Tencent/LoopForgePublic

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.

AI summary: Self-hosted orchestration engine that chains multiple coding-agent CLIs into repeatable, human-approved SOPs

Stars
3.7K
+651 today
Forks
515
Watchers
14
Open issues
35
Open PRs
37
Contributors
~17
Commits
324
Branches
114
Views (30d)
2

GoOtherCreated Jul 28, 2026Last push 2d agoLatest release v0.3.8+2.3K stars this week+2.3K this month

Quick answers

What is LoopForge?
Self-hosted orchestration engine that chains multiple coding-agent CLIs into repeatable, human-approved SOPs
What does LoopForge do?
LoopForge addresses the lack of repeatable, auditable delivery when using LLM-powered coding agents. It runs a self-hosted Docker-based platform that creates isolated sandboxes, checks out repositories, and invokes any of ten supported agent CLIs (CodeBuddy, Codex, Claude Code, etc.) as sub-agents. Users can interact via a chat “Main Bot” that dynamically builds a workflow, or trigger a predefined SOP that sequences Agent, Script, and Human-gate nodes. Each node runs in its own container, logs artifacts, and can be paused, retried, or resumed, providing full observability and human-in-the-loop approvals before PR creation. The engine stores requirements, execution history, and cost metrics, enabling teams to standardize delivery across projects while keeping all data on their own infrastructure.
Who is LoopForge for?
Engineers and DevOps teams that want to integrate LLM coding agents into their delivery process while retaining full control over data and infrastructure. Requires Docker, Docker Compose, and basic Git knowledge; optional model API keys for real agent execution.
How do I get started with LoopForge?
git clone https://github.com/Tencent/LoopForge.git
How popular is LoopForge on GitHub?
Tencent/LoopForge has 3,736 stars and 515 forks on GitHub, and gained 2,300 stars in the last 7 days.
What license does LoopForge use?
Tencent/LoopForge is released under the Other license.

Star history

since Nov 15, 2026
01K2K3KNov 2026Nov 2026Nov 2026Nov 2026
3.7K stars as of Nov 18, 2026. Measured daily since Nov 15, 2026; GitHub no longer exposes earlier star timestamps.

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 0 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 0 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 0 commits2026-01-06: 0 commits2026-01-07: 0 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 0 commits2026-01-16: 0 commits2026-01-17: 0 commits2026-01-18: 0 commits2026-01-19: 0 commits2026-01-20: 0 commits2026-01-21: 0 commits2026-01-22: 0 commits2026-01-23: 0 commits2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 0 commits2026-01-27: 0 commits2026-01-28: 0 commits2026-01-29: 0 commits2026-01-30: 0 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 0 commits2026-02-03: 0 commits2026-02-04: 0 commits2026-02-05: 0 commits2026-02-06: 0 commits2026-02-07: 0 commits2026-02-08: 0 commits2026-02-09: 0 commits2026-02-10: 0 commits2026-02-11: 0 commits2026-02-12: 0 commits2026-02-13: 0 commits2026-02-14: 0 commits2026-02-15: 0 commits2026-02-16: 0 commits2026-02-17: 0 commits2026-02-18: 0 commits2026-02-19: 0 commits2026-02-20: 0 commits2026-02-21: 0 commits2026-02-22: 0 commits2026-02-23: 0 commits2026-02-24: 0 commits2026-02-25: 0 commits2026-02-26: 0 commits2026-02-27: 0 commits2026-02-28: 0 commits2026-03-01: 0 commits2026-03-02: 0 commits2026-03-03: 0 commits2026-03-04: 0 commits2026-03-05: 0 commits2026-03-06: 0 commits2026-03-07: 0 commits2026-03-08: 0 commits2026-03-09: 0 commits2026-03-10: 0 commits2026-03-11: 0 commits2026-03-12: 0 commits2026-03-13: 0 commits2026-03-14: 0 commits2026-03-15: 0 commits2026-03-16: 0 commits2026-03-17: 0 commits2026-03-18: 0 commits2026-03-19: 0 commits2026-03-20: 0 commits2026-03-21: 0 commits2026-03-22: 0 commits2026-03-23: 0 commits2026-03-24: 0 commits2026-03-25: 0 commits2026-03-26: 0 commits2026-03-27: 0 commits2026-03-28: 0 commits2026-03-29: 0 commits2026-03-30: 0 commits2026-03-31: 0 commits2026-04-01: 0 commits2026-04-02: 0 commits2026-04-03: 0 commits2026-04-04: 0 commits2026-04-05: 0 commits2026-04-06: 0 commits2026-04-07: 0 commits2026-04-08: 0 commits2026-04-09: 0 commits2026-04-10: 0 commits2026-04-11: 0 commits2026-04-12: 0 commits2026-04-13: 0 commits2026-04-14: 0 commits2026-04-15: 0 commits2026-04-16: 0 commits2026-04-17: 0 commits2026-04-18: 0 commits2026-04-19: 0 commits2026-04-20: 0 commits2026-04-21: 0 commits2026-04-22: 0 commits2026-04-23: 0 commits2026-04-24: 0 commits2026-04-25: 0 commits2026-04-26: 0 commits2026-04-27: 0 commits2026-04-28: 0 commits2026-04-29: 0 commits2026-04-30: 0 commits2026-05-01: 0 commits2026-05-02: 0 commits2026-05-03: 0 commits2026-05-04: 0 commits2026-05-05: 0 commits2026-05-06: 0 commits2026-05-07: 0 commits2026-05-08: 0 commits2026-05-09: 0 commits2026-05-10: 0 commits2026-05-11: 0 commits2026-05-12: 0 commits2026-05-13: 0 commits2026-05-14: 0 commits2026-05-15: 0 commits2026-05-16: 0 commits2026-05-17: 0 commits2026-05-18: 0 commits2026-05-19: 0 commits2026-05-20: 0 commits2026-05-21: 0 commits2026-05-22: 0 commits2026-05-23: 0 commits2026-05-24: 0 commits2026-05-25: 0 commits2026-05-26: 0 commits2026-05-27: 0 commits2026-05-28: 0 commits2026-05-29: 0 commits2026-05-30: 0 commits2026-05-31: 0 commits2026-06-01: 0 commits2026-06-02: 0 commits2026-06-03: 0 commits2026-06-04: 0 commits2026-06-05: 0 commits2026-06-06: 0 commits2026-06-07: 0 commits2026-06-08: 0 commits2026-06-09: 0 commits2026-06-10: 0 commits2026-06-11: 0 commits2026-06-12: 0 commits2026-06-13: 0 commits2026-06-14: 0 commits2026-06-15: 0 commits2026-06-16: 0 commits2026-06-17: 0 commits2026-06-18: 0 commits2026-06-19: 0 commits2026-06-20: 0 commits2026-06-21: 0 commits2026-06-22: 0 commits2026-06-23: 0 commits2026-06-24: 0 commits2026-06-25: 0 commits2026-06-26: 0 commits2026-06-27: 0 commits2026-06-28: 0 commits2026-06-29: 0 commits2026-06-30: 0 commits2026-07-01: 0 commits2026-07-02: 0 commits2026-07-03: 0 commits2026-07-04: 0 commits2026-07-05: 0 commits2026-07-06: 0 commits2026-07-07: 0 commits2026-07-08: 0 commits2026-07-09: 0 commits2026-07-10: 0 commits2026-07-11: 0 commits2026-07-12: 0 commits2026-07-13: 0 commits2026-07-14: 0 commits2026-07-15: 0 commits2026-07-16: 0 commits2026-07-17: 0 commits2026-07-18: 0 commits2026-07-19: 0 commits2026-07-20: 0 commits2026-07-21: 0 commits2026-07-22: 0 commits2026-07-23: 0 commits2026-07-24: 0 commits2026-07-25: 0 commits2026-07-26: 0 commits2026-07-27: 0 commits2026-07-28: 1 commit2026-07-29: 0 commits2026-07-30: 0 commits2026-07-31: 0 commits2026-08-01: 0 commits2026-08-02: 0 commits2026-08-03: 0 commits2026-08-04: 5 commits2026-08-05: 0 commits2026-08-06: 0 commits2026-08-07: 0 commits2026-08-08: 0 commits2026-08-09: 0 commits2026-08-10: 0 commits2026-08-11: 0 commits2026-08-12: 0 commits2026-08-13: 0 commits2026-08-14: 0 commits2026-08-15: 0 commits2026-08-16: 0 commits2026-08-17: 0 commits2026-08-18: 0 commits2026-08-19: 0 commits2026-08-20: 0 commits2026-08-21: 0 commits2026-08-22: 0 commits2026-08-23: 0 commits2026-08-24: 0 commits2026-08-25: 0 commits2026-08-26: 0 commits2026-08-27: 0 commits2026-08-28: 0 commits2026-08-29: 0 commits2026-08-30: 0 commits2026-08-31: 0 commits2026-09-01: 0 commits2026-09-02: 0 commits2026-09-03: 0 commits2026-09-04: 0 commits2026-09-05: 0 commits2026-09-06: 0 commits2026-09-07: 0 commits2026-09-08: 0 commits2026-09-09: 0 commits2026-09-10: 1 commit2026-09-11: 0 commits2026-09-12: 0 commits2026-09-13: 0 commits2026-09-14: 0 commits2026-09-15: 1 commit2026-09-16: 5 commits2026-09-17: 8 commits2026-09-18: 0 commits2026-09-19: 0 commits2026-09-20: 0 commits2026-09-21: 0 commits2026-09-22: 0 commits2026-09-23: 0 commits2026-09-24: 0 commits2026-09-25: 0 commits2026-09-26: 0 commits2026-09-27: 0 commits2026-09-28: 0 commits2026-09-29: 0 commits2026-09-30: 0 commits2026-10-01: 0 commits2026-10-02: 0 commits2026-10-03: 0 commits2026-10-04: 0 commits2026-10-05: 0 commits2026-10-06: 0 commits2026-10-07: 0 commits2026-10-08: 0 commits2026-10-09: 0 commits2026-10-10: 0 commits2026-10-11: 3 commits2026-10-12: 1 commit2026-10-13: 1 commit2026-10-14: 0 commits2026-10-15: 0 commits2026-10-16: 0 commits2026-10-17: 0 commits2026-10-18: 0 commits2026-10-19: 1 commit2026-10-20: 2 commits2026-10-21: 0 commits2026-10-22: 0 commits2026-10-23: 0 commits2026-10-24: 0 commits2026-10-25: 0 commits2026-10-26: 0 commits2026-10-27: 0 commits2026-10-28: 0 commits2026-10-29: 0 commits2026-10-30: 0 commits2026-10-31: 0 commits2026-11-01: 0 commits2026-11-02: 0 commits2026-11-03: 2 commits2026-11-04: 0 commits2026-11-05: 1 commit2026-11-06: 10 commits2026-11-07: 19 commits2026-11-08: 0 commits2026-11-09: 4 commits2026-11-10: 11 commits2026-11-11: 14 commits2026-11-12: 22 commits2026-11-13: 130 commits2026-11-14: 80 commits2026-11-15: 2 commits2026-11-16: 0 commits2026-11-17: 0 commits2026-11-18: 0 commits2026-11-19: 0 commits2026-11-20: 0 commits2026-11-21: 0 commits
324 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Breakout launch

