explainx.ai350K+ learn from us
TrendingAI News TodayExplainx for Business
Pricing
explainx.ai

Upskill in AI — 16 free pathways, live workshops & bootcamps, and 50+ courses from practitioners. Plus the skills, tools, and MCP servers to practice on.

follow us

follow on google

Add explainx.ai as a preferred source

corporate training

support@explainx.ai

get started

Find your pathTake Free Evaluation

community

Join the community

learn

mind: share how you thinkpathways — start freeworkshopsbootcampscoursescompare Explainxcertificationsmock testsexplainx universitycorporate traininglearn skills & mcp

discover

skillsmcp serversexplainx mcpestacktoolsmdx readeragentsllmsdesignsdictionarypeopleagi trackerfelony benchranks

company

aboutvisionmissionteaminstructorsteach on explainxpartnershipscommunityhackathonscareers

content

daily AI newsstate of AI — live resultsblogreleasespromptsgeneratorsresource libraryfor LLMsexplainx.ai kids

solutions

all solutionsdeveloper upskillingmarketing upskillingproduct manager upskillingleadership upskilling

newsletter · weekly

Get AI news, tools, and insights in your inbox.

supportcontactprivacytermsdata rightshow we create contentsubmission guidelines

© 2026 AISOLO Technologies Pvt Ltd

explainx.ai

On this page

  • TL;DR
  • Why another agent platform?
  • How a request flows from chat to sign-off
  • Which harnesses plug in?
  • Plugins versus skills and agents
  • Install paths: desktop, Docker, demo
  • Data, telemetry, and runner security
  • How SoduWork compares to alternatives
  • Licensing, competitors, and when to wait
  • Roadmap and community
  • What to try this week
  • Related reading
← Back to blog

explainx / blog

SoduWork: Self-Hosted Multi-Harness Agent Workspace for Teams

Coding Agents, Open Source, Agent Harness, Self-Hosted AI, Guides

Part of AI Coding Tools

SoduWork is a self-hosted hub where Pi, OpenCode, DeepSeek Harness, Qwen Code, Kimi, and Codex run on shared issues with acceptance criteria, AI review, and plugins.

Nov 18, 2026·8 min read·Yash Thakker
add explainx.ai
go deep
SoduWork: Self-Hosted Multi-Harness Agent Workspace for Teams

SoduWork is a self-hosted hub where coding agents finish work only after someone signs off on evidence, not when the model stops typing. The mdiri-ai/SoduWork repository describes itself as an AI-native engine for teams and agents: multi-harness, multi-agent, and self-hosted. GitHub listed about 2,431 stars when explainx.ai checked on November 18, 2026.

The pitch is governance for harnesses you may already run. Instead of three subscriptions and three chat logs, SoduWork puts requests, plugins, and review in one Hub so Pi can implement, OpenCode can review on a different model, and a human accepts or sends work back.

Daily briefFrom Yash · 350K+ students taught

Catch up on AI

One AI story explained in plain English, plus one thing to try. Every day, free. Unsubscribe anytime.

TL;DR

table · 2 cols
QuestionAnswer (per SoduWork README, Nov 2026)
What ships?Hub, admin console, desktop client, optional cloud runners
Harness countNine named adapters plus ACP catalog entries
Done meansRequester sign-off after AI review checks criteria
Local startsh start.sh --desktop after clone
Team deploypython3 ops/self-host/deploy.py up with PostgreSQL
StatusPublic beta; evaluate before production

Why another agent platform?

Individual developers already get fast output from Claude Code, Codex, or OpenCode. The README argues the missing layer is trust and reuse: time saved generating text returns as time spent verifying it, and good workflows die in private threads.

SoduWork targets four pains it lists in prose:

table · 2 cols
PainSoduWork response
Fast output, slow trustAcceptance criteria before work; separate AI review; human sign-off
Methods trapped in chatPlugins versioned and granted to people or teams
Many AI tools, no standardOne workbench; switch harness mid-conversation
Handoffs re-explain contextIssues carry history, files, and audit trail

That is adjacent to Tencent LoopForge, which chains CLIs through SOP nodes and Docker sandboxes, and Agent Autoloop, which watches GitHub with approval cards. SoduWork leans toward issue tracking plus plugin catalog rather than only CI delivery.

