{ "data": { "a": { "slug": "deepseek-superagent", "name": "dsh-superagent (DeepSeek)", "vendor": "DeepSeek", "vendorUrl": "https://github.com/deepseek-ai/dsh-superagent-prototype", "kind": "harness", "category": "agent-harnesses", "summary": "dsh-superagent is DeepSeek's MIT-licensed research prototype of a proactive coding agent for one GitHub repository, run as a DeepSeek Harness bundle. A main Session admits requests from allowed people and parallel Executor Sessions work them into pull requests.", "url": "https://www.anchorterminal.com/tools/deepseek-superagent", "markdownUrl": "https://www.anchorterminal.com/tools/deepseek-superagent.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/deepseek-superagent.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/deepseek-superagent.json", "dns": "deepseek-superagent.grade.anchorterminal.com", "repo": "https://github.com/deepseek-ai/dsh-superagent-prototype", "license": "MIT", "transports": [], "packages": [], "auth": "pat", "authNotes": "No account with the project. The agent acts through a dedicated GitHub user account signed in to a `gh` wrapper with `auth login`, and optionally a Feishu bot through `lark-cli`. DSH needs a model provider key. The local Management API takes no credential and accepts only loopback requests with `x-orchestrator-request: 1`.", "pricing": "free", "pricingNotes": "Free and MIT, with nothing to buy. The operator pays the model provider DSH is set up with, usually DeepSeek's API, for a main Session and one Session per Ticket.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, SETUP.md or docs/000 to 008 (checked 2026-11-01).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-01" }, "docsUrl": "https://github.com/deepseek-ai/dsh-superagent-prototype/tree/main/docs", "capabilities": [ "agent.harness", "agent.multi-agent" ], "tags": [ "official", "harness", "coding-agent", "open-source", "mit", "typescript", "local", "free", "no-card", "pre-1.0", "preview", "telemetry-default-on" ], "lastRelease": "2026-10-31", "graded": true, "anchor": { "graded": true, "score": 42.1, "grade": "E", "agentReady": false, "rank": 1108, "ranked": true, "rankOf": 1251, "categoryRank": 41, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 34, "payments": 40, "reliability": 15, "schema": 61, "security": 33, "transparency": 52 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "The authorization design is careful, with allowed lists, Mandates and a Policy enforced in code, proactive work only recorded by default and auto-merge off. Executors run every command without approval under the operator's OS user, and the README calls it a research prototype with no release, changelog or security policy.", "bestFor": "Teams on github.com that want a DeepSeek Harness agent to turn allowed people's issue requests into pull requests, run on an isolated machine or OS account.", "strengths": [ "MIT licence, with nine numbered design and operations documents that state each rule, from admission to restart recovery", "Only listed GitHub logins can start work by default, and messages, comments and prompts cannot change the gate, which code enforces", "Proactive work starts in `observe` mode, which records what the agent would have done and accepts nothing", "The agent never enables auto-merge as its own account, and the default merge rule needs approvals and fewer than 200 changed lines", "Setup and worker shells drop environment variables named KEY, PASSWORD, SECRET or TOKEN, and git uses only the agent account's credentials" ], "weaknesses": [ "Executor and main Sessions run with `danger-full-access` as the operator's OS user, and the docs say a worker can read the operator's home directory", "The README calls it a research prototype, not an official DeepSeek product, at version 0.1.0 with no tag, release or changelog found", "Not on npm. Installing means a git clone, `pnpm build`, a pinned DSH release candidate, tmux and a dedicated GitHub user account", "The docs don't mention that DSH's shipped profiles upload the session log to DeepSeek with official API requests by default", "No SECURITY.md, security.txt or CI workflow found, and GitHub's issues and pull requests couldn't be read" ], "agentNotes": [ "Run it under a dedicated OS account holding only the agent's credentials. Executors run commands without approval and can read the operator's home directory", "Set `enabled: false` on the `session-log-deepseek` row of the `superagent` profile before using DeepSeek's official API on private code", "Keep the accept mode at `observe` and the allowed list short until the recorded Decisions look right", "Wait for `scripts/dsh-superagent status` to stop exiting 1 after any save that answers `restarting: true` before the next request", "Send `x-orchestrator-request: 1` and a loopback Host to the Management API, and send `revision` with each PUT, since a stale one gets 409" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 42.1 } ], "editorialScores": { "ergonomics": 67, "maintenance": 