forge-orchestrator

Stage: Alpha. The Forge plugin and orchestrator are in alpha. On 2026-10-15 (UTC) a separate NXTG.AI team (product-oracle) ran the pre-registered core-job test on a clean install of the plugin (v3.14.0) and the orchestrator (forge 1.7.0). The test passed; each repeated check passed 3 of 3 (run 7). The evidence is attached to the forge-plugin v3.14.0 release. No SLA; interfaces may change without notice.

Orchestration for Claude Code on shared repos, with Codex CLI and Antigravity CLI (agy) as task runners — single Rust binary, zero deps.

Multi-agent inside a single tool works fine. Claude Code runs 20 subagents and they stay aligned because the tool manages that orchestration internally. The problem is multi-tool: several AI coding tools on the same repo with no shared state. That's what the orchestrator solves: today for Claude Code, with Codex CLI and Antigravity CLI (agy) as task runners. The orchestrator launches agy as a task runner; what else Forge does on agy is being measured (build B1, target 2026-10-27).

It adds file locking, knowledge capture, task planning, drift detection, and multi-tool orchestration to your development workflow. The tools read from and write to a single state directory. A 12-tool MCP server exposes the full orchestration state to any connected AI client, and can create, claim and complete tasks.

The orchestrator exists because I ran two AI tools on the same codebase and watched them fail in the same ways human teams fail. Claude refactored a module. Codex updated tests against the pre-refactor interface. Both saved. Tests failed. Neither tool knew the other existed. I'd spent 23 years watching this exact scenario with talented human teams. The solution was always the same: orchestration infrastructure.

Install

curl -fsSL https://forge.nxtg.ai/install.sh | sh
export PATH="$HOME/.local/bin:$PATH"   # this shell only; new shells already have it
forge init

The installer installs Forge v1.7.1, the pinned release, not whichever release is newest. It puts forge in ~/.local/bin (change it with FORGE_INSTALL_DIR) and adds that directory to your PATH with one guarded line in ~/.profile, ~/.bashrc and, if you have zsh, ~/.zshenv. Set FORGE_NO_MODIFY_PATH=1 to leave your shell files alone.

If the claude CLI is on your PATH, the installer then adds forge's MCP tools to Claude Code, using only that CLI: it adds and refreshes the nxtg-forge marketplace (nxtg-ai/forge-plugin), updates nxtg-forge@nxtg-forge if you already have it, and installs the companion plugin nxtg-forge-orchestrator@nxtg-forge. It prints one line per change and changes no Claude configuration any other way. Without claude, or if a step fails, it prints the commands for you to run and still exits 0. Set FORGE_NO_CLAUDE_PLUGIN=1 to skip it.

Single binary. No runtime dependencies.

Related MCP server: session-coord-mcp

Connect Codex CLI to the MCP server

Register the orchestrator's MCP server with Codex CLI, then check that Codex lists it:

codex mcp add forge -- forge mcp
codex mcp list

This writes the entry to ~/.codex/config.toml:

[mcp_servers.forge]
command = "forge"
args = ["mcp"]

The server works on the project in the directory it starts in. To pin one project, bind it when you register: codex mcp add forge --env FORGE_PROJECT_ROOT=/path/to/project -- forge mcp. Checked with codex-cli 0.162.1: codex mcp list shows forge enabled over stdio, and the server answers tools/list with its 12 tools. A tool call made from inside a Codex session has not been measured yet (build B1).

Quick Demo

Four commands from zero to task board:

# 1. Initialize — creates .forge/ directory with state, event log, knowledge base
forge init

# 2. Configure the AI brain — choose 'openai' (needs API key) or 'rule-based' (free)
forge config brain openai

# 3. Generate tasks — reads your SPEC.md or README, creates dependency-aware task graph
forge plan --generate

# 4. See the result — task board with assignments, dependencies, and project health
forge status

From here you can:

• forge run — execute tasks headlessly (autonomous mode, great for CI)

• forge dashboard --pty — launch the TUI dashboard with interactive agent panes

Past Result: Stargate Mode (before v1.6.1)

From a 94-line specification, an earlier version of the orchestrator coordinated three AI coding tools to build a complete CLI toolkit. That run drove the retired Gemini CLI; since v1.6.1 the adapter launches Antigravity CLI (agy) instead, and the run has not been re-measured.