    3,736 stars in 116 days

  • Rising fast

    +2,300 stars this week

  • Well documented

    High community health score

  • Continuous integration

    Automated checks passing

  • Repeat trending

    4 trending appearances

What LoopForge does

LoopForge addresses the lack of repeatable, auditable delivery when using LLM-powered coding agents. It runs a self-hosted Docker-based platform that creates isolated sandboxes, checks out repositories, and invokes any of ten supported agent CLIs (CodeBuddy, Codex, Claude Code, etc.) as sub-agents. Users can interact via a chat “Main Bot” that dynamically builds a workflow, or trigger a predefined SOP that sequences Agent, Script, and Human-gate nodes. Each node runs in its own container, logs artifacts, and can be paused, retried, or resumed, providing full observability and human-in-the-loop approvals before PR creation. The engine stores requirements, execution history, and cost metrics, enabling teams to standardize delivery across projects while keeping all data on their own infrastructure.

Engineers and DevOps teams that want to integrate LLM coding agents into their delivery process while retaining full control over data and infrastructure. Requires Docker, Docker Compose, and basic Git knowledge; optional model API keys for real agent execution.

  • Chat-driven orchestration: Main Bot converts natural-language requests into Docker sandboxes, invokes agents, and opens PRs.
  • SOP engine: Define repeatable Standard Operating Procedures that chain Agent, Script, and Human-gate nodes with versioned checkpoints.
  • Multi-agent support: Integrates ten coding-agent CLIs (CodeBuddy, Codex, Claude Code, OpenCode, Cursor, etc.) selectable per role.
  • Human-in-the-loop gates: Approval steps pause execution, expose logs and artifacts, and allow rerouting or retrying specific nodes.
  • Observability dashboard: Central UI shows node status, tool traces, logs, and per-node artifacts for debugging and audit.
  • Self-hosted Docker deployment: Single-command installer provisions MySQL, platform services, and pre-loaded sandboxes via Docker Compose.
  • Extensible executor model: Executors can run in the platform container or on external machines, with per-user credentials and MCP tools.

Where teams use it

Small dev teams

Teams that want AI-assisted coding but need repeatable, auditable workflows can define SOPs and keep all execution on‑premise.

Enterprises with compliance requirements

Organizations can self‑host the entire stack, control model keys, and enforce human approvals before code merges.

CI/CD pipeline augmentation

Add LLM agents as pipeline steps, with built‑in human gates and artifact logging, without exposing external services.

Individual developers experimenting safely

Solo developers can run the demo project, test AI agents in isolated sandboxes, and avoid leaking API keys to third‑party services.

Getting started: git clone https://github.com/Tencent/LoopForge.git

README

main branch

LoopForge — From idea to merged code. Chat with coding agents in sandboxed workspaces, run repeatable SOPs, and approve what ships.

CI npm loopforge-cli MIT License Self-hosted with Docker GitHub stars

Tencent%2FLoopForge | Trendshift

English · 简体中文

Two ways to work · Quick start · SOPs · Features · Local · FAQ · Docs

loopforge-promo-v11-en.mp4

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 LoopForge chat workbench: a request is typed into the composer and the @ picker offers roles, skills, requirements and SOPs

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 Code to OpenCode, Cursor CLI and more. GitHub, Skills and MCP as tools. Docker sandboxes or your own machine as the runtime.

Quick start

Install Git and clone the repository first. The installer checks Docker, Compose, Python 3 and curl and offers to install missing components. Python/curl installation supports apt, dnf and yum on Linux; the Compose plugin supports x86_64/arm64 and verifies the official release SHA-256. macOS needs a working Python 3 and Docker Desktop; Homebrew can install missing components. Ordinary Linux users are supported through Docker group access or sudo. Set LOOPFORGE_YES=1 to accept installation prompts. Package and image downloads require internet access.

git clone https://github.com/Tencent/LoopForge.git
cd LoopForge
./start.sh

./start.sh pulls the GHCR release image pinned in compose.yaml without building locally (bash scripts/install.sh does the same). It creates the MySQL and platform services, generates configuration and session secrets, and installs the built-in sandboxes, starter SOPs and welcome project. Host Go and Node.js installations are not required. Configure model API keys and GitHub authorization after startup. Use ./start.sh logs, stop, restart or pull to manage it, and ./start.sh dev to build the checkout from source.

If downloads from ghcr.io stall, set MIRROR to a registry host that can stand in for ghcr.io. ./start.sh pulls from that host and tags the image back to the name pinned in compose.yaml. Setting MIRROR trusts that host, because the download is tagged with the official name. The GitHub Release records the digest; docker image inspect --format '{{index .RepoDigests 0}}' ghcr.io/tencent/loopforge:<pin> should show the same digest after @. Without MIRROR, ./start.sh still pulls ghcr.io directly, and compose.yaml stays unchanged. Upgrade with the same variable and ./start.sh pull. ghcr.nju.edu.cn is one such host. A Docker registry-mirrors entry such as https://docker.nju.edu.cn only accelerates Docker Hub and is not a value for MIRROR.