34, "payments": 40, "reliability": 15, "schema": 61, "security": 33, "transparency": 51 }, "provenanceScore": 52, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install -g @deepseek-ai/dsh@0.2.1-rc.3 \u0026\u0026 git clone https://github.com/deepseek-ai/dsh-superagent-prototype dsh-superagent \u0026\u0026 cd dsh-superagent \u0026\u0026 pnpm install \u0026\u0026 pnpm build \u0026\u0026 dsh superagent --from-default-profile web --dump-config \u003e /dev/null \u0026\u0026 dsh plugin --profile superagent add \"link:$PWD\"" }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/deepseek-superagent" }, "sameCompany": [ "deepseek-harness" ], "area": "frameworks", "provenance": { "legalEntity": "DeepSeek (the LICENSE names the DeepSeek Harness Team; DeepSeek Harness's terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)", "domain": "github.com", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "https://www.deepseek.com/en/harness/privacy/", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-01", "notes": [ "The repository has no terms or privacy policy of its own. DeepSeek Harness's terms of use and privacy policy (both last updated 20 September 2026) name Hangzhou DeepSeek Artificial Intelligence Co., Ltd. and cover the harness it runs on. The README says the prototype is not an official DeepSeek product.", "package.json names `DeepSeek Harness Team \u003cteam@dsh.dev\u003e` as author. dsh.dev didn't resolve from our network on 1 November 2026.", "No SECURITY.md in the root or .github, and www.deepseek.com/.well-known/security.txt returned 404 on 1 November 2026.", "No CHANGELOG.md, tags or releases found. GitHub's web pages and API weren't reachable, so files were read on raw.githubusercontent.com and the commit history, stars and issues are unchecked." ], "score": 52 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/deepseek-superagent.json" }, "answer": "dsh-superagent (DeepSeek) and Harness² score within a point of each other on agent readiness, 42.1 (E) and 42 (E). Harness² leads on reliability and security \u0026 auth.", "b": { "slug": "harness2", "name": "Harness²", "vendor": "Google (Google Research)", "vendorUrl": "https://harness2.github.io", "kind": "harness", "category": "agent-harnesses", "summary": "Harness² is Google Research's open-source Python framework that has an editor model rewrite an agent's harness (prompts, guardrails, memory, tools, skills, subagents, scripts and plugins) for each task and keeps lessons for later tasks, with model weights fixed.", "url": "https://www.anchorterminal.com/tools/harness2", "markdownUrl": "https://www.anchorterminal.com/tools/harness2.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/harness2.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/harness2.json", "dns": "harness2.grade.anchorterminal.com", "repo": "https://github.com/google-research/harness2", "license": "Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).", "transports": [], "packages": [], "auth": "none", "authNotes": "No Harness² account or key. Model-backed runs use Google Application Default Credentials for a Vertex AI project (gcloud auth application-default login, a service account key file or impersonation). The optional Codex bridge generates its own local access key.", "pricing": "free", "pricingNotes": "Free under Apache-2.0, with nothing to buy. Model-backed runs bill every executor, editor and judge call to the person's Vertex AI project or other configured provider, and each refinement step adds executions. The local demo needs no credentials.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, docs or source (checked 2026-10-18). The software has nothing to buy.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 4200, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-18" }, "docsUrl": "https://github.com/google-research/harness2/tree/main/docs", "capabilities": [ "agent.harness" ], "tags": [ "open-source", "apache-2.0", "local", "self-hosted", "free", "python", "cli", "linux" ], "lastRelease": "2026-10-08", "graded": true, "anchor": { "graded": true, "score": 42, "grade": "E", "agentReady": false, "rank": 1109, "ranked": true, "rankOf": 1251, "categoryRank": 42, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 59, "maintenance": 36, "payments": 40, "reliability": 20, "schema": 51, "security": 44, "transparency": 49 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-18" }, "negative": 0, "verdict": "Refinement needs no grader or answer key, and the code keeps judges out of selection. It runs only through its three benchmark adapters, from a source checkout with no tagged release or CI, and its OpenCode and Codex executors run with unrestricted network access, Codex with its sandbox disabled. The benchmark gains are the authors' claims.", "bestFor": "Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI.", "strengths": [ "Refining a harness needs no grader, rubric or answer key. The judge module runs only after selection, and nothing in the method imports