Microsoft Agent Framework (MAF) plugin for DeepSeek Harness: validate, run, and scaffold declarative agents and workflows (YAML).
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:WODE25500/dsh-maf
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
Microsoft Agent Framework (MAF) integration for DeepSeek Harness (dsh) — let the dsh agent validate, run and scaffold MAF declarative agents/workflows defined in YAML.
Independent community project, not official. Based on microsoft/agent-framework (MIT). MAF is the enterprise successor to Semantic Kernel (v1.0 released).
Why
MAF (13k★, Python/.NET) is Microsoft's current agent orchestration framework with no DSH adaptation yet. Its core is YAML declarative agents/workflows — a natural fit for agents to generate, validate and run:
| Tool | Behavior |
|---|---|
maf_status |
MAF package versions + env check |
maf_validate |
validate declarative agent YAML (AgentFactory parse) |
maf_run_agent |
run a declarative agent (YAML + prompt) |
maf_run_workflow |
run a declarative workflow sample (main.py) |
maf_scaffold |
scaffold agent/workflow YAML templates |
Prerequisites
pip install agent-framework agent-framework-declarative python-dotenv
Agent YAML model.id often references env vars (=Env.OPENAI_CHAT_MODEL_ID);
configure .env / environment (provider keys) before running.
Install
# in a profile's cordis.patch.yml
- insert:
- id: maf
name: './src/index.js'
config:
pythonCmd: python
enginePath: scripts/maf.py
pnpm dsh web --patch ./dsh-maf/cordis.patch.yml
Then ask the agent: "Use maf_status to check the env and maf_validate to check ./agents/Assistant.yaml."
Engine
scripts/maf.py wraps the MAF SDK:
AgentFactory(safe_mode=False).create_agent_from_yaml_path(path)→await agent.run(prompt)- workflows use the standard sample layout (
workflow.yaml+main.py→python main.py)
Config
| Key | Default | Purpose |
|---|---|---|
pythonCmd |
python |
Python interpreter |
enginePath |
scripts/maf.py |
engine script path |
timeoutMs |
180000 |
per-call timeout |
Known limitations
maf_run_agent/maf_run_workflowconsume the configured provider quota- The declarative agents API is officially marked experimental (may change)
- Output is returned verbatim (may contain model-generated content)
Layout
dsh-maf/
src/index.js # 5 tools + config
scripts/maf.py # MAF SDK engine (status/validate/run/scaffold)
skills/maf/SKILL.md
docs/
cordis.patch.yml
License
MIT.
Links
More in this category
yjh051108/dsh-routing-suite★ 7022
One repository, three parts: a runtime injector for DSH plugin packages (inject, hot-reload, unload, promote a dev staging tool to the front, route self-heal, plus a settings-page plugin manager that lists, unloads and drags folders in to internalize), a task-aware reasoning-mode router agent preset (router-standard / router-spec / router-react), and a graded two-level task protocol whose six tools (commit_star, lock_stage, revise_do, edit_plan, mark_task, redteam_verdict) pin task state to disk. The injector implementation ships in-tree, so the install carries its own behaviour rather than a dependency list.
strukto-ai/mirage#dsh★ 3691
Swaps the filesystem and bash providers for a mirage virtual workspace: file tools and shell commands run over mounted resources (RAM, S3, Redis, Slack, Gmail, Notion, Postgres) instead of the host disk, with per-mount read/write/exec modes, per-command sandbox routing (monty, pyodide, quickjs in process; docker, e2b, daytona remote), and installed CLIs (git, gh, slack, linear, ntn, gws, or one you register) as head words in the virtual terminal.
hust-open-atom-club/oh-dsh★ 322
Community distribution: TUI, desktop, and Web UI as one bundle with layered installation.
weijiafu14/pi2dsh★ 216
Pi Host ABI compatibility engine: after one install, unmodified Pi extensions from npm mount as native DSH plugins with `dsh plugin add <pi-package>`. Verified end to end on stock DSH with pi-mcp-adapter (full MCP manager: OAuth, resources, prompts, MCP Apps, elicitation, sampling), @tintinweb/pi-subagents, pi-code, pi-hermes-memory and pi-background-tasks; `pi2dsh inspect` reports a package's compatibility before installing.
Fishquito7/dsh-skill-mcp-panel★ 202
Manages DSH skills and MCP servers from the web settings: skill cards with hot enable/disable, workspace scopes, groups, batch migration and drag-and-drop import, plus stdio/HTTP MCP CRUD with connection tests, secret redaction and the unified dsh-panel CLI.
lire1131/dsh-undo-savepoint★ 181
Undo/redo & rollback system for DSH: every config change is auto-snapshotted; undo/redo/restore to any version from the WebUI or the offline CLI/GUI tools (works even when DSH fails to boot).
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.