Teams already wrestling with parallel Claude and Codex tabs sometimes adopt a git-backed queue or Worktrunk worktrees before they adopt a Hub. SoduWork tries to sit one layer above that: shared issues, grants, and review so the same acceptance bar applies whether the assignee is you, a contractor, or an agent process on a cloud runner.

How a request flows from chat to sign-off

The README’s workflow diagram is explicit: raise a request, let AI refine acceptance criteria, assign yourself or a colleague or an agent, run work with a team plugin, run AI review (assignee confirms), requester signs off, then optionally save the method as a plugin for the next person.

That separation matters for builders shipping agent skills or MCP tools. The Hub is the single source of truth for issues, approvals, and evidence; harnesses are interchangeable executors.

Levels of multi-agent behavior, again per README:

table · 2 cols
LevelWho moves work
Sequential stepsPlugin workflow nodes
Human and agentColleague’s agent delivers; requester signs off
Parallel issuesHub schedules different agents on different issues

Agents do not autonomously delegate to other agents unless the plugin workflow or a person assigns the next step—an intentional guard against runaway chains.

Which harnesses plug in?

SoduWork treats a harness as the runtime that drives tools, not the model weights. Nine are documented:

table · 3 cols
HarnessModelsConnection
PiSoduWork model catalogBuilt in
OpenCodeCatalog modelsNative adapter
DeepSeek HarnessCatalog or your DeepSeek keyACP, on-demand install
Qwen CodeCatalogACP
Kimi CodeCatalogACP
Codex HarnessCatalogACP
CodexIts own OpenAI accountNative adapter

Programs that speak the Agent Client Protocol (ACP) can be added through a catalog declaration—similar in spirit to CLI-Anything’s agent-native wrapping, but here the Hub owns permissions and audit.

Switching harnesses mid-conversation keeps history and the working folder, which is harder when each CLI is a separate terminal tab.

Hub with cables into distinct tool nodes, matching multiple harness adapters on one workspaceHub with cables into distinct tool nodes, matching multiple harness adapters on one workspace

Plugins versus skills and agents

The README includes a comparison table between skills, standalone agents, SoduWork plugins, and SoduWork apps:

table · 4 cols
CapabilitySkill docTypical agentSoduWork plugin
Step-by-step processNoPartialYes
Harness choiceNoPartialYes
Criteria + AI review + sign-offNoPartialYes
Versioning and grantsPartialPartialYes

A plugin can be as simple as a weekly brief workflow: draft node on Pi, review node on Qwen that blocks claims without sources, then publish. The JSON example in the README uses ai and ai_review node types with explicit dependsOn edges—closer to a miniature LangGraph-style graph than a single prompt file.

Teams can keep plugins private or submit them for review, publish, and scoped grants—the enterprise pattern CowAgent and Octop chase from different angles.

Market-stall motif for team plugin catalog with grants and versioningMarket-stall motif for team plugin catalog with grants and versioning

Install paths: desktop, Docker, demo

From source (solo or team lab):

Requirements on the README: Python 3.12+, Node.js 22.19+, Git. After clone:

text
sh start.sh --desktop

First boot installs dependencies, starts Hub and admin console, prompts for a 12–128 character admin password, and opens the desktop client. The README stresses that saving an API key in the admin UI does not create a selectable chat model—you must add the provider’s exact model ID under Capabilities → Model catalog.

Docker team deploy:

text
python3 ops/self-host/deploy.py up
python3 ops/self-host/deploy.py credentials

That brings up Hub, admin console, and PostgreSQL on one server; production use expects HTTPS in front.

Hosted demo: Releases ship Windows .exe, macOS .dmg, and Linux packages. Point Connection at https://service.soduwork.ai only for evaluation—the README forbids real business data on the demo Hub.

Rounded server rack beside a building, illustrating on-prem agent hub deploymentRounded server rack beside a building, illustrating on-prem agent hub deployment

Data, telemetry, and runner security

Self-hosters should read the Where does my data go? section carefully. When you run your own Hub, issues and chat live on your database. Model calls still go to whichever provider you configure, using short-lived credentials per run.

The README also documents operational traffic to the selected Hub: device auth, usage accounting (conversation IDs, token counters, timestamps), and client update checks every six hours for installed builds. Source launches skip installer update polling. There is no toggle documented to disable Hub accounting or update checks on installed clients—if you want zero calls to MDiRi’s hosted service, you aim the client at your Hub only.