it", "Edits reach eight harness components, from the system prompt and guardrails to skills, scripts, subagents and plugins, not only the prompt", "Apache-2.0, with upstream checkouts pinned by commit, a hash list for bundled files and each third-party runner's licence and provenance", "Rerunning a command resumes it, failed grades stay unscored rather than zero, and `--dry-run` previews task selection without model calls", "Each editor session's prompt, response, model and cost are written to an audit folder beside the run" ], "weaknesses": [ "No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI", "The CLI accepts only JobBench, LAB and WorkBuddy-Bench, with no documented way to run it on your own tasks", "Executor network access is unrestricted, Codex runs with approvals and sandbox bypassed, and executors inherit the whole shell environment", "The quick start copies `.env.example`, which the repository doesn't contain, and no .gitignore keeps a filled-in .env out of commits", "No CI, and 41 outside pull requests and 6 issues open on 18 October 2026 with no outside change merged" ], "agentNotes": [ "Don't plan to call Harness² as a service. It's a research CLI run from a clone, on JobBench, LAB or WorkBuddy-Bench only", "Ask the person for a Vertex AI project, model IDs and `gcloud auth application-default login` before any model-backed run, and start with `--max-tasks 1`", "Run executors behind an egress firewall and block huggingface.co and github.com after setup, as the docs advise, so rubrics can't be fetched", "Write .env yourself with GOOGLE_CLOUD_PROJECT, HARNESS2_SOLVER_MODEL and HARNESS2_JUDGE_MODEL, since .env.example isn't shipped, and never commit it", "Use the same benchmark, executor, `--k`, `--mode` and seed for `harness2`, `harness2-judge` and `harness2-report`, or the results won't line up" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 42 } ], "editorialScores": { "ergonomics": 59, "maintenance": 36, "payments": 40, "reliability": 20, "schema": 51, "security": 44, "transparency": 48 }, "provenanceScore": 50, "checked": { "categories": { "ergonomics": "2026-10-18", "maintenance": "2026-10-18", "payments": "2026-10-18", "reliability": "2026-10-18", "schema": "2026-10-18", "security": "2026-10-18", "transparency": "2026-10-18" }, "last": "2026-10-18", "lastMoved": "2026-10-27", "oldest": "2026-10-18", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "git clone https://github.com/google-research/harness2.git \u0026\u0026 cd harness2 \u0026\u0026 uv venv --python 3.12 .venv \u0026\u0026 source .venv/bin/activate \u0026\u0026 uv pip install -e '.[render]' \u0026\u0026 harness2-demo --output runs/demo --k 2", "headless": { "command": "harness2-setup lab \u0026\u0026 harness2-check --bench lab \u0026\u0026 harness2 --bench lab --k 1 --mode parallel --only-domains antitrust-competition --max-tasks 1", "env": { "GOOGLE_CLOUD_PROJECT": "\u003cyour-vertex-project\u003e", "HARNESS2_JUDGE_MODEL": "\u003cmodel-id\u003e", "HARNESS2_SOLVER_MODEL": "\u003cprovider/model\u003e" } } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/harness2" }, "area": "frameworks", "provenance": { "legalEntity": "Google LLC", "domain": "harness2.github.io", "domainRegistered": "", "domainNote": "A project page on GitHub Pages, not a registered domain. The code is in the google-research organisation on GitHub.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-18", "notes": [ "LICENSE is Apache-2.0, and pyproject.toml and every source file name Google LLC. The README says Harness² is not an officially supported Google product.", "No terms or privacy policy govern the package or the project page. Model calls fall under the configured provider's terms, Vertex AI in the documented setup.", "The repository has no SECURITY.md, and harness2.github.io/.well-known/security.txt returns 404. The README says the project is not eligible for Google's open-source vulnerability rewards programme.", "No changelog, tags or GitHub releases. The version is 0.1.0 in pyproject.toml.", "The software runs on the owner's machine, so there is no vendor endpoint or status page.", "The project page has no robots.txt and carries a noindex, nofollow robots meta tag. It was read once as a public page." ], "score": 50 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/harness2.json", "live": { "slug": "harness2", "githubStars": 21608, "securityTxt": { "url": "https://harness2.github.io/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-31T15:39:39.450551792Z" }, "domain": { "domain": "github.io", "checkedAt": "2026-10-25T13:54:29.184658481Z" }, "github": { "repo": "google-research/harness2", "checkedAt": "2026-10-26T07:31:08.941074475Z", "stars": 19838, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-14T02:22:51Z", "openIssues": 28, "openPRs": 104, "issuesOpened90d": 29, "issuesClosed90d": 1, "prsMerged90d": 0, "replies": { "sampled": 25, "unanswered": 24, "medianDays": 0 } }, "updatedAt": "2026-10-31T15:58:19.062758675Z" } }, "edges": [ { "by": 