Hardcore Reviews
Hardcore Reviews

Agent Harness Compared: DeepSeek Harness vs Claude Code vs OpenCode vs Codex - How to Choose Among the Big Four Coding Agents

A four-way coding-agent harness comparison: DeepSeek Harness (101,905★ MIT, everything-is-a-plugin composable foundation) vs Claude Code (141,500★ out-of-box productivity) vs OpenCode (197,583★ model-agnostic daily driver) vs Codex CLI (106,006★ OpenAI ecosystem). Two tables, best-range-per-tool, layered selection, 5 FAQs. Representative comparison, not a hands-on benchmark; stars are API snapshots; per official sources.

Published August 15, 20269 min read
<!-- agent-harness-comparison-review | review | Agent Harness Compared: DeepSeek Harness vs Claude Code vs OpenCode vs Codex - How to Choose Among the Big Four Coding Agents -->

DeepSeek Harness hit 100K stars in two days, turning "agent harness" from testing jargon into a category: the execution scaffolding wrapped around models is becoming a selection criterion alongside the models themselves. This piece puts the four most notable contenders on one table: DeepSeek Harness (dsh), Anthropic Claude Code, OpenCode, and OpenAI Codex CLI. Verdict first: this is not a one-of-four substitution - there are three distinct needs (out-of-box productivity, model-agnostic daily use, hackable foundation), each with its own best answer.

Boundaries: a representative comparison based on official repos and docs (as of 2026-08-15), not a benchmark under identical conditions; star counts are GitHub API snapshots; features move fast - official docs are authoritative. Background in the Harness hotspot; using DeepSeek models with Claude Code is covered in the DeepSeek × Claude Code SOP.

1. The Overall Table

DimensionDeepSeek Harness (dsh)Claude CodeOpenCodeCodex CLI
PositioningComposable agent runtime (foundation)Terminal coding agent (product)Terminal coding agent (open daily use)Terminal coding agent (OpenAI official)
GitHub stars101,905 (two days old)141,500197,583106,006
LanguageTypeScriptPython (CLI distribution)TypeScriptRust
LicenseMITRepo open, service closedOpen sourceApache-2.0 (CLI)
Model bindingNone (model is a plugin)Claude family (swappable via compat layer)None (multi-provider)OpenAI family mostly
Extension modelEverything is a plugin (kernel to UI swappable)Skills/MCP (edge extension)Plugins/provider configLimited config
ObservabilityAppend-only trajectory: resume/fork/replaySession logsTUI session managementSession logs
InterfaceLocal Web UI (127.0.0.1:3080)Native terminalTerminal TUINative terminal
Maturityv0.1 developer preview (breaking-change warning)Commercial matureCommunity matureCommercial mature

On the snapshots: OpenCode's 197K stars are the highest stock (long-accumulated community project); dsh's 100K in two days is a speed record of hype, not a stock comparison; Claude Code and Codex stars include brand effects - real capability per official docs.

2. Best Range, One by One

DeepSeek Harness: the foundation for people who modify agents. It wins on "decomposability": model, tools, sandbox, loop, orchestration, UI are all Cordis plugins - swap any layer without forking; Minimal mode is the environment for official model benchmarks, directly reusable for evaluation. It loses on maturity: v0.1 preview, breaking-change warnings, ~300 unreviewed plugins, spartan UI. Verdict: for builders, researchers, and teams wanting a self-hosted fully open stack (MIT weights + MIT runtime); not for people who just need to get work done today.

Claude Code: the out-of-box productivity ceiling. Native terminal experience, the most mature task orchestration and skills ecosystem, plus Claude-family long-task reliability - the representative of "pay for certainty." Costs: deep binding to Anthropic models and subscription; using cheaper DeepSeek models requires the Anthropic-compatible layer (we have an SOP). Verdict: teams and heavy users with budget who want maximum completion rates.

OpenCode: the model-agnostic open-source daily driver. 197K stars, TypeScript, multi-provider plug-and-play, the highest community stock of the four. It and dsh are both open source but on different roads: OpenCode is "a better coding agent product"; dsh is "a runtime any agent can grow out of." Verdict: if you refuse vendor lock-in and want a stable usable open terminal agent, this is it.

Codex CLI: the OpenAI-ecosystem default. Rust implementation, Apache-2.0, deep synergy with OpenAI models and cloud sandbox. If your workflow already lives inside the ChatGPT/Codex subscription ecosystem, it's the smoothest line; cross-vendor flexibility is the weakest of the four. Verdict: the default answer for OpenAI subscribers.

3. Layered Selection and Combinations

Your needPickCombination tip
Max productivity today, budget no objectClaude CodePair with skills to bank team assets
Open-source daily use, multi-model cost savingOpenCodeDeepSeek-V4 as workhorse, Claude for hard problems
Building/modifying your own agent, or self-hosting fully openDeepSeek HarnessMIT weights + dsh runtime, end-to-end no proprietary dependency
Already in the OpenAI ecosystemCodex CLIWith Codex cloud sandbox

A three-layer lens makes the rivalry clearer: the model layer is commoditizing (replaceable), and the moat migrates to "the infrastructure that runs the models"; dsh turns the orchestration paradigm into composable blocks, but the paradigm itself (loop, tools, trajectory) doesn't break new ground; for ordinary developers the realistic future is multiple harnesses coexisting - work in Claude Code, save money with OpenCode, watch dsh grow up.

