Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

LoopForge by Tencent

Self-hosted platform from Tencent for coding-agent delivery: chat with coding agents (CodeBuddy, Codex, Claude Code) in sandboxed workspaces, run repeatable SOP workflows with scripts and human approval gates, and approve what ships. Docker deploy plus the loopforge-cli npm package for local workflows.

Agent orchestration and team workspaces New · Added to AgentGid on Nov 17, 2026Open source · MITFree to start
Price
Free (OSS)
free and open source
Popularity
#9 in Orchestration
Gid Score 40 / 100 · limited data, 2/4 signals · #86 of 251 ranked AI agents
Trend
Gaining stars fast
about +501 GitHub stars a day
Development
Actively updated
latest 0.4.0, 3d ago
Community
3,890 GitHub stars
public signals

Usage data: latest readings Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number

What LoopForge does

It is free and open source (MIT); you pay only for the models it calls.

Key facts

MakerTencent
First releasedJuly 2026
LicenseMIT
Main languageGo
Open issues and PRs233

Pricing

Open source under MIT (third-party components keep their own licences) and self-hosted with Docker.

Checked Nov 17, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

What's new in LoopForge: November 2026 so far

Full monthly summary

November brought significant stability improvements and security hardening to LoopForge, along with expanded agent capabilities and better workspace management. The month focused on refining the chat workbench experience and fixing critical deployment and authentication issues.

  • GitHub SSH repositories now support per-host user keys for better key management.
  • Agents can now install missing CLI tools directly from conversation failures, improving reliability.
  • Workspace editing is now possible while agents are actively running.
  • Security improvements include confining agent CLI config writes and removing credentials from clone URLs.

9 releases this month · summarised from the official release notes · all months

Compare LoopForge with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
27
Herdr Newherdrdev
55 — — — 51.8K+202/day 0.9.537d ago Free (OSS)
31
PaperclipPaperclip
53 69.3K up 5.1% up 17.9% 115K+245/day 2026.1117.02d ago Free (OSS)
34
OrcaStably
53 — — — 129K+933/day 1.4.2632d ago Free (OSS)
43 50 69.4K down 28.1% up 25.4% 82.1K+87/day 3.77.23d ago Free (OSS)
58
DS-Bot NewFei2411
462/4 — — — 8,392+193/day 0.3.84d ago Free (OSS)
66
MulticaIndex Labs (Hong Kong) Limited
44 — — — 56.7K+131/day 0.11.02d ago Free self-hosted; cloud and commercial via sales

Ratings from people who use LoopForge

No ratings yet. Used LoopForge? Rate it and say what it is good and bad at.

LoopForge news

All AI agent news

  1. Release GitHub Releases

    LoopForge 0.4.0 released

    feat(chat): install a missing CLI from the conversation failure; feat(git): support SSH repositories with per-host user keys; fix(security): confine agent CLI config writes to home

  2. New on AgentGid AgentGid

    4 agents added to AgentGid

    LoopForge, Nod, bb, AgentRun

  3. Data AgentGid data

    LoopForge gained 1,766 GitHub stars in a week

    Now at 1,927 stars, against about 29 a week over the month before.

  4. Release GitHub Releases

    LoopForge 0.3.8 released

    fix(deps): patch vulnerable chatbot test toolchain; ci: mirror the platform image to TCR after publishing GHCR; fix(runtime): keep index.lock while an alternate-path holder is live

What changed: recent LoopForge releases

12 stable releases in the last 90 days · Monthly summary · Full changelog

0.4.0
  • feat(chat): install a missing CLI from the conversation failure
  • feat(git): support SSH repositories with per-host user keys
  • fix(security): confine agent CLI config writes to home
  • fix(repo): keep credentials out of repository clone URLs
  • fix(schedule): drop the length limit on scheduled task prompts
  • fix(bind-cli): start the systemd user bus before installing the service
0.3.8
  • fix(deps): patch vulnerable chatbot test toolchain
  • ci: mirror the platform image to TCR after publishing GHCR
  • fix(runtime): keep index.lock while an alternate-path holder is live
  • ci(platform): run repository-bound and second-user e2e API tests
  • fix(chatbot): clear the missing-key notice once quick access saves a key
  • fix(access): never emit http:// endpoints for token-bearing snippets on https
Earlier releases
0.3.6
  • fix(sop): provide a default sandbox and validate sandbox selection
  • chore(release): prepare v0.3.6
  • ci: keep browser jobs running when runners cannot reach the Ubuntu archives
0.3.5
  • feat: fail pull requests when coverage or a platform job drops
  • feat(assistant): lightweight GitHub tools for Main Bot without opening a workspace
  • feat(local): support Hermes and DSH host integrations
  • fix(workspace): report progress and stop hung clones and image builds
  • feat(runtime): add ZCode as an agent CLI executor
  • fix: show the Pi mark in the chat CLI selector
0.3.4
  • docs: use ./start.sh as the quick start
  • chore(deps-dev): Bump @playwright/test from 1.55.1 to 1.64.1 in /e2e
  • chore(deps): Bump actions/upload-artifact from 4 to 7
  • chore(deps): Bump actions/setup-node from 7.0.0 to 7.1.0 in the actions group across 1 directory
  • fix(deps): upgrade setuptools while preserving Python 3.8 support
  • chore(deps): update MySQL driver and refresh license notices
0.3.3
  • fix(web,chatbot): copy GitHub device code on HTTP; rename remaining AgentFlow labels to LoopForge
  • fix: show LoopForge instead of AgentFlow in user-visible text
  • docs: keep bash scripts/install.sh as the quick start alongside ./start.sh
  • fix(web): keep the credential wizard from stealing focus from a field the user picked
  • fix: Codex and Claude Code SOP roles in Docker sandboxes; label installer addresses (0.3.3)

LoopForge popularity and usage data

The GitHub repository has 3,890 stars, 3,840 of them added in the last 30 days. The latest stable release is 0.4.0, published Nov 17, 2026; there were 9 stable releases in the past 30 days.

GitHub starsrunning total 3,890

Download the raw daily series: loopforge.csv

Gid Score breakdown

Adoption—
Community25
Attention—
Momentum100

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. For LoopForge, public data covers only 2 of the 4 components, so treat this score as limited: closed products often publish few numbers, and a missing component lowers the score. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
GitHub starsNov 19, 2026Nov 19, 06:26 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

LoopForge FAQ

How much does LoopForge cost?

Open source under MIT (third-party components keep their own licences) and self-hosted with Docker.

Is LoopForge open source?

Yes. LoopForge is open source, released under the MIT license.

How popular is LoopForge?

The GitHub repository has 3,890 stars, 3,840 of them added in the last 30 days. The latest stable release is 0.4.0, published Nov 17, 2026; there were 9 stable releases in the past 30 days.

What is the latest version of LoopForge?

The latest stable release we track is 0.4.0, published on Nov 17, 2026.

What are the alternatives to LoopForge?

The closest alternatives in the same category by Gid Score are Herdr, Paperclip, Orca, Ruflo.

For the makers of LoopForge badges, corrections

Add a live badge to your README or site:

AgentGid: #9 in Orchestration Gid Score: 40/100

[![AgentGid: #9 in Orchestration](https://agentgid.com/badges/loopforge-rank.svg)](https://agentgid.com/agents/loopforge/)
[![Gid Score: 40/100](https://agentgid.com/badges/loopforge-score.svg)](https://agentgid.com/agents/loopforge/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

GitHub: tencent/loopforge. Site rank: loopforge.cn on the Tranco list. See data sources for how each one is collected.

Product facts and pricing were checked against: loopforge.cn, github.com.