11, "category": "security", "leads": "harness2", "name": "Security \u0026 auth", "reasons": { "a": "Harness reading of the framework checklist, 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. The `superagent` profile is created from DSH's Web template, and DSH documents that shipped profiles mount `session-log-deepseek`, enabled by default, which adds the session log to each official DeepSeek API request, up to 8 MiB. dsh-superagent's docs don't mention it, and its Sessions read issue, pull request and chat text and the repository. Setup and worker shells drop variables named KEY, PASSWORD, SECRET or TOKEN, and `GH_TOKEN` and `GITHUB_TOKEN` are removed from git (8). Both presets run `danger-full-access` without approval as the operator's OS user. docs/006 says the account wrappers don't isolate the process, a worker can run programs by path and read the operator's home directory, and recommends a dedicated OS account. The gate, `observe` default, blocked commands and no auto-merge as the agent account narrow what it does, not what it can do (6). docs/002 says messages, comments and quoted documents are inputs to a decision and can't change allowed lists, rules or Mandates, bots can never make explicit requests, and prompt edits don't change the gate. Workers with full access still read untrusted Thread text, and no further guidance on that was found (7). Decisions are recorded with reasons, Ticket details show the Trigger, Decision, scope and Policy version, the host records the prompt revisions each Session used, and every GitHub message starts with an automated-agent line by default (12). No SECURITY.md (404 at the root and in .github), no security.txt on www.deepseek.com (404), no bug bounty or advisory found. NVD has no record for the prototype. The CVEs against DSH itself are on the deepseek-harness listing (0).", "b": "Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture and network egress, 15 for audit and 20 for the security programme. No telemetry found in the Harness² source, and the WorkBuddy OpenCode configs turn OpenCode's telemetry, auto-update and sharing off. Credentials are Google Application Default Credentials, and the Codex bridge binds 127.0.0.1 by default with a generated key stored with mode 0600. Against that, executors inherit the whole shell environment (the editor channel drops only five Anthropic variables), and no .gitignore keeps a filled-in .env out of commits (20). Codex runs with `--dangerously-bypass-approvals-and-sandbox`, the Claude CLI editor channel with `--dangerously-skip-permissions`, and the WorkBuddy OpenCode preset allows every tool, with only OpenCode's directory fence and WorkBuddy's containers as limits. The README and setup guide say so (4). Executor network access is unrestricted by default. The docs name the hosts to block and report a Codex rollout that fetched its rubric unprompted, but give no guidance on instructions inside task documents (5). Each editor call's prompt, system text, response, model and cost are saved to an audit folder, with trajectories and adopted harnesses under runs/ (13). No SECURITY.md or security.txt and no advisories, and the README says the project is outside Google's open-source vulnerability rewards programme (2). 44 in all." }, "scores": { "a": 33, "b": 44 } }, { "by": 10, "category": "schema", "leads": "deepseek-superagent", "name": "Schema \u0026 documentation", "reasons": { "a": "Framework reading, as for deepseek-harness. No OpenAPI or JSON Schema is published. docs/006 documents the Management API's routes, fields, block shapes and refusals in tables, and the code validates settings with zod (12). Markdown docs in the repository, readable raw, and a SETUP.md written for a coding agent. No llms.txt (5). Nine numbered documents read in order, each stating purpose, limits and what not to do, such as never rerunning the profile-creation command for an upgrade (17). Closed sets for accept mode (`off`, `observe`, `auto`), admission cells, Source states, health states and `listen` (12). A worked curl example, refusals as 400, 404, 409 and 500 with `issues`, `setup` or `code`, a troubleshooting table and status exit codes 0 to 3 (13). package.json says 0.1.0 and pins an `engines.dsh` range, but no changelog or tags were found (2).", "b": "Framework reading. Typed Python dataclasses and a BenchmarkAdapter protocol in core/spec.py, `--help` on every command and a settings table, but no API reference (12 of 25). Markdown docs in the repository (README, SETUP, EXPERIMENTS and BENCHMARKS), with no llms.txt (5 of 10). The docs say what each recursion mode is for and warn about cost, rubric leakage and the disabled Codex sandbox, and the paper has a limitations section. Nothing says how to use it outside the three benchmarks (13 of 20). `--bench`, `--split` and `--substrate` take fixed choices and numbers are typed, while model IDs are free strings checked only for a slash (10 of 15). Every command has a worked example and ConfigError messages name the fix, but the quick start's `cp .env.example .env` fails because the file isn't shipped (8 of 15). Version 0.1.0 with no changelog (3 of 15). 