Agents-OSS
EN
Submit

deepseek-harness vs OpenAI Agents SDK

Both are catalogued under Agent Frameworks. The figures come from the GitHub API; the assessments are ours.

deepseek-harnessDeepSeek AI's own agent harness: everything is a plugin, run behind a local Web UI on the Cordis runtime.OfficialMITOpenAI Agents SDKA deliberately small agent framework from OpenAIOfficialMIT

At a glance

At a glancedeepseek-harnessOpenAI Agents SDK
LicenseMITMIT
LanguagesTypeScriptPython
DeploymentSelf-hosted / Runs locallySelf-hosted / Runs locally
MaturityGrowingGrowing
Stars116k28.7k
Star growth over the last 7 days—+8 ★
Forks11.4k4.5k
Open issues016
Last commit13 Aug 202616 Aug 2026
ActivityActiveActive

What each one does

deepseek-harness

`dsh` is the agent harness DeepSeek AI develops itself. `npx @deepseek-ai/dsh web` brings up a Web UI on `http://127.0.0.1:3080`, and the architecture behind it is one where everything is a plugin, powered by the Cordis runtime, so it suits people who intend to extend a harness rather than only operate one. The caveat comes from the project itself: it is labelled a developer preview and warns in capitals that there will be compatibility-breaking changes, so plugins written today should budget for rework. It is also a poor fit if you want a documented scripted or embedded entry point right now, since the README covers only the `web` command and a source checkout, and links out to a development guide and architecture documentation without saying what either contains.

Full entry →

OpenAI Agents SDK

Few primitives — agents, handoffs, guardrails, tracing — and little else. The small surface area is the appeal: there is not much to learn and not much to fight. It is built around OpenAI's own models first, so weigh that if multi-provider portability matters to you.

Full entry →

What you can do

deepseek-harness

  • Get a Web UI running from one command — With Node.js installed, npx @deepseek-ai/dsh web starts the harness and serves its Web UI at http://127.0.0.1:3080 by default.
  • Build on the plugin architecture — The harness is powered by the Cordis runtime under an everything-is-a-plugin architecture; the README's Development section points at a development guide (docs/development.md) and architecture documentation (docs/architecture.md).
  • Make your plugin discoverable — Adding the dsh-plugin GitHub topic to a plugin repository is the route the README gives for discoverability, with feedback and bug reports going through GitHub Discussions or the project's Discord.
  • Run and modify the harness from source — Clone the repo, then pnpm install, pnpm run build and pnpm dsh web to launch your own checkout instead of the published package.
  • Hand the repo to a coding agent — The README directs agents working in this codebase to follow AGENTS.md at the repo root.

OpenAI Agents SDK

  • Delegate between specialist agents — Handoffs and agents-as-tools let one Agent pass work to another, and Runner.run_sync executes the whole chain and returns final_output.
  • Give an agent a workspace — SandboxAgent takes a Manifest of entries such as GitRepo and runs commands, inspects files and applies patches through UnixLocalSandboxClient, or DockerSandboxClient on Windows.
  • Build voice agents two ways — RealtimeAgent holds a WebSocket session with gpt-realtime-2.1, while VoicePipeline chains speech-to-text, an agent workflow and text-to-speech from the optional voice extra.
  • Point it at models other than OpenAI's — The README calls the SDK provider-agnostic across the OpenAI Responses and Chat Completions APIs plus 100+ other LLMs, though every quickstart example still expects OPENAI_API_KEY in the environment.
  • Trace and resume conversations — Tracing is built in for viewing and debugging runs, and Sessions carries conversation history across separate Runner invocations without manual bookkeeping.

Other comparisons