Complete Your Development Stack
Stoneforge users also rely on these tools to enhance their workflow:
1Password
Try FreeSecrets and credential manager
Keep API keys and .env secrets out of your repo
Gamma
Try FreeAI presentation builder
Turn ideas into polished decks instantly
Consensus
Try FreeAI search across 200M research papers
Source real evidence behind your analysis
💰 Affiliate disclosure: We may earn a commission if you sign up through these links at no extra cost to you.
Stoneforge
Open-source orchestration for running teams of AI coding agents in parallel git worktrees
0Visit Stoneforge
https://stoneforge.ai
About Stoneforge
Stoneforge is an open-source orchestration layer for running several AI coding agents at once on the same repository. The failure mode it targets is specific: once you have more than one Claude Code, Codex, or OpenCode session working on a project, they edit the same files on the same branch, two of them grab the same task, and you cannot see what any of them is doing without tabbing through terminals. Stoneforge fixes each of those in turn. Every worker agent runs inside its own isolated git worktree, so agents never collide on the filesystem, and a merge steward handles integration back to main — reviewing CI status and resolving conflicts as a separate role rather than leaving it to whichever agent finished first. A dispatch daemon tracks task priorities and dependencies and auto-assigns ready work to idle workers, so nothing gets double-claimed and nothing starts while it is still blocked. Over the top sits a real-time web dashboard at localhost:3457 that shows active agents, tasks in progress, merge requests awaiting review, and recent completions in one view, with a command palette for driving the whole thing. Roles are explicit — Director agents execute plans, Workers implement, Stewards review and merge — and recent versions added GitHub, Linear, and Notion sync so the task board can mirror the tracker a team already uses.
Key Features
Stoneforge Pros & Cons
✅ Pros
- +Worktree isolation is the correct structural fix for parallel agents, not a coordination convention agents can ignore
- +Free and self-hosted — no per-seat cost on top of what you already pay for model access
- +Dependency-aware dispatch prevents the duplicated-work problem that makes naive multi-agent setups slower than one agent
- +Dashboard gives a single place to approve merges instead of watching several terminals
- +Agent-agnostic — works across Claude Code, Codex, and OpenCode rather than locking you to one vendor
⚠️ Cons
- −Self-hosting means you operate the daemon and dashboard yourself; there is no managed option
- −Only useful once you are genuinely running multiple agents — overkill for a single-agent workflow
- −Multi-agent orchestration multiplies model spend, and Stoneforge does not reduce that
- −No published pricing or support tier, so no commercial backstop if you depend on it
Who Is Stoneforge Best For?
Tags
Is this your tool?
Claim your listing to get a Featured badge, edit your description, and stand out from competitors. All plans include a permanent dofollow backlink to your site.
Claim Now →ChatGPT already recommends Stoneforge. Does it recommend yours?
If you're building in Coding & Development, run a free AI-visibility scan on your own product — we ask ChatGPT across 5 prompt angles and score how often you get named. ~30 seconds, no signup, no card.
Stay updated on Coding & Development tools — join our weekly newsletter
One concise email with fresh launches, trending picks, and featured standouts.
Alternatives to Stoneforge
View all Stoneforge alternatives →Agent connectivity: not yet verified