51 in all." }, "scores": { "a": 61, "b": 51 } }, { "by": 8, "category": "ergonomics", "leads": "deepseek-superagent", "name": "Agent ergonomics", "reasons": { "a": "Harness reading, scored on what a team or pipeline driving it has to supply. The worker preset is DSH's `standard` with web fetch, plan mode, questions, scheduling and workflows left out, the main Session can't write files, and tool results over 8,192 characters are pruned (18). A concurrency limit with one extra slot for a person's message, a 5-second foreground shell, a 10-minute prepare limit and 30 minutes for background work after a turn. No cost or turn limit per Ticket was found (12). Ticket stages, health entries per part, Reports of `blocked` or `failed`, API refusals with codes, and three retries with growing backoff on 408, 429, 5xx and dropped connections (17). Saves carry a revision and a stale one gets 409, state and Sessions survive a restart, and a restarted Assignment gets a recovery note to check git and GitHub before repeating any outside action (16). Sensible defaults (observe mode, port 3082, branch prefix `agent/`), but setup needs a dedicated GitHub user account, CLI wrappers, tmux and a profile, and there is no SDK. Work is requested by mentioning the agent account on GitHub or Feishu (4).", "b": "Framework reading, adapted to a harness that a pipeline drives. Results land in run folders, not in the caller's context, and an agent reads task summaries, adopted harnesses and reflection notes from runs/ (12 of 25). `--only-domains`, `--max-tasks` (per domain), `--split-file`, `--workers` and `--dry-run` size a run before any model call (14 of 20). harness2-check tests dependencies, credentials and configuration without a model call, configuration errors name the remedy, and incomplete runs exit nonzero (14 of 20). Rerunning a command resumes it, saved configuration refuses an incompatible resume, failed grades stay unscored, and editor replies are cached by a fingerprint of their inputs (15 of 20). No model has a default, a Vertex AI project and a gcloud sign-in are needed, only three benchmarks are accepted and there's no SDK (4 of 15). 59 in all." }, "scores": { "a": 67, "b": 59 } }, { "by": 5, "category": "reliability", "leads": "harness2", "name": "Reliability", "reasons": { "a": "Local-package reading, since it runs as a DSH bundle on the operator's machine. Not published to npm (`private: true` in package.json, and the registry has no `dsh-superagent`). It installs from a git clone with `pnpm install \u0026\u0026 pnpm build` on top of `@deepseek-ai/dsh@0.2.1-rc.3`, with Node 22.19+ or 24+, git 2.32+, Python 3.8+, tmux and gh 2.48+ stated, so half credit (10). A vitest suite of about 25 spec files is listed in docs/007, and `pnpm check` runs the typecheck, tests and build. Two spec files were read on raw.githubusercontent.com. No CI workflow was found at five common paths under .github/workflows, and the directory couldn't be listed (5). Open issues couldn't be read, because github.com and api.github.com weren't reachable from our network. Unchecked, so scored absent (0). Version 0.1.0 with no tag, release or changelog found, so no semver record (0). A research prototype, not stable (0).", "b": "Local-package reading. Not on PyPI (the release feed for harness2 answers 404). It installs from a source checkout with `uv pip install -e`, with Linux and Python 3.12 stated (the package allows 3.13), plus Node.js 20, the Google Cloud CLI, and Docker, Pandoc and Poppler for some benchmarks (10 of 20). No CI workflow in the repository. tests/test_workflow.py holds five unit tests over the deterministic demo, which needs no credentials (5 of 25). Six issues and 42 pull requests were open on 18 October, the pull requests mostly fixes by their titles, such as the missing .env.example, report failures, seeds lost between refinement and grading, and resume. None is merged and no issue is closed. Issue text and replies couldn't be read (5 of 25). No tags or changelog (0). Version 0.1.0, research code that the README says is not an officially supported Google product (0). 20 in all." }, "scores": { "a": 15, "b": 20 } } ], "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "DeepSeek", "b": "Google (Google Research)", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "Token", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-31", "b": "2026-10-08", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "2026-09-20", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "none", "b": "4.2k stars", "name": "Popularity" }, { "a": "none", "b": "2.5/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "dsh-superagent (DeepSeek) and Harness² score within a point of each other on agent readiness, 42.1 (E) and 42 (E). Harness² leads on reliability and security \u0026 auth.", "question": "Which is better for AI agents, dsh-superagent (DeepSeek) or Harness²?" }, { "answer": "Yes. dsh-superagent (DeepSeek) is open source (MIT). Harness² is open source (Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).).", "question": "Are dsh-superagent (DeepSeek) and Harness² open source?