# LoopForge — AI Coding Tool Review & Pricing

> LoopForge is a self-hosted workspace from Tencent for shipping software with coding agents. You either chat with Main Bot, which opens a Docker sandbox with your repositories and opens the pull request, or run an SOP: a versioned workflow of agent roles, scripts and human approval gates that delivers every requirement the same way.

Source: https://ai.dosa.dev/tools/loopforge · Updated Nov 14, 2026 · Category: Autonomous & Async Agents · Published by dosa.dev

## At a glance

- **Tool**: LoopForge
- **Company**: Tencent
- **Category**: [Autonomous & Async Agents](https://ai.dosa.dev/category/async-agents)
- **Pricing model**: Open Source
- **Official website**: https://loopforge.cn

## Key features

- Main Bot chat that works in on-demand Docker sandboxes and opens pull requests
- Visual SOP designer with Agent, Script, Human-gate, Sub-SOP and Preview-build nodes
- Ten coding-agent CLIs as executors, including CodeBuddy, Codex, Claude Code, OpenCode and Cursor CLI
- Roles with their own prompt, model, rules, Skills and MCP tools
- Needs review inbox, run traces, artifacts and token cost accounting
- Scheduled AI tasks and an HTTP and MCP API
- LoopForge Local brings the built-in workflows into Claude Code, Codex, Cursor and other hosts

## Pricing

**Model**: Open Source

LoopForge is free and open-source under the MIT licence and runs on your own infrastructure with Docker. Model usage is not included: each user brings credentials for the coding-agent CLI they pick, billed by that provider.

## Who it is for

- **Best for**: Engineering teams that want repeatable, reviewable delivery with coding agents on their own servers, with fixed stages, reviewers and sign-off.
- **Not ideal for**: Untrusted multi-tenant deployments, since sandboxes use the host Docker socket, or teams that need an English chat workbench today.

## Verdict

A serious open-source take on agent delivery pipelines with human gates, best suited to teams willing to self-host.

## Recent updates

v0.3.8 was released on November 12, 2026, followed by the v0.3.9-rc.1 pre-release on November 13; the repository was trending on GitHub on November 14, 2026.

## Frequently asked questions

### Is LoopForge free?

Yes - LoopForge is Open Source. LoopForge is free and open-source under the MIT licence and runs on your own infrastructure with Docker. Model usage is not included: each user brings credentials for the coding-agent CLI they pick, billed by that provider.

### Is LoopForge open source?

Yes - LoopForge is open source. LoopForge is free and open-source under the MIT licence and runs on your own infrastructure with Docker. Model usage is not included: each user brings credentials for the coding-agent CLI they pick, billed by that provider.

### Who is LoopForge best for?

Engineering teams that want repeatable, reviewable delivery with coding agents on their own servers, with fixed stages, reviewers and sign-off.

### Who is LoopForge not ideal for?

Untrusted multi-tenant deployments, since sandboxes use the host Docker socket, or teams that need an English chat workbench today.

### What are the best LoopForge alternatives?

The closest LoopForge alternatives on ai.dosa.dev are Jules by Google, OpenHands, SWE-agent - all listed under Autonomous & Async Agents.

### Who makes LoopForge?

LoopForge is developed by Tencent. It is listed in the Autonomous & Async Agents category on ai.dosa.dev.

## Top alternatives

- [Jules by Google](https://ai.dosa.dev/tools/jules) (Freemium) — Developers who want to offload repetitive, non-urgent tasks like dependency version bumps, lint fixes, test scaffolding, and resolving CI failures in GitHub-hosted projects.
- [OpenHands](https://ai.dosa.dev/tools/openhands) (Freemium) — Individual developers and software teams looking to automate repetitive coding tasks, repository maintenance, and issue resolution through autonomous agents.
- [SWE-agent](https://ai.dosa.dev/tools/swe-agent) (Open Source) — Autonomous resolution of software engineering issues in real GitHub repositories and performing custom developer tasks using language models.
- [mini-swe-agent](https://ai.dosa.dev/tools/mini-swe-agent) (Open Source) — Researchers and engineers who want a small, transparent coding agent baseline for benchmarks, fine-tuning or sandboxed batch runs, and developers who want a simple bash-only agent in the terminal.
- [Sweep](https://ai.dosa.dev/tools/sweep) (Freemium) — Individual developers and teams working primarily in JetBrains IDEs who want a native-feeling assistant for routine coding tasks, bug fixes, and autocompletions.
- [Ellipsis](https://ai.dosa.dev/tools/ellipsis) (Freemium) — Teams looking to centralize and govern AI coding agents across repositories with secure, non-personal credentials and persistent cloud-based execution.
- Full alternatives guide: https://ai.dosa.dev/tools/loopforge/alternatives