MIRROR=ghcr.nju.edu.cn ./start.sh

Open the address printed by the installer and create your account; the first one becomes the administrator. The service listens on 0.0.0.0:8090 by default. On a cloud host, the installer reads the public IP from the provider's metadata service and prints it; allow the port in your security group, or put an HTTPS reverse proxy in front. Restrict access to your own IP until the administrator account exists. The home page's quick-access guide walks you through adding a model key, connecting a repository and choosing an SOP.

For GitLab, Gitea, Gogs and other Git hosts, set up Git SSH to check out and push branches with a personal key. PR/MR and Issue automation requires a hosting API token or a separately configured MCP.

Try it without an API key

New accounts join the LoopForge demo project, which includes an SOP made only of a script and a human gate:

  1. Switch to the demo project, open Templates, and open Platform check · script & approval.
  2. Click Run SOP. A real script writes a report, then the run waits for you at the approval step.
  3. Approve it from Needs review or the run page, and watch the run continue to its final artifact.

What you need for real work

I want to… You need
Run the script + approval demo Nothing
Chat with Main Bot, generate a document or a new project An API key for the selected executor
Change an existing repository (in chat or via an SOP) and open a PR Model credentials and a GitHub repository (connect GitHub in personal settings)
More setup details: executors, GitHub, sandboxes, access model
  • Executors. Pick one of ten CLIs beside the home composer, then a model. Every SOP role can choose its executor independently (built-in roles default to CodeBuddy). Requirement clarification, AI notification summaries, Bot replies and run evals currently use CodeBuddy, so their model pickers list CodeBuddy models only and the server refuses a model of another CLI instead of switching it to CodeBuddy; scheduled assistant tasks run on the CLI the task selects.

    Executor Credentials Installation
    CodeBuddy Personal key, or a shared key an administrator configures for chat and SOP runs In the Docker image
    Codex Personal key; a connected execution machine can use its local login In the Docker image
    Claude Code Personal key; a connected execution machine can use its local login Installed from npm on first use, then cached
    OpenCode · Kimi Code · Pi Personal key only Installed from npm on first use, then cached
    DeepSeek Harness Personal key only In the Docker image
    Cursor CLI · Antigravity Personal key only Provider installer on first chat use; not installed into SOP sandboxes
    ZCode Personal key only Not bundled; install it on the service or execution machine PATH

    The seven agent CLIs after Claude Code keep their model and MCP configuration in a private home directory per run, so they always use the responsible user's own key and Base URL from personal settings, even on a connected execution machine. When rolling them out to a team, each member configures their own credentials. First-use installs need npm or provider access; native deployments need the CLI for the executor you choose.

  • GitHub is optional. All built-in generic SOPs run without a repository: product SOPs deliver documents, and new frontend/backend projects deliver source files in the task workspace. Bug fixes still need source code and reproduction details. Connect a repository when you work on existing code or want PRs.

  • Delivering to a repository. Choose Connect GitHub in personal settings, approve the device code on GitHub and pick your repository (the LoopForge OAuth App is built in; no PAT required, manual PAT entry still works). Set executor credentials (or bind a local execution machine), then either run a project SOP or ask Main Bot to change the code and submit a PR/MR.

  • Sandboxes. In the default Compose installation, SOP runs and conversation workspaces both use Docker sandbox containers started through the host Docker socket. Default sandboxes reuse the installed runtime image, so nothing extra is built after installation; custom Dockerfiles still build their own images. Docker socket access grants control of the host daemon, so this setup is for trusted teams, not untrusted multi-tenant isolation. See deployment boundaries. Re-running the installer keeps your data.

  • Accounts and access. New installations listen on all interfaces (existing bind settings are kept) and are designed for a trusted team: signed-in users can read project data across the instance, and teammates can sign up from the login page (AGENTFLOW_ALLOW_SIGNUP=false in .env turns that off). Read the account and access model before exposing it beyond your team.

  • Remote access, HTTPS, separate workers. See Deployment.

  • Hacking on LoopForge itself? bash scripts/dev.sh runs it natively (Go 1.26.11+).

How SOPs work

An SOP is the workflow a delivery follows. Agents, scripts and people take part in the same run:

The SOP flow: Requirement, then Clarify, Design, Implement, Review (agents), Test (script) and Accept (human gate), then Delivery; acceptance can send work back to Implement

The LoopForge SOP designer showing the built-in bug-fix SOP, with the Independent review step selected and its role, executor and failure policy in the inspector

The SOP designer with the built-in bug-fix SOP. Each step picks a role; failed checks can send the work back to an earlier step.

Node What it does
Agent A role (prompt, executor, model, rules, Skills and MCP tools) that designs, implements, reviews or tests.
Script A deterministic shell step: build, test, lint, generate a report. No AI where AI is not needed.
Human gate Pauses the run until someone checks the artifacts and approves, or sends the work back to a step.
Sub-SOP Runs another SOP as a sub-workflow.
Preview build Builds a static site and archives it for review.

Each node declares its artifacts and dependencies, and the engine starts each step once its dependencies complete. Start from a built-in SOP, adapt its roles, rules and environment to your project, and publish versions as it evolves.

LoopForge run details: the report script has finished and the run waits at the human gate with approve, add-context and send-back actions

A run waiting at a human gate: approve and continue, add context and rerun the step, or send the work back upstream.