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 61 against 51", "Agent ergonomics, 67 against 59" ], "also": [ "Free to start without a card" ], "goodFor": "Teams on github.com that want a DeepSeek Harness agent to turn allowed people's issue requests into pull requests, run on an isolated machine or OS account.", "slug": "deepseek-superagent", "watchFor": "Executor and main Sessions run with `danger-full-access` as the operator's OS user, and the docs say a worker can read the operator's home directory" }, { "aheadOn": [ "Reliability, 20 against 15", "Security \u0026 auth, 44 against 33" ], "also": [ "No key needed to call it" ], "goodFor": "Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI.", "slug": "harness2", "watchFor": "No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI" } ], "history": { "deepseek-superagent": null, "harness2": [ { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.4, "from": 41.6, "fromGrade": "E", "to": 42, "toGrade": "E" } ] }, "job": { "capability": "agent.harness", "name": "Agent harnesses" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-deepseek-superagent.json", "title": "Agent Zero vs dsh-superagent (DeepSeek)", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-deepseek-superagent" }, { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-harness2.json", "title": "Agent Zero vs Harness²", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-deepseek-superagent.json", "title": "Aider vs dsh-superagent (DeepSeek)", "url": "https://www.anchorterminal.com/compare/aider-vs-deepseek-superagent" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-harness2.json", "title": "Aider vs Harness²", "url": "https://www.anchorterminal.com/compare/aider-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-deepseek-superagent.json", "title": "Amp vs dsh-superagent (DeepSeek)", "url": "https://www.anchorterminal.com/compare/amp-vs-deepseek-superagent" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-harness2.json", "title": "Amp vs Harness²", "url": "https://www.anchorterminal.com/compare/amp-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-deepseek-superagent.json", "title": "Antigravity CLI vs dsh-superagent (DeepSeek)", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-deepseek-superagent" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.json", "title": "Antigravity CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/auggie-vs-deepseek-superagent.json", "title": "Auggie CLI vs dsh-superagent (DeepSeek)", "url": "https://www.anchorterminal.com/compare/auggie-vs-deepseek-superagent" }, { "json": "https://www.anchorterminal.com/compare/auggie-vs-harness2.json", "title": "Auggie CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/auggie-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-deepseek-superagent.json", "title": "Claude Code vs dsh-superagent (DeepSeek)", "url": "https://www.anchorterminal.com/compare/claude-code-vs-deepseek-superagent" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-harness2.json", "title": "Claude Code vs Harness²", "url": "https://www.anchorterminal.com/compare/claude-code-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-deepseek-superagent.json", "title": "Cline vs dsh-superagent (DeepSeek)", "url": "https://www.anchorterminal.com/compare/cline-vs-deepseek-superagent" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-harness2.json", "title": "Cline vs Harness²", "url": "https://www.anchorterminal.com/compare/cline-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-deepseek-superagent.json", "title": "Crush vs dsh-superagent (DeepSeek)", "url": "https://www.anchorterminal.com/compare/crush-vs-deepseek-superagent" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-harness2.json", "title": "Crush vs Harness²", "url": "https://www.anchorterminal.com/compare/crush-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-deepseek-superagent.json", "title": "Cursor CLI vs dsh-superagent (DeepSeek)", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-deepseek-superagent" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.json", "title": "Cursor CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-deepseek-superagent.json", "title": "DeepSeek Harness (dsh) vs dsh-superagent (DeepSeek)", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-deepseek-superagent" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2.json", "title": "DeepSeek Harness (dsh) vs Harness²", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-devin.json", "title": "dsh-superagent (DeepSeek) vs Devin", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-devin" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-droid-cli.json", "title": "dsh-superagent (DeepSeek) vs Droid