SPEC.md (94 lines) → forge plan --generate → 15 tasks

Claude Code:  6 design tasks     → completed
Codex CLI:    6 implementation   → completed
Gemini CLI:   3 test/doc tasks   → completed   (pre-1.6.1 adapter)

Result: 5,306 lines of working code
        10 auto-committed git entries
        13 Python files (CLI + tests)
        Zero file conflicts

Three companies. Three tools. One orchestrator. One command:

forge dashboard --pty

What You Get

Key Commands

forge init                     # Initialize Forge in a project
forge plan --generate          # Generate task plan from spec
forge dashboard                # Live TUI dashboard
forge dashboard --pty          # TUI with interactive agent panes (Stargate)
forge run                      # Headless autonomous mode
forge status                   # Current state summary
forge verify                   # Run automated acceptance tests
forge uat                      # Interactive UAT test runner
forge ship                     # Release ceremony: changelog, archive, tag

Architecture

The orchestrator is the policy core of Forge. All governance rules, file locks, and orchestration logic live here. The plugin (L1: Vibe Coder) and UI (L3: Ship Lord) are adapter surfaces. They present the orchestrator's state through different interfaces but don't make policy decisions.

┌──────────────────────────────────────┐
│        forge-orchestrator            │
│        (Rust)                        │
│                                      │
│  File locking · Task planning        │
│  Knowledge · Governance · MCP        │
│  Multi-tool adapters                 │
│                                      │
│  Policy enforced here.               │
│  Nowhere else.                       │
└───────────┬──────────────────┬───────┘
            │                  │
   ┌────────┴────────┐  ┌────┴────────┐
   │  forge-plugin   │  │  forge-ui   │
   │  (L1 Safety)    │  │  (L3 MC)    │
   │  Claude Code    │  │  React      │
   │  adapter        │  │  dashboard  │
   └─────────────────┘  └─────────────┘

Communication: .forge/ filesystem + MCP stdio. No daemon. No database. State is files.

Tool adapters: Claude Code uses MCP stdio. Codex CLI and Antigravity CLI (agy) run tasks through filesystem conventions. The agy adapter keeps the agent id gemini in task files, config keys and MCP arguments, so existing projects keep working. Each tool reads its own config format. No Forge-specific configuration language.

How File Locking Works

File locking exists because I've watched teams lose days to conflicting edits.

When Claude Code starts editing a file, the orchestrator acquires an exclusive lock in .forge/locks/. Codex CLI requesting the same file is queued with a notification of who holds the lock. Locks include timeouts (crashed tools don't hold locks forever) and deadlock detection.

The test suite covers concurrent access, timeout behavior, multi-adapter locking, and edge cases.

How the Knowledge Flywheel Works

The knowledge flywheel exists because I've watched decisions evaporate between sprints.

Every decision, pattern, and learning from tool sessions is captured in .forge/knowledge/. Entries are auto-classified by category. Search across sessions and across tools. Knowledge captured during a Claude Code session is available to Codex CLI the next day.

After a week, the system knows your conventions better than you remember them. New sessions start with context instead of from scratch.

Upgrade Path

The TUI dashboard shows everything. Forge UI shows it better.

Visual dashboards. Governance HUD. Real-time agent collaboration network. And the Infinity Terminal: sessions that survive browser close, network drops, and server restarts. If you've lost a 3-hour agent session to a disconnected SSH pipe, you know why this matters.

git clone https://github.com/nxtg-ai/forge-ui && cd forge-ui && npm install && npm run dev

Links

• Forge Product Page

• Forge Plugin (L1: Vibe Coder)

• Forge UI (L3: Ship Lord)

• Documentation

• MCP Registry: mcp-name: io.github.nxtg-ai/forge-orchestrator

License

Source available under the Functional Source License 1.1 (FSL-1.1-ALv2). Converts to Apache License 2.0 on 2028-03-18. See LICENSE.md for full terms.