A delivery we actually ran: four CodeBuddy roles planned a Python fix, implemented it, reviewed it independently and summarized the delivery. Three real tests passed; the run waited for human approval, then verified the accepted code had not changed. The reusable acceptance case checks the files and results. See the validation record for scope and known gaps.

Features

Area What you get
Chat workbench Main Bot with per-conversation executor, model and permission mode. @ references for roles, skills, requirements, SOPs and repositories. Messages queue while a reply runs; Steer interrupts and sends now. Generated files open in a side panel with preview, source and download.
Conversation workspaces On-demand Docker sandboxes with the project's repositories checked out, project roles as native subagents, and direct control of a running SOP workspace: pause, resume or take over.
SOP designer Visual canvas with Agent, Script, Human gate, Sub-SOP and Preview nodes, rework-on-failure edges, validation, version history and publishing. Built-in backend, frontend, bug-fix and product SOPs.
Roles Reusable definitions: prompt, executor, model, rules, Skills, MCP tools, artifacts and gates, shared across SOP nodes and chat subagents.
Requirement → delivery Requirements tracked end to end, whether shipped by an SOP or straight from chat, with PR/MR status tracking, merge detection and direct-branch merges.
Runs & approvals Live node status, tool traces, worker logs, per-node artifact snapshots and workspace previews. A single Needs review inbox for every gate waiting on you.
AI scheduled tasks Recurring agent tasks with full workspace, SOP and MCP access; a shared market of versioned, parameterized task templates; automatic SOP dispatch for new requirements.
Insights & cost Engineering metrics, business-domain reports with static HTML/SVG export, and token/cost accounting for SOPs and conversations at public list prices.
Execution environments Platform workers, Docker sandboxes, or a connected local execution machine using your own tools and repositories.
Team-ready Password accounts, projects and members, light/dark/system themes, an OpenAPI-described HTTP and MCP API. Management pages are in English and Chinese; the chat workbench is Chinese for now.

The Templates page listing the four built-in SOPs: backend delivery, frontend delivery, product proposal and bug fix

Built-in SOPs are read-only blueprints; copy one into your project to run and edit it.

LoopForge Local

Don't want to run a server? LoopForge Local brings the built-in delivery workflows straight into the coding assistant you already use:

# Run inside your target project, e.g. for Claude Code
npx -y loopforge-cli@latest install claude

Then run /start-devflow "<your request>" in Claude Code.

Host Supported
Claude Code · CodeBuddy · Codex · Cursor Classic (default) and Portable editions
Pi Portable edition
DeepSeek Harness Portable edition
Hermes Agent Portable edition

See the local guide for each host's entry point and editions for the differences. Source lives in local/. Local runs the built-in workflows today; exporting a platform SOP for standalone local execution is planned.

Platform Local
Best for Teams sharing chat workspaces, SOPs, approvals and history One developer inside an IDE or CLI
Needs Docker + Python 3 Node.js 20+, Python 3.8+ and a coding assistant
Workflows Chat with Main Bot + custom SOPs on a visual canvas Built-in Classic / Portable workflows
Evidence Shared run details, approvals and metrics in the web workspace Artifacts under artifacts/{task_slug}/ + optional local dashboard

FAQ

Do I need an API key to try it? No. The demo SOP uses only a script and a human gate. Chat and agent steps need a key for the executor you pick. Model usage is not included; you bring your own credentials.

Do I need GitHub? No. Chat, documents and new projects run in the task workspace. Connect GitHub when you want to change an existing repository or open PRs.

Should I use chat or an SOP? Use chat to explore and iterate; Main Bot can still open a PR. Once you find a way of working you want every requirement to follow, with fixed reviewers, tests and sign-off, put it in an SOP. Main Bot can start, pause and take over SOP runs, so the two paths work together.

How is this different from Dify, n8n or Flowise? Those are general-purpose AI and automation workflow builders. LoopForge is built for software delivery with coding agents: implementer and reviewer roles, Docker sandboxes with real repositories, GitHub delivery, human acceptance gates and run evidence.

How is this different from using Claude Code, Codex, CodeBuddy or another coding CLI directly? LoopForge doesn't replace them; it orchestrates them. Each agent step and each chat turn runs one of those CLIs. LoopForge adds what surrounds it: who does what, in which sandbox, in which order, with which checks, and who signs off.

Is it safe to expose on the internet? New installations listen on all interfaces and target a trusted team. Read the account and access model and set up HTTPS before opening it up. Report vulnerabilities privately via the security policy.

Documentation

I want to… Start here
Deploy, manage accounts, connect execution machines Deployment
Understand chat workspaces, scheduled AI tasks and token pricing Conversation workspaces · AI scheduled tasks · Token pricing
Install local workflows or choose an edition LoopForge Local · Editions
Extend the platform or use the HTTP / MCP API Architecture · API reference · Shared schedules API
Contribute to the UI Frontend design conventions (Chinese)
Check functional coverage and release readiness Validation record · Acceptance matrix · Release review
Understand source provenance and maintenance Public scope · Upstream synchronization

Community

Scan the QR code to join the LoopForge community group.

LoopForge community group QR code

Contributing

Issues and PRs are welcome: share a use case, report a bug, or improve workflows, integrations and the platform experience. Start with the contributing guide. Security issues go through the security policy.

If LoopForge is useful to you, a star helps others find it.

Star history

License

MIT. Third-party components keep their own licenses and notices; see THIRD_PARTY_NOTICES.md.

View on GitHub

Recent activity

commits and pull requests

Releases and announcements

13 total
  1. LoopForge v0.3.9-rc.1v0.3.9-rc.1Nov 13, 2026pre-release

    ## Install ```bash git clone --branch v0.3.9-rc.1 https://github.com/Tencent/LoopForge.git cd LoopForge ./start.sh ``` Platform image: `ghcr.io/tencent/loopforge:0.3.9-rc.1` (pinned in `compose.yaml`). Digest: `ghcr.io/tencent/loopforge@sha256:02321b3f08fafccda83dd42e580d2b97dfd7368f0f23942af5819fa48424a193`. 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:0.3.9-rc.1` and compare the digest after `@`. Existing installations: check out `v0.3.9-rc.1`, run `./start.sh`, and apply the new files under `migrations/` listed in [CHANGELOG.md](https://github.com/Tencent/LoopForge/blob/v0.3.9-rc.1/CHANGELOG.md). ## What's Changed * feat(chat): install a missing CLI from the conversation failure by @crispinhu27 in https://github.com/Tencent/LoopForge/pull/183 * feat(git): support SSH repositories with per-host user keys by @crispinhu27 in https://github.com/Tencent/LoopForge/pull/207 * fix(security): confine agent CLI config writes to home by @crispin

  2. LoopForge v0.3.8v0.3.8Nov 12, 2026

    ## Install ```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 after `@`. Existing installations: check out `v0.3.8`, run `./start.sh`, and apply the new files under `migrations/` listed in [CHANGELOG.md](https://github.com/Tencent/LoopForge/blob/v0.3.8/CHANGELOG.md). ## What's Changed * fix(deps): patch vulnerable chatbot test toolchain by @hxy91819 in https://github.com/Tencent/LoopForge/pull/166 * ci: mirror the platform image to TCR after publishing GHCR by @cocofhu in https://github.com/Tencent/LoopForge/pull/205 * fix(runtime): keep index.lock while an alternate-path holder is live by @Robert0622 in https://github.com/Tencen

  3. LoopForge v0.3.6v0.3.6Nov 11, 2026

    ## Install ```bash git clone --branch v0.3.6 https://github.com/Tencent/LoopForge.git cd LoopForge ./start.sh ``` Platform image: `ghcr.io/tencent/loopforge:0.3.6` (pinned in `compose.yaml`). Existing installations: check out `v0.3.6`, run `./start.sh`, and apply the new files under `migrations/` listed in [CHANGELOG.md](https://github.com/Tencent/LoopForge/blob/v0.3.6/CHANGELOG.md). ## What's Changed * fix(sop): provide a default sandbox and validate sandbox selection by @Robert0622 in https://github.com/Tencent/LoopForge/pull/176 * chore(release): prepare v0.3.6 by @Robert0622 in https://github.com/Tencent/LoopForge/pull/185 * ci: keep browser jobs running when runners cannot reach the Ubuntu archives by @Robert0622 in https://github.com/Tencent/LoopForge/pull/186 **Full Changelog**: https://github.com/Tencent/LoopForge/compare/v0.3.5...v0.3.6

  4. LoopForge v0.3.5v0.3.5Nov 11, 2026

    ## Install ```bash git clone --branch v0.3.5 https://github.com/Tencent/LoopForge.git cd LoopForge ./start.sh ``` Platform image: `ghcr.io/tencent/loopforge:0.3.5` (pinned in `compose.yaml`). Existing installations: check out `v0.3.5`, run `./start.sh`, and apply the new files under `migrations/` listed in [CHANGELOG.md](https://github.com/Tencent/LoopForge/blob/v0.3.5/CHANGELOG.md). ## What's Changed * feat: fail pull requests when coverage or a platform job drops by @fx-kurumi in https://github.com/Tencent/LoopForge/pull/115 * feat(assistant): lightweight GitHub tools for Main Bot without opening a workspace by @newexploreor in https://github.com/Tencent/LoopForge/pull/159 * feat(local): support Hermes and DSH host integrations by @Zhong-Chenchen in https://github.com/Tencent/LoopForge/pull/158 * fix(workspace): report progress and stop hung clones and image builds (#124) by @wycocoyu in https://github.com/Tencent/LoopForge/pull/150 * feat(runtime): add ZCode as an agent CLI executor (#125) by @wycocoyu in https://github.com/Tencent/LoopForge/pull/161 * fix: show the Pi mark in the chat CLI selector by @crispinhu27 in https://github.com/Tencent/LoopForge/pull/143 * feat: run p

  5. LoopForge v0.3.4v0.3.4Nov 9, 2026

    ## Install ```bash git clone --branch v0.3.4 https://github.com/Tencent/LoopForge.git cd LoopForge ./start.sh ``` Platform image: `ghcr.io/tencent/loopforge:0.3.4` (pinned in `compose.yaml`). Existing installations: check out `v0.3.4`, run `./start.sh`, and apply the new files under `migrations/` listed in [CHANGELOG.md](https://github.com/Tencent/LoopForge/blob/v0.3.4/CHANGELOG.md). ## What's Changed * docs: use ./start.sh as the quick start by @cocofhu in https://github.com/Tencent/LoopForge/pull/107 * chore(deps-dev): Bump @playwright/test from 1.55.1 to 1.64.1 in /e2e by @dependabot[bot] in https://github.com/Tencent/LoopForge/pull/56 * chore(deps): Bump actions/upload-artifact from 4 to 7 by @dependabot[bot] in https://github.com/Tencent/LoopForge/pull/58 * chore(deps): Bump actions/setup-node from 7.0.0 to 7.1.0 in the actions group across 1 directory by @dependabot[bot] in https://github.com/Tencent/LoopForge/pull/57 * fix(deps): upgrade setuptools while preserving Python 3.8 support by @dependabot[bot] in https://github.com/Tencent/LoopForge/pull/64 * chore(deps): update MySQL driver and refresh license notices by @dependabot[bot] in https://github.com/Tencent/LoopForge/