CLI", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-droid-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-earendil-pi.json", "title": "dsh-superagent (DeepSeek) vs Pi", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-gemini-cli.json", "title": "dsh-superagent (DeepSeek) vs Gemini CLI", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-gemini-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-github-copilot-cli.json", "title": "dsh-superagent (DeepSeek) vs GitHub Copilot CLI", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-github-copilot-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-goose.json", "title": "dsh-superagent (DeepSeek) vs goose", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-goose" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harnessrouter.json", "title": "dsh-superagent (DeepSeek) vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-jules.json", "title": "dsh-superagent (DeepSeek) vs Jules", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-jules" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-junie.json", "title": "dsh-superagent (DeepSeek) vs Junie CLI", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-junie" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-kilo-code-cli.json", "title": "dsh-superagent (DeepSeek) vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-kimi-code-cli.json", "title": "dsh-superagent (DeepSeek) vs Kimi Code CLI", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-kimi-code-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-kiro-cli.json", "title": "dsh-superagent (DeepSeek) vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-mini-swe-agent.json", "title": "dsh-superagent (DeepSeek) vs mini-swe-agent", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-mini-swe-agent" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-minimax-code.json", "title": "dsh-superagent (DeepSeek) vs MiniMax Code", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-minimax-code" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-mistral-vibe-cli.json", "title": "dsh-superagent (DeepSeek) vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-muse-code.json", "title": "dsh-superagent (DeepSeek) vs Muse Code", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-openai-codex.json", "title": "dsh-superagent (DeepSeek) vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-opencode.json", "title": "dsh-superagent (DeepSeek) vs OpenCode", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-openhands.json", "title": "dsh-superagent (DeepSeek) vs OpenHands", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-openmausbot.json", "title": "dsh-superagent (DeepSeek) vs OpenMausBot", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-openmausbot" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-prime-agent.json", "title": "dsh-superagent (DeepSeek) vs Prime Agent", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-qoder-cli.json", "title": "dsh-superagent (DeepSeek) vs Qoder CLI", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-qoder-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-qwen-code.json", "title": "dsh-superagent (DeepSeek) vs Qwen Code", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-reflection-mirror.json", "title": "dsh-superagent (DeepSeek) vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-rovo-dev-cli.json", "title": "dsh-superagent (DeepSeek) vs Rovo Dev CLI", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-rovo-dev-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-unstoppable.json", "title": "dsh-superagent (DeepSeek) vs Unstoppable", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-unstoppable" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-vibe-trading.json", "title": "dsh-superagent (DeepSeek) vs Vibe-Trading", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-vibe-trading" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-warp.json", "title": "dsh-superagent (DeepSeek) vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-harness2.json", "title": "Devin vs Harness²", "url": "https://www.anchorterminal.com/compare/devin-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/droid-cli-vs-harness2.json", "title": "Droid CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.json", "title": "Pi vs Harness²", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.json", "title": "Gemini CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.json", "title": "GitHub Copilot CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/goose-vs-harness2.json", "title": "goose vs Harness²", "url": "https://www.anchorterminal.com/compare/goose-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.json", "title": "Harness² vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/harness2-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-jules.json", "title": "Harness² vs Jules", "url": "https://www.anchorterminal.com/compare/harness2-vs-jules" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-junie.json", "title": "Harness² vs