Self-hosted workflows for coding-agent delivery. Orchestrate CodeBuddy, Codex and Claude Code with scripts and human approval gates. Includes Local workflows for coding assistants.
★ 2,045⑂ 323👁 9⑃ 210● 66▤ 13
+986
Daily
2,045
stars
323
forks
9
watchers
210
prs
66
issues
13
releases
README
English · 简体中文
Two ways to work ·
Quick start ·
SOPs ·
Features ·
Local ·
FAQ ·
Docs
https://github.com/user-attachments/assets/8af401d9-1aae-427c-b4bc-455c12d17beb
80-second product tour (1080p, with sound).
LoopForge is a self-hosted workspace where your team ships software with coding agents. Describe what you need to Main Bot in chat: it opens a Docker sandbox, checks out your repositories, delegates to project roles, and opens the PR. When a way of working proves itself, save it as an SOP (a standard workflow of agents, scripts and human gates) so the next requirement is delivered the same way, with review and approval built in.
Coding-agent CLIs do the work: CodeBuddy, Codex, Claude Code, OpenCode, Cursor CLI, Antigravity, Kimi Code, Pi, DeepSeek Harness and ZCode. LoopForge adds the roles, sandboxes, checkpoints and history around them, all on your own infrastructure under the MIT license.
Two ways to work
| | Chat with Main Bot | Run an SOP |
| --- | --- | --- |
| Best for | Exploring, quick fixes, iterating with the agent | Repeatable delivery with fixed stages and sign-off |
| How it runs | Main Bot opens a conversation workspace (a Docker sandbox with your repos) on demand and calls project roles as subagents | The engine runs Agent, Script, Human-gate and sub-SOP nodes in order, in their own sandbox |
| You stay in control by | Queuing or steering messages mid-reply, and pausing, resuming or taking over a running SOP from chat | Approving at human gates, sending work back to a chosen step, retrying or rerunning from any node |
| Delivers | A PR/MR, or a direct merge into a shared branch (mode=direct) | Documents, code or a PR, plus per-node artifacts and logs |
Both paths track the same requirements, so every change, whether made in chat or by an SOP, links back to what was asked for and counts toward delivery and cost reports.
The chat home. Type a request, @ a role, skill, requirement, SOP or repository, and pick the executor, model and permission mode per conversation.
Why LoopForge
Ask a coding agent to "fix this bug" and the result depends on that run. It might skip the plan, forget the tests, review its own code, or stop halfway without anyone noticing. That's fine for a demo, but it isn't how a team ships.
- Repeatable. Same SOP, same stages, same checks for every requirement. Start from built-in backend, frontend, bug-fix and product SOPs.
- Separated roles. Planning, implementation, review and testing each get their own prompt, executor, model, rules, Skills and MCP tools. A role works as an SOP node or as a subagent in chat.
- Human in the loop. Approval gates where they matter. Read the report, approve, or send the work back to a chosen step.
- Observable and resumable. Node status, tool traces, logs and artifacts in one place. Pause, retry a failed step, or rerun from any node.
- Your stack, your servers. Ten coding-agent CLIs as executors, from CodeBuddy, Codex and Claude Top issues
#450[Bug]: 默认的SOP不进入下一个环节2 comments · 2026-11-13#201[Feature]: 安装和升级时补齐必须的 SQL,避免缺列直接报给用户4 comments · 2026-11-12#125[Feature]: 支持 ZCode 与 Reasonix 作为执行器与本地宿主4 comments · 2026-11-09#660对话中 CLI 连续异常退出(CLI_EXIT_NONZERO),后续消息不到 1 秒即失败,且进度文字重复输出3 comments · 2026-11-13#434[Bug] DeepSeek 聊天长历史在启动 CLI 前触发 E2BIG(argument list too long)3 comments · 2026-11-13#180[Bug]: codex api 没法读取最新模型3 comments · 2026-11-11#128[Feature]: 支持 GitLab,以及通过 Git SSH 接入 Gogs 等其它仓库3 comments · 2026-11-09#884[Feature]: 支持飞书通知渠道和阿里云云校代码仓库2 comments · 2026-11-15
Discussions
Latest release
LoopForge v0.3.8 v0.3.8 2026-11-12Install
bash
git clone --branch v0.3.8 https://github.com/Tencent/LoopForge.git
cd LoopForge
./start.sh
Platform image: ghcr.io/tencent/loopforge:0.3.8 (pinned in compose.yaml).
Digest: ghcr.io/tencent/loopforge@sha256:481ecb6334a21308acb93f164f5dc74f508109d3e108089981a7ea87de095963.
Where ghcr.io is slow, set MIRROR to a registry host that replaces it (for example MIRROR=ghcr.nju.edu.cn ./start.sh). This trusts that host: the download is tagged as the pinned name. Check it with docker image inspect --format '{{index .RepoDigests 0}}' ghcr.io/tencent/loopforge:0.3.8 and compare the digest