Code frequency

additions and deletions
+539.8K-539.8KWeek of 2026-07-26: +1 linesWeek of 2026-07-26: -0 linesWeek of 2026-08-02: +27,598 linesWeek of 2026-08-02: -51 linesWeek of 2026-08-09: +0 linesWeek of 2026-08-09: -0 linesWeek of 2026-08-16: +0 linesWeek of 2026-08-16: -0 linesWeek of 2026-08-23: +0 linesWeek of 2026-08-23: -0 linesWeek of 2026-08-30: +0 linesWeek of 2026-08-30: -0 linesWeek of 2026-09-06: +19 linesWeek of 2026-09-06: -5 linesWeek of 2026-09-13: +45,982 linesWeek of 2026-09-13: -62 linesWeek of 2026-09-20: +0 linesWeek of 2026-09-20: -0 linesWeek of 2026-09-27: +0 linesWeek of 2026-09-27: -0 linesWeek of 2026-10-04: +0 linesWeek of 2026-10-04: -0 linesWeek of 2026-10-11: +2,246 linesWeek of 2026-10-11: -477 linesWeek of 2026-10-18: +539,821 linesWeek of 2026-10-18: -74,707 linesWeek of 2026-10-25: +0 linesWeek of 2026-10-25: -0 linesWeek of 2026-11-01: +174,937 linesWeek of 2026-11-01: -31,220 linesWeek of 2026-11-08: +71,661 linesWeek of 2026-11-08: -12,467 linesWeek of 2026-11-15: +3,025 linesWeek of 2026-11-15: -128 linesJul 26, 2026Nov 15, 2026
+865.3K lines added, -119.1K removed over the last year.

Commits per week

last 52 weeks
2610Week of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 0 commitsWeek of 2026-01-11: 0 commitsWeek of 2026-01-18: 0 commitsWeek of 2026-01-25: 0 commitsWeek of 2026-02-01: 0 commitsWeek of 2026-02-08: 0 commitsWeek of 2026-02-15: 0 commitsWeek of 2026-02-22: 0 commitsWeek of 2026-03-01: 0 commitsWeek of 2026-03-08: 0 commitsWeek of 2026-03-15: 0 commitsWeek of 2026-03-22: 0 commitsWeek of 2026-03-29: 0 commitsWeek of 2026-04-05: 0 commitsWeek of 2026-04-12: 0 commitsWeek of 2026-04-19: 0 commitsWeek of 2026-04-26: 0 commitsWeek of 2026-05-03: 0 commitsWeek of 2026-05-10: 0 commitsWeek of 2026-05-17: 0 commitsWeek of 2026-05-24: 0 commitsWeek of 2026-05-31: 0 commitsWeek of 2026-06-07: 0 commitsWeek of 2026-06-14: 0 commitsWeek of 2026-06-21: 0 commitsWeek of 2026-06-28: 0 commitsWeek of 2026-07-05: 0 commitsWeek of 2026-07-12: 0 commitsWeek of 2026-07-19: 0 commitsWeek of 2026-07-26: 1 commitsWeek of 2026-08-02: 5 commitsWeek of 2026-08-09: 0 commitsWeek of 2026-08-16: 0 commitsWeek of 2026-08-23: 0 commitsWeek of 2026-08-30: 0 commitsWeek of 2026-09-06: 1 commitsWeek of 2026-09-13: 14 commitsWeek of 2026-09-20: 0 commitsWeek of 2026-09-27: 0 commitsWeek of 2026-10-04: 0 commitsWeek of 2026-10-11: 5 commitsWeek of 2026-10-18: 3 commitsWeek of 2026-10-25: 0 commitsWeek of 2026-11-01: 32 commitsWeek of 2026-11-08: 261 commitsWeek of 2026-11-15: 2 commitsNov 23, 2025Nov 15, 2026
324 commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 0 commitsSun 1:00 — 0 commitsSun 2:00 — 0 commitsSun 3:00 — 0 commitsSun 4:00 — 1 commitsSun 5:00 — 0 commitsSun 6:00 — 1 commitsSun 7:00 — 0 commitsSun 8:00 — 0 commitsSun 9:00 — 0 commitsSun 10:00 — 0 commitsSun 11:00 — 0 commitsSun 12:00 — 0 commitsSun 13:00 — 0 commitsSun 14:00 — 0 commitsSun 15:00 — 0 commitsSun 16:00 — 0 commitsSun 17:00 — 0 commitsSun 18:00 — 0 commitsSun 19:00 — 0 commitsSun 20:00 — 0 commitsSun 21:00 — 0 commitsSun 22:00 — 1 commitsSun 23:00 — 2 commitsMon 0:00 — 1 commitsMon 1:00 — 0 commitsMon 2:00 — 1 commitsMon 3:00 — 0 commitsMon 4:00 — 0 commitsMon 5:00 — 0 commitsMon 6:00 — 0 commitsMon 7:00 — 0 commitsMon 8:00 — 0 commitsMon 9:00 — 0 commitsMon 10:00 — 0 commitsMon 11:00 — 0 commitsMon 12:00 — 0 commitsMon 13:00 — 0 commitsMon 14:00 — 0 commitsMon 15:00 — 2 commitsMon 16:00 — 1 commitsMon 17:00 — 0 commitsMon 18:00 — 0 commitsMon 19:00 — 0 commitsMon 20:00 — 0 commitsMon 21:00 — 1 commitsMon 22:00 — 0 commitsMon 23:00 — 0 commitsTue 0:00 — 0 commitsTue 1:00 — 0 commitsTue 2:00 — 0 commitsTue 3:00 — 0 commitsTue 4:00 — 2 commitsTue 5:00 — 0 commitsTue 6:00 — 0 commitsTue 7:00 — 0 commitsTue 8:00 — 0 commitsTue 9:00 — 0 commitsTue 10:00 — 0 commitsTue 11:00 — 2 commitsTue 12:00 — 0 commitsTue 13:00 — 0 commitsTue 14:00 — 1 commitsTue 15:00 — 2 commitsTue 16:00 — 1 commitsTue 17:00 — 4 commitsTue 18:00 — 0 commitsTue 19:00 — 3 commitsTue 20:00 — 0 commitsTue 21:00 — 0 commitsTue 22:00 — 6 commitsTue 23:00 — 2 commitsWed 0:00 — 0 commitsWed 1:00 — 6 commitsWed 2:00 — 0 commitsWed 3:00 — 0 commitsWed 4:00 — 0 commitsWed 5:00 — 0 commitsWed 6:00 — 0 commitsWed 7:00 — 0 commitsWed 8:00 — 0 commitsWed 9:00 — 0 commitsWed 10:00 — 1 commitsWed 11:00 — 0 commitsWed 12:00 — 0 commitsWed 13:00 — 0 commitsWed 14:00 — 0 commitsWed 15:00 — 0 commitsWed 16:00 — 0 commitsWed 17:00 — 4 commitsWed 18:00 — 1 commitsWed 19:00 — 2 commitsWed 20:00 — 1 commitsWed 21:00 — 1 commitsWed 22:00 — 2 commitsWed 23:00 — 1 commitsThu 0:00 — 0 commitsThu 1:00 — 0 commitsThu 2:00 — 0 commitsThu 3:00 — 0 commitsThu 4:00 — 0 commitsThu 5:00 — 0 commitsThu 6:00 — 0 commitsThu 7:00 — 0 commitsThu 8:00 — 0 commitsThu 9:00 — 0 commitsThu 10:00 — 1 commitsThu 11:00 — 0 commitsThu 12:00 — 0 commitsThu 13:00 — 0 commitsThu 14:00 — 1 commitsThu 15:00 — 3 commitsThu 16:00 — 7 commitsThu 17:00 — 2 commitsThu 18:00 — 3 commitsThu 19:00 — 7 commitsThu 20:00 — 4 commitsThu 21:00 — 0 commitsThu 22:00 — 1 commitsThu 23:00 — 3 commitsFri 0:00 — 0 commitsFri 1:00 — 1 commitsFri 2:00 — 2 commitsFri 3:00 — 2 commitsFri 4:00 — 0 commitsFri 5:00 — 0 commitsFri 6:00 — 0 commitsFri 7:00 — 0 commitsFri 8:00 — 0 commitsFri 9:00 — 0 commitsFri 10:00 — 0 commitsFri 11:00 — 1 commitsFri 12:00 — 0 commitsFri 13:00 — 1 commitsFri 14:00 — 0 commitsFri 15:00 — 0 commitsFri 16:00 — 1 commitsFri 17:00 — 24 commitsFri 18:00 — 44 commitsFri 19:00 — 34 commitsFri 20:00 — 21 commitsFri 21:00 — 4 commitsFri 22:00 — 3 commitsFri 23:00 — 2 commitsSat 0:00 — 3 commitsSat 1:00 — 4 commitsSat 2:00 — 36 commitsSat 3:00 — 8 commitsSat 4:00 — 3 commitsSat 5:00 — 0 commitsSat 6:00 — 8 commitsSat 7:00 — 3 commitsSat 8:00 — 0 commitsSat 9:00 — 0 commitsSat 10:00 — 0 commitsSat 11:00 — 0 commitsSat 12:00 — 0 commitsSat 13:00 — 0 commitsSat 14:00 — 0 commitsSat 15:00 — 0 commitsSat 16:00 — 4 commitsSat 17:00 — 6 commitsSat 18:00 — 0 commitsSat 19:00 — 0 commitsSat 20:00 — 17 commitsSat 21:00 — 0 commitsSat 22:00 — 5 commitsSat 23:00 — 2 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Nov 18, 2026daily#3+590
Nov 17, 2026daily#3+590
Nov 16, 2026daily#10+33
Nov 15, 2026daily#10+33
  • morluto/rea

    Reverse engineer anything with agents, from app behavior down to native binaries.

    471.6K stars · TypeScript

  • awesome-selfhosted/awesome-selfhosted

    A list of Free Software network services and web applications which can be hosted on your own servers

    339K stars

  • obra/superpowers

    An agentic skills framework & software development methodology that works.

    322.9K stars · Shell

  • affaan-m/ECC

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    307.9K stars · JavaScript

  • NousResearch/hermes-agent

    The agent that grows with you

    265K stars · Python

  • n8n-io/n8n

    Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

    211.6K stars · TypeScript