LoopForge
Active·★ 5.5k·NOASSERTION·Updated 2026-11-21
LoopForge wraps coding-agent CLIs in self-hosted software-delivery workflows. Chat-driven tasks and reusable SOPs share requirements, sandboxes, checkpoints and execution history.
#agent-orchestration#agentic-workflow#ai-agents#ai-coding#claude-code#code-review#codebuddy#codex
01
Features
01SOP nodes combine agents, scripts and human gates.
02Project roles separate planning, implementation, review and tests.
03Tracks artifacts and supports pausing, retries and node reruns.
02
Why choose it
+
+
+
+
03
Trade-offs
!
!
!
!
04
Maintenance check
ActiveChecked: 2026-11-18
- Last commit
- 2026-11-17
- Commits, last 90 days
- 100+
- Releases, last 90 days
- 13
- Latest release
- v0.4.0 (2026-11-17)
- Open issues
- 184
- Recent issues with at least one comment
- 5/5
Commits per week, last 12 weeks
Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.
Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.
Most discussed open issues
- #125 [Feature]: 支持 ZCode 与 Reasonix 作为执行器与本地宿主6 comments · 2026-11-09
- #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
- #949 [Feature]: 沙箱磁盘占用缺少容量检查与预警,写满后故障无法定位3 comments · 2026-11-16
- #892 [Bug]: Docker 部署首次使用 Claude Code 失败,页面无错误提示(CLI 从 npm 安装超时)3 comments · 2026-11-15
- #717 [SOP run] Code loss: workspace cleaned after success while changes stay uncommitted; repository-patch stores file inventory only3 comments · 2026-11-14
Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.
05
Compatibility
docker
Docker Compose; Git, Python 3 and curl checked by installer
Verified via docs
macos
Docker Desktop and working Python 3 required
Verified via docs
linux
Linux installer supports apt, dnf and yum
Verified via docs
06
Quick start
1
$ git clone https://github.com/Tencent/LoopForge.git
2
$ cd LoopForge
3
$ ./start.sh
07
Use cases
↳Run a repeatable feature-delivery pipeline.
↳Review artifacts at a human approval gate.
↳Resume a failed delivery step with its execution history.
08
Alternatives
apra-fleet★ 108
AI agents that write code, review each other's work, and coordinate across your machines
claude-delegator★ 188
Ask Codex, Gemini/Antigravity, and Grok (xAI) for second opinions or arbiter-mediated consensus inside Claude Code.
better-code-review-graph★ 76
Knowledge graph for token-efficient code reviews — fixed search, qualified call resolution, dual-mode embedding (ONNX + multi-provider cloud)
takt★ 1.5k
TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML
Comments
Log in to leave a comment
No comments yet. Be the first!