Junie CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-junie" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.json", "title": "Harness² vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-kimi-code-cli.json", "title": "Harness² vs Kimi Code CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-kimi-code-cli" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.json", "title": "Harness² vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-mini-swe-agent.json", "title": "Harness² vs mini-swe-agent", "url": "https://www.anchorterminal.com/compare/harness2-vs-mini-swe-agent" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-minimax-code.json", "title": "Harness² vs MiniMax Code", "url": "https://www.anchorterminal.com/compare/harness2-vs-minimax-code" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-mistral-vibe-cli.json", "title": "Harness² vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-muse-code.json", "title": "Harness² vs Muse Code", "url": "https://www.anchorterminal.com/compare/harness2-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-openai-codex.json", "title": "Harness² vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/harness2-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-opencode.json", "title": "Harness² vs OpenCode", "url": "https://www.anchorterminal.com/compare/harness2-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-openhands.json", "title": "Harness² vs OpenHands", "url": "https://www.anchorterminal.com/compare/harness2-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-openmausbot.json", "title": "Harness² vs OpenMausBot", "url": "https://www.anchorterminal.com/compare/harness2-vs-openmausbot" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent.json", "title": "Harness² vs Prime Agent", "url": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-qoder-cli.json", "title": "Harness² vs Qoder CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-qoder-cli" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-qwen-code.json", "title": "Harness² vs Qwen Code", "url": "https://www.anchorterminal.com/compare/harness2-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.json", "title": "Harness² vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-rovo-dev-cli.json", "title": "Harness² vs Rovo Dev CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-rovo-dev-cli" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-unstoppable.json", "title": "Harness² vs Unstoppable", "url": "https://www.anchorterminal.com/compare/harness2-vs-unstoppable" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-vibe-trading.json", "title": "Harness² vs Vibe-Trading", "url": "https://www.anchorterminal.com/compare/harness2-vs-vibe-trading" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-warp.json", "title": "Harness² vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/harness2-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/clawboo-vs-deepseek-superagent.json", "title": "Clawboo vs dsh-superagent (DeepSeek)", "url": "https://www.anchorterminal.com/compare/clawboo-vs-deepseek-superagent" }, { "json": "https://www.anchorterminal.com/compare/cli-manager-vs-deepseek-superagent.json", "title": "CLI Manager vs dsh-superagent (DeepSeek)", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-deepseek-superagent" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness-autonomous.json", "title": "dsh-superagent (DeepSeek) vs Harness", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness-autonomous" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-paperclip.json", "title": "dsh-superagent (DeepSeek) vs Paperclip", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-parallax-agents.json", "title": "dsh-superagent (DeepSeek) vs Parallax", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-parallax-agents" } ], "panel": null, "scores": [ { "by": 5, "deepseek-superagent": 15, "edge": "harness2", "harness2": 20, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 10, "deepseek-superagent": 61, "edge": "deepseek-superagent", "harness2": 51, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 8, "deepseek-superagent": 67, "edge": "deepseek-superagent", "harness2": 59, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 11, "deepseek-superagent": 33, "edge": "harness2", "harness2": 44, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "deepseek-superagent": 40, "edge": "", "harness2": 40, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 2, "deepseek-superagent": 34, "edge": "harness2", "harness2": 36, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 3, "deepseek-superagent": 52, "edge": "deepseek-superagent", "harness2": 49, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "dsh-superagent (DeepSeek) and Harness² score within a point of each other on agent readiness, 42.1 (E) and 42 (E). Harness² leads on reliability and security \u0026 auth. Both do agent harnesses.", "tasks": null, "tutorials": [], "verdicts": { "deepