
Forge Orchestrator coordinates Claude Code, Codex CLI, and Gemini CLI when they work on the same repository. It's for developers who use multiple AI coding assistants and need them to share decisions, respect file ownership, and follow the same specification.
Exclusive file locks prevent tools from editing a file simultaneously. Locks have timeouts and deadlock detection, so a crashed tool doesn't keep a file locked indefinitely. Shared knowledge captures decisions and coding patterns across sessions, with automatic categorization and search. Context recorded by Claude Code remains available to Codex CLI in a later session.
The orchestrator turns specifications into tasks with dependencies, assigns tools, and tracks progress. Drift detection compares work in progress with the specification and flags departures. A terminal dashboard shows live agent panes, task status, lock state, and health scores; headless execution supports autonomous work in CI/CD pipelines.
Written in Rust, it runs as a single binary without runtime dependencies. Coordination state stays in plain files under the repository's .forge/ directory, without a daemon or database. An MCP server exposes that state to connected AI clients. This local state storage doesn't establish that the connected coding assistants process requests offline.
The orchestrator is source-available under FSL-1.1-Apache-2.0, which converts to Apache 2.0 after two years. The separate Forge plugin uses the MIT license, while the optional Forge UI provides a browser dashboard.
Claim this page with an email at forge.nxtg.ai. Forge Orchestrator gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Forge Orchestrator?Promote it
Something wrong or outdated on this page?
587Updated 20 hours agoMIT
Web · VS Code · JetBrains#Agent Client Protocol#Code execution#Git integration
Claw Orchestrator is a self-hosted runtime for developers who want to coordinate coding agents on their own machine or server. It brings Claude Code, Codex, Antigravity, Grok Build and OpenCode into one interface, with support for custom coding CLIs. The runtime and browser dashboard run locally.
4.4KUpdated 24 hours agoMIT
macOS · Windows · Linux · Web · JetBrains#Agent Client Protocol#Code execution#Git integration
1.2KUpdated 4 weeks agoMIT
#Agent Skills#Code execution#Git integration
137Updated 14 hours ago
macOS · Windows · Linux · Docker · Web#Agent Skills#Human approval#Knowledge graphs
195Updated 7 months agoMIT
macOS · Windows · Linux · Web#Agent Skills#Code execution#Guardrails
42Updated 2 days ago
macOS · Windows · Linux · Docker#Agent Skills#Code execution#Distributed execution
gptme is a self-hosted AI agent that works directly in your terminal, with access to your files and installed tools. It's for developers who want a coding assistant in their own environment, and people who want an agent for data analysis or other knowledge work. The software is free under the MIT license and doesn't require a gptme account.
Pi Subagents adds specialized AI agents to pi for developers who want to split coding work across separate sessions. Each agent can have its own model, prompt and tool permissions. The extension runs within pi and is open source under the MIT license.
Project Orchestrator is a self-hosted coordination tool for developers working with multiple AI coding agents. It keeps code knowledge, development plans, and architectural decisions in a shared store so agents can reuse context across tasks and projects. It runs on macOS, Windows, and Linux, with desktop apps and Docker deployment available.
VibeHQ Hub coordinates separate Claude Code, Codex and Gemini CLI agents on your own computer. It's for developers assigning parts of a project to multiple coding assistants who need agreement on interfaces, dependencies and deliverables. The hub runs locally. It's open source under the MIT license, with tested Windows and macOS support; some Linux components remain untested.
Code Buddy is an AI coding assistant for developers who want a terminal agent running on their own machine, with a choice of local or cloud models. It reads repositories, edits code and runs commands on Linux, macOS and Windows. Ollama keeps model inference local without an API key or account; cloud providers send model requests off the machine. Routing includes automatic provider failover.