Coordinates OpenAI Codex CLI sessions on shared repositories, providing task planning, file locking, and shared state across AI coding tools.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@forge-orchestrator Plan the tasks from the spec and orchestrate Claude, Codex, and Gemini on them."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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, with Codex CLI as a task runner, on shared repos — single Rust binary, zero deps. Gemini CLI support is in development (build B1, target 2026-10-27).
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 as a task runner. Gemini CLI support is in development (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.
curl -fsSL https://forge.nxtg.ai/install.sh | sh
export PATH="$HOME/.local/bin:$PATH" # this shell only; new shells already have it
forge initThe installer 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: all-agents-mcp
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 statusFrom here you can:
forge run — execute tasks headlessly (autonomous mode, great for CI)
forge dashboard --pty — launch the TUI dashboard with interactive agent panes
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 Gemini CLI; since v1.6.1 the "gemini" adapter drives Antigravity agy instead, and the run has not been re-measured. Gemini CLI support is in development (build B1, target 2026-10-27).
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 conflictsThree companies. Three tools. One orchestrator. One command:
forge dashboard --ptyFeature | What It Does |
File locking | Exclusive locks prevent tools from editing the same file simultaneously |
Knowledge flywheel | Captures decisions, patterns, learnings across tools. Auto-classified and searchable. |
Plan generation |
|
Drift detection | Compares in-progress work against specs, flags divergence early |
Task board | Dependency-tracked tasks, tool assignment, progress monitoring |
Multi-tool adapters | Claude Code (MCP stdio); Codex CLI as a task runner (filesystem). Gemini CLI support is in development (build B1, target 2026-10-27) |
TUI dashboard |
|
Headless mode |
|
MCP server | 12 tools accessible by any connected AI tool via stdio, including |
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, tagThe 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 runs tasks through filesystem conventions. Gemini CLI support is in development (build B1, target 2026-10-27); today the "gemini" adapter drives Antigravity agy. Each tool reads its own config format. No Forge-specific configuration language.
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.
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.
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 devForge Plugin (L1: Vibe Coder)
Forge UI (L3: Ship Lord)
MCP Registry: mcp-name: io.github.nxtg-ai/forge-orchestrator
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.
This server cannot be deployed
Shared control plane for AI coding agents — tasks, memory, decisions, file locks. 12 tools.
Project management shared by people and AI agents, with persistent project state through MCP.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
AI-native git hosting — repos, PRs, issues, CI gates, and AI code review over MCP (60 tools).
