Agent harness vs agent framework: which layer to build on

A framework gives a team building blocks to write the agent; a harness arrives as a finished agent with tools, prompts and subagents. LangChain adds a third layer, the runtime. On every route the tool list, approval rule and log stay with the team, and each route fails in a different place, shown on the Cisco ISE patch check of 16 Sep 2026.

Three layers and what each is for

LangChain's Runtimes, frameworks, and harnesses page separates three layers and says when to use each. The word harness itself is defined on what an agent harness is.

LangChain, which maintains products in all three columns, read 19 Nov 2026. Option names are the page's own list.
LayerWhat it adds, per LangChainWhen to use it, per LangChainOptions the page names
RuntimeDurable execution, streaming, human-in-the-loop, persistenceLow-level control; long-running, stateful workflows and agentsLangGraph, Temporal, Inngest
FrameworkAbstractions, integrationsGetting started quickly; standardizing how a team buildsLangChain, Vercel's AI SDK, CrewAI, OpenAI Agents SDK, Google ADK, LlamaIndex
HarnessPredefined tools, prompts, subagentsMore autonomous agents; agents faced with complex, non-deterministic tasksDeep Agents SDK, Claude Agent SDK, Manus

One job, four routes: the Cisco ISE patch check

The job is narrow. When Cisco published advisory cisco-sa-ISE-ABP-VNSW7Tn5 on 16 Sep 2026, CVE-2026-76460 (an unauthenticated API authentication bypass in Cisco ISE, CVSS 10.0, added to CISA's KEV catalog the same day) named one first fixed patch per release train: 3.1 Patch 12, 3.2 Patch 11, 3.3 Patch 12, 3.4 Patch 7 and 3.5 Patch 4. The agent must read the advisory, read the version of each ISE node, say which nodes are below the fixed patch, and post that as a comment on the ticket. Three tools cover it: two that only read and one that writes the comment.

Take a six-node estate (constructed for this example). Two nodes run 3.2 Patch 8, so each needs Patch 11. One runs 3.3 Patch 12, which is the fixed patch. Two run 3.4 Patch 5, so each needs Patch 7. One runs 3.5 Patch 4, which is the fixed patch. The right comment names four of six nodes. Whatever route builds the agent, that is the result to test it against.

Quotations are from OpenAI's Agents SDK pages and Anthropic's Agent SDK pages, read 19 Nov 2026. The "what your team writes" column is this site's reading of the job above, not a test of the products.
RouteWho writes the loopWhat your team writes for this jobThe setting that gates the one write
Model API directly (OpenAI Responses API, Claude Client SDK)You. OpenAI: use it when you "want to own the loop, tool dispatch, and state handling yourself"; Anthropic: "you write the tool loop yourself"The loop, the three tools, the version comparison, the stop rule, the trace storeYour own code: a check that the comment tool is the only write, and a prompt to a person before it runs
Framework (OpenAI Agents SDK)The SDK. OpenAI recommends it when you "want the runtime to manage turns, tool execution, guardrails, handoffs, or sessions"Instructions and three function tools; the SDK runs the turnsMark the comment tool as needing approval. The SDK's human-in-the-loop flow then pauses the run and returns the pending call in interruptions
Harness (Claude Agent SDK)The harness, which ships Claude Code's built-in tools: read, write and edit files, run commands, search the webMostly subtraction: allow only the two read tools and the comment tool, deny the restAllow rules and disallowed_tools. A deny rule blocks a call even in bypassPermissions mode, and in dontAsk mode anything not allowed is denied, not asked
Hosted harness (Claude Managed Agents)Anthropic, in a sandbox it manages or one you hostThe tool definitions, which systems the sandbox may reach, who may open a sessionThe tool definitions you attach and what the sandbox can reach are yours; the pause-and-approve mechanism is the supplier's, so get it in writing (see supplier controls)

The cost moves rather than disappearing. On the API route the team writes about everything and sees everything. On the harness route it writes little, but the agent arrives able to edit files and run commands that a patch check never needs, so the work is removing capabilities and then proving they are gone. The tools and permissions page covers that least-privilege step, and approvals and checkpoints covers who answers when a run pauses.

What to test on each route, and how each fails

Every route gets the same first test: give it the six-node estate and require a comment that names the four nodes below their fixed patch, and no others. Add a seventh node on ISE 3.0, which Cisco's advisory says has reached end of software maintenance: the right comment tells the owner to migrate, not to apply a patch. The tests that differ are in the table.

Tests for the Cisco ISE job on each route. Quotations from OpenAI's and Anthropic's documentation, read 19 Nov 2026; the tests are this site's.
RouteSecond testHow it failsSource
Model API directlyLeave the approval prompt unanswered for a day, restart the process, then answer it. Expect one comment, posted onceThe pause lives in your code. If the pending call and transcript are not stored, the restart loses the question or repeats itOpenAI: you "own the loop, tool dispatch, and state handling yourself"
Framework (OpenAI Agents SDK)Pause on the comment tool, stop the process, rebuild the run from the stored state, approve. Expect one commentThe pending approval exists only if the run state was stored with to_json() or to_string(). If the process stops after the tool ran but before the new state was saved, resuming from the older snapshot can post the comment twice: "Approval permits a tool call to execute; it does not guarantee exactly-once execution"OpenAI Agents SDK, Human-in-the-loop, Long-running approvals and Recovering after a crash
Harness (Claude Agent SDK)Ask the agent to edit a file and to run a shell command during the check. Expect both deniedAn allow list does not remove tools: "Any other tool not listed in allowed_tools is still available to Claude", and allowed_tools "does not constrain bypassPermissions". A built-in left enabled is hidden only by adding its bare name to disallowedToolsAnthropic, Agent SDK, Configure permissions
Hosted harness (Claude Managed Agents)From a session, list which hosts the sandbox reaches. Expect the ISE inventory and the ticket system onlyThe tool definitions and sandbox reach are yours to test. How a pause behaves when the supplier restarts a session is the supplier's, so ask for it in writing before the comment tool is attachedSupplier controls

The fix for the duplicate comment is the same on every route: give the write an idempotency key, here the run ID plus the advisory ID, and have the comment tool refuse a second comment that carries it. OpenAI's page recommends a stable key per logical action for exactly this reason.

When the raw API is the wrong route

Anthropic's essay suggests starting with the model API directly, since "many patterns can be implemented in a few lines of code". For the ISE job the loop is that short. The route turns wrong when the approver answers hours later: the pause then has to survive restarts, and storing the pending call, resuming it and preventing a double post are yours to write and test. The framework route ships serializable run state for that; the harness route ships permission rules but, for this job, mostly adds tools to remove.

When the layer labels mislead

Vendors do not use the three words the same way, so a label is a poor basis for a purchase.

  • LangChain lists the OpenAI Agents SDK as a framework. OpenAI's own page says the SDK "wraps model calls in a higher-level runtime" and lets you choose it when you want the runtime to manage turns, tool execution and guardrails.
  • LangChain lists the Claude Agent SDK as a harness. Anthropic's overview describes it as "A library that runs the Claude Code binary" and reserves the phrase "hosted agent harness" for Managed Agents.
  • Anthropic's older essay Building effective agents warns that frameworks "often create extra layers of abstraction that can obscure the underlying prompts and responses, making them harder to debug". That cost applies to every layer above the raw API.

Ask three questions of any product instead: who runs the loop, which tools exist before you add any, and where a run pauses for a person. Those map to the route table above. The answers also decide what you re-test when the supplier ships a new version, since an evaluation on your own findings tests the harness and the model together. For the money side of owning more of the stack, see build vs buy; for the thinnest harness that does one security job, see how to build an agent harness.

Sources

  1. LangChain docs, Runtimes, frameworks, and harnesses, read 19 Nov 2026
  2. OpenAI Agents SDK documentation, home page (Agents SDK or Responses API?), read 19 Nov 2026
  3. OpenAI Agents SDK documentation, Human-in-the-loop, read 19 Nov 2026
  4. Anthropic, Agent SDK overview, read 19 Nov 2026
  5. Anthropic, Agent SDK, Configure permissions, read 19 Nov 2026
  6. Anthropic, Building effective agents, When and how to use frameworks, read 19 Nov 2026
  7. Cisco advisory cisco-sa-ISE-ABP-VNSW7Tn5 (fixed patches per train), read 19 Nov 2026
  8. CISA KEV catalog entry for CVE-2026-76460, read 19 Nov 2026

Last reviewed 19 Nov 2026