Runners connect over WebSocket with deduplicated dispatch IDs and subprocess isolation per harness, but the FAQ states runners are not a general-purpose sandbox—actual isolation depends on the harness and your host hardening. Pair that with external sandbox guides for coding agents when exposure matters.

How SoduWork compares to alternatives

The README’s comparison matrix places SoduWork against low-code agent builders, coding harnesses alone, multi-agent orchestrators, and AI office assistants. The recurring claim: it does not replace Codex or Claude Code—it runs them with issue state, review, and plugin governance.

table · 3 cols
CategoryTypical gapSoduWork emphasis
Low-code buildersCanvas wiringSave a real task as a versioned plugin
Coding harness onlyNo team sign-offIssues + independent review harness
OrchestratorsAgent-to-agent autonomyPeople set checkpoints
Office AIHistory trapped per userPublished plugin catalog

For a coding-only orchestration without plugin marketplace framing, compare LoopForge’s SOP engine and Microsoft’s agent spend analytics at Ignite for the enterprise FinOps side.

Licensing, competitors, and when to wait

SoduWork is not a model provider. You bring API keys for whichever catalog models you enable, similar to OpenRouter-style routing except the router is your issue assignee field plus plugin workflow. If you only need a single harness on one laptop, starting with Pi or Codex alone remains simpler—SoduWork pays off when two people or two harnesses must agree on the same definition of done.

The README compares itself to low-code agent builders (canvas wiring), raw coding harnesses (no sign-off), multi-agent orchestrators (agent-to-agent autonomy), and AI office assistants (history locked per user). None of those rows claim SoduWork wins on every axis; the bet is governance plus reuse on top of harnesses you already like.

For regulated teams, the audit record—who asked, who ran which plugin, which model, who approved—is the feature that survives a security review better than “we pasted logs into Slack.” Pair Hub grants with MCP tool allow lists so agents cannot silently attach new connectors mid-run.

Roadmap and community

The README roadmap (November 2026) marks cloud runner (Personal Agent) support as shipped, with plugin SDKs, runner sandbox management, and web/mobile clients in progress. Community links point to Discord and GitHub issues.

What to try this week

  1. Self-host with SQLite via start.sh and run one request end-to-end: criteria, Pi implementation, second harness review, sign-off.
  2. Publish a tiny plugin from a chat you already trust—weekly summary, ticket triage, or doc refresh—and grant it only to your user first.
  3. Point Connection at your Hub on installed clients so update and accounting traffic stays on infrastructure you control.
  4. Read runner limits before attaching a cloud runner with sensitive repositories—match harness choice to Agent Client Protocol hardening you already use locally.

Related reading

  • Tencent LoopForge SOP orchestration
  • Agent Autoloop background hub
  • CLI-Anything: agent-native CLIs
  • External sandboxes for coding agents
  • What are agent skills?
  • CowAgent harness comparison

Facts follow the SoduWork README and GitHub API star counts as of November 18, 2026.

Spotted something out of date? Let us know.
Daily briefFrom Yash · 350K+ students taught

Catch up on AI

One AI story explained in plain English, plus one thing to try. Every day, free. Unsubscribe anytime.

  • ✓ Free
  • ✓ One email a day, no spam
  • ✓ Unsubscribe anytime
Yash Thakker

Written by

Yash Thakker

Yash is an AI expert with over 300K learners. Join his workshops →

View Yash Thakker in People in AI →

Related posts

Nov 18, 2026

Self-Improvement Memory: Google’s CRSI Harness Optimization Paper

When you evolve an agent harness on one model and move to another, inherited edits may help or hurt. Google’s Self-Improvement Memory records why each harness change was made so optimization can continue instead of restarting blind.

Nov 16, 2026

ffmpeg-skill: Local Video Editing MCP for Claude Code, Cursor and Codex

ffmpeg-skill teaches coding agents a probe-edit-verify workflow with 42 Python FFmpeg tools and an MCP server. It runs offline with no API keys and trended past 6,000 GitHub stars in November 2026.

Nov 16, 2026

Qwen Code: Open-Source Terminal Coding Agent From Alibaba's QwenLM

Qwen Code is an open-source agent harness from QwenLM with terminal, desktop, web, and chat integrations. The repo crossed 30,000 GitHub stars this week with Agent Teams, Auto-Memory, and multi-provider routing.