel execution, code for surgical edits. Move between levels as your project evolves.

Autonomy spectrum. Run the full loop autonomously (implement, test, commit, push) or step in at any point. Dial autonomy up or down per task, per spec, per project.

Spec as intermediate representation. Ideas don't go straight to code. They become structured specs that agents can reason about, iterate on, and implement against. Specs are versioned and reviewable.

Per-task git worktrees. Each task works in its own git worktree for safe parallel execution. Multiple agents work simultaneously without stepping on each other.

Operator visibility. Live logs, traces, timelines, diff review, and usage and cost tracking. A full audit trail from idea to merged code.

Self-development. Wallfacer builds Wallfacer. Most recent capabilities were developed by the system itself.

Harness flexibility. Works with Claude Code, Codex, Cursor, OpenCode, and Pi through a pluggable harness layer. Pick one per task or per agent role; not locked to any single provider.

Quick Start

Install:

curl -fsSL https://raw.githubusercontent.com/changkun/wallfacer/main/install.sh | sh

Check prerequisites:

wallfacer doctor

Start the server:

wallfacer run                    # execs your chosen harness CLI directly as a host process

A browser window opens automatically. Add your Claude credential (OAuth token via claude setup-token, or API key from console.anthropic.com) in Settings. See Getting Started for the full walkthrough.

Other commands: wallfacer status (print or watch board state), wallfacer spec (validate or scaffold specs), and wallfacer auth (cloud sign-in). Run wallfacer -help for flags.

How It Works

1. Explore. Describe what you want to build in chat. Wallfacer helps you shape the idea.
2. Specify. The idea becomes a structured spec. Iterate on it until the design is right.
3. Execute. Specs break into tasks on a board. Agents implement, test, and commit in isolated git worktrees.
4. Ship. Reviewed changes merge automatically. Auto-commit, auto-push, and auto-build when you're ready.

flowchart LR
    Idea([Idea]) --> Chat[Planning Chat]
    Chat --> Spec[Root Spec]
    Spec --> BreakDown[Break Down]
    BreakDown --> Leaves[Leaf Specs]
    Leaves --> Tasks[Dispatched Tasks]
    Tasks --> Commits([Commits])

The Autonomy Spectrum

Wallfacer lets you work at whichever abstraction level fits the problem, and move between them as the shape becomes clearer.

graph LR
    Chat[Chat<br/>exploratory] --> Spec[Spec<br/>structured design]
    Spec --> Task[Task<br/>scoped execution]
    Task --> Code[Code<br/>surgical edits]

Move left for more freedom and lower commitment; move right for more precision and higher commitment. Agents operate at every level, and autonomy dials up or down independently at each one. Specs move through a seven-state lifecycle (vague to drafted to validated to testing to complete, with stale and archived off to the side), and the planning chat exposes slash commands like /create, /validate, /break-down, and /dispatch to drive them.

Read more: Concepts, Plan, and Chat.

How execution is structured

Wallfacer runs every task through one built-in pipeline:

• Tasks run implementation turns in their own git worktree, then a test, then a commit message, title, and oversight summary. A task's instructions come from the repository's instruction files (AGENTS.md, CLAUDE.md) and its prompt.
• Agent roles carry the pipeline: impl, test, commit-msg, title, and oversight. Each runs on the task's harness (Claude, Codex, Cursor, OpenCode, or Pi), and a per-role setting can route one role to a different harness.
• Routines spawn ordinary tasks on a schedule. A scheduled routine running an ordinary prompt covers recurring idea generation.

Read more: Concepts and Configuration.

Product Tour

Task board: managed execution

The board (shown above) coordinates many agent tasks at once. Drag cards across the lifecycle, batch-create with dependency wiring, refine prompts before execution, and let autoimplement promote backlog items as capacity opens. Each task runs as a host process in its own git worktree.

Plan mode: structured design

Design before you build (shown above). The three-pane plan view gives you an explorer tree (left), a focused markdown view (center), and the planning chat (right). Break large ideas into structured specs, validate dependencies, and dispatch leaf specs to the board when the design is right.

Oversight: an actionable audit trail

!Oversight summary, event timeline, and diff

Inspect what happened, when, and why before you accept any automated output. Every task produces a structured event timeline, a diff against the default branch, and an AI-generated oversight summary.

Cost and usage visibility

!Usage and cost breakdown

Track token usage and cost by task, activity, and turn, so operations stay measurable as automation scales. The per-activity breakdown (implementation, testing, refinement, oversight) shows exactly where budget goes.

Capability Stack

• Chat. Planning chat with slash commands and file-explorer context, conversational drift away from or back into specs.
• Spec. Seven-state lifecycle, dependency DAG, recursive progress tracking, impact analysis, atomic dispatch and undo.
• Task. Host-process execution, per-task git worktrees, autoimplement, auto-test, auto-submit, auto-retry, circuit breakers, cost and token budgets, oversight summaries.
• Code. File explorer with editor, integrated terminal, live logs and diff review, per-turn usage and timeline, native per-repo AGENTS.md/CLAUDE.md discovery.

Roadmap

Development is organized into three parallel tracks with shared foundations. See specs/README.md for the full dependency graph and spec index.

Foundations (complete): Execution backend interface, storage backend interface, file explorer, host terminal, multi-workspace groups, Windows support.

Local Product: Developer workflow. Spec coordination (document model, planning UX, drift detection), routine tasks (scheduled spawns), file and image attachments, host mounts, oversight risk scoring, visual verification, live serve.

Cloud Platform: Two axes over the Latere platform. Axis A, the coordination plane (signed-in local instances connect over one outbound connection for presence, spec comments, and metadata projection; local stays the source of truth). Axis B, demand-gated remote execution: a task chosen to run remotely runs as a hosted agent session on the platform, and its repository travels by git.

Shared Design: Cross-track specs. Authentication, agent abstraction, native sandboxes (Linux, macOS, Windows), overlay snapshots.

Documentation

User Manual is the full reading order. Guides are grouped by what you are doing.

Get Started

| Guide | Topics | |-------|--------| | Getting Started | Installation, credentials, sign-in, first task | | Concepts | Mental model: workspaces, tasks, specs, agents, autonomy |

Use Wallfacer

| Guide | Topics | |-------|--------| | Board | Task board, lifecycle, dependencies, search, task detail | | Chat | Chat sessions, slash commands, @mentions | | Plan | Spec mode, lifecycle states, dispatch, planning chat | | Routines | Scheduled cards that spawn tasks on an interval | | Whiteboard | Free-form drawing canvas per workspace | | Artifacts | Serve and open self-contained HTML pages from the workspace |

Operate

| Guide | Topics | |-------|--------| | Automation | Autoimplement, auto-test, auto-submit, auto-retry, circuit breakers | | Oversight | Oversight summaries, timelines, logs, diff review, analytics | | Mission Control | Unified spec and task graph, acting on the pipeline | | Workspaces | Workspace management, git integration, branches | | Configuration | Settings, env vars, harnesses, CLI, shortcuts |

Build On (Internals) is the deep reference for how the system works. Start at Technical Internals.

| Reference | Topics | |-----------|--------| | Architecture | System design, package map, handler organization, end-to-end walkthrough | | Data & Storage | Data models, persistence, event sourcing, spec document model | | Task Lifecycle | State machine, turn loop, dependencies, failure categorization | | Git Operations | Worktree lifecycle, commit pipeline, branch management | | API & Transport | HTTP route reference, SSE, WebSocket terminal, middleware | | Auth & Identity | OIDC, device sign-in, principal context, cloud mode | | Service Identity | Wallfacer's slice of the latere.ai family identity shape: the sandbox-proxy inbound audience, per-route scopes, fail-closed validator | | Automation | Background watchers, autoimplement, review, circuit breakers, routines | | Agent Graph Runtime | Embedded topos runtime, the native in-process harness, live traces | | Plan Mode | Spec tree, agent sessions, slash commands, dispatch, undo | | Workspaces & Config | Workspace manager, harness routing, templates, env config | | Development Setup | Building, testing, make targets, release workflow |

Contributing? See CONTRIBUTING.md for the developer orientation, build commands, and conventions.

Origin

Wallfacer started as a task board for coordinating concurrent agent runs and grew from there: spec coordination, oversight, refinement, an integrated IDE. Most recent capabilities were developed by Wallfacer itself. See docs/origin.md for the long version.

Status

Wallfacer is pre-1.0 and released from main as tagged versions. The HTTP API (documented in API & Transport), the on-disk layout under ~/.wallfacer/, and the WALLFACER_* environment variables can still change between releases. Per-release changes are recorded in docs/releases/. The command surface is wallfacer run, status, spec, auth, web, and doctor. Every Go package lives under internal/, so this repository exposes no importable public Go API.

License

MIT