FAQ

Q1: Which of the four is "strongest"? A1: No single answer. For out-of-box productivity and task completion, Claude Code is the most commercially mature; for open-source stock and model-agnostic daily use, OpenCode (197,583★) is the steadiest; for architectural composability and a self-hosted open stack, dsh is the boldest; for OpenAI ecosystem synergy, Codex is the smoothest. "Strongest" depends on whether you are a user, a saver, a builder, or an ecosystem subscriber.

Q2: Can DeepSeek Harness replace Claude Code? A2: Not in the short term. dsh is a v0.1 developer preview (official breaking-change warning), unreviewed plugins, spartan UI, deployment friction. Its rival is not Claude Code's present but the "composable agent runtime" category's future. To save money with DeepSeek models on a mature harness today, OpenCode or Claude Code + compatibility layer is steadier.

Q3: Why is dsh's "everything is a plugin" different from ordinary plugin systems? A3: Ordinary tools (including Claude Code/OpenCode/Codex) extend at the periphery - add tools, connect MCP, install skills - while the kernel loop, orchestration, and UI are welded shut. dsh is built on the Cordis meta-framework where models/tools/skills/sessions/sandbox/storage/loop/orchestration/UI are all plugins; replacing any layer requires no framework-source changes - that's the difference between "edge extensibility" and "whole-system composability."

Q4: OpenCode and DeepSeek Harness are both open source - how to choose? A4: Decide whether you want a product or a foundation. OpenCode is a polished terminal coding agent - install and use, multi-provider switching, "daily driver" positioning. dsh is a runtime foundation - its value is decomposability and researchability (Minimal mode for model evaluation, Creator mode for plugin experiments), "builder" positioning. Most developers should pick OpenCode today and re-evaluate dsh when its API stabilizes.

Q5: Does harness choice affect how to read model benchmark scores? A5: Yes, enormously. DeepSeek officially runs its Code Agent benchmarks in Harness Minimal mode (just bash + file editing) - the same model can differ by a tier in production depending on harness and tooling scaffolding. Whenever you see "XX model #1 at coding," ask first: measured in which harness, which mode?


References

  • GitHub API snapshots (2026-08-15): deepseek-ai/deepseek-harness 101,905★/MIT/TypeScript; anthropics/claude-code 141,500★; anomalyco/opencode 197,583★/TypeScript; openai/codex 106,006★/Rust
  • DeepSeek official: Harness launch page (everything is a plugin, four modes, Minimal & benchmarks)
  • NetEase Tech / Eigent AI / AI Reading Hub (InfoQ): dsh launch coverage and analysis (2026-08-13/14)
  • Official docs of each project: Claude Code, OpenCode, Codex CLI features and licenses

A representative comparison (2026-08-15), not a hands-on benchmark; stars and features per official sources. Related: Harness hotspot | Harness quickstart SOP | DeepSeek × Claude Code SOP | Frontier coding model comparison

This article is AI-assisted and human-edited. Last updated: 2026-08-15

FAQ

Which of the four is "strongest"?
No single answer. For out-of-box productivity and task completion, Claude Code is the most commercially mature; for open-source stock and model-agnostic daily use, OpenCode (197,583★) is the steadiest; for architectural composability and a self-hosted open stack, dsh is the boldest; for OpenAI ecosystem synergy, Codex is the smoothest. "Strongest" depends on whether you are a user, a saver, a builder, or an ecosystem subscriber.
Can DeepSeek Harness replace Claude Code?
Not in the short term. dsh is a v0.1 developer preview (official breaking-change warning), unreviewed plugins, spartan UI, deployment friction. Its rival is not Claude Code's present but the "composable agent runtime" category's future. To save money with DeepSeek models on a mature harness today, OpenCode or Claude Code + compatibility layer is steadier.
Why is dsh's "everything is a plugin" different from ordinary plugin systems?
Ordinary tools (including Claude Code/OpenCode/Codex) extend at the periphery - add tools, connect MCP, install skills - while the kernel loop, orchestration, and UI are welded shut. dsh is built on the Cordis meta-framework where models/tools/skills/sessions/sandbox/storage/loop/orchestration/UI are all plugins; replacing any layer requires no framework-source changes - that's the difference between "edge extensibility" and "whole-system composability."
OpenCode and DeepSeek Harness are both open source - how to choose?
Decide whether you want a product or a foundation. OpenCode is a polished terminal coding agent - install and use, multi-provider switching, "daily driver" positioning. dsh is a runtime foundation - its value is decomposability and researchability (Minimal mode for model evaluation, Creator mode for plugin experiments), "builder" positioning. Most developers should pick OpenCode today and re-evaluate dsh when its API stabilizes.
Does harness choice affect how to read model benchmark scores?
Yes, enormously. DeepSeek officially runs its Code Agent benchmarks in Harness Minimal mode (just bash + file editing) - the same model can differ by a tier in production depending on harness and tooling scaffolding. Whenever you see "XX model #1 at coding," ask first: measured in which harness, which mode?

Related

Hardcore Reviews

Testing DeepSeek-V4-Flash Official Release with Codex: A 30-Question Hardcore Benchmark

Built a pure-standard-library benchmark harness with Codex, then made real API calls to DeepSeek-V4-Flash (0731 official) at 2026-08-02 10:51 to run 30 self-built questions. Result: 30/30 correct, 59/59 coding test cases passed, 30-question cost under 5 fen, ~3s average latency, 84% reasoning tokens. Includes the official 9-benchmark comparison and a price showdown (V4-Flash output ~1/90 of Opus 4.8). A hands-on benchmark with reproducible, auditable raw data, including limitations and known weaknesses.

Aug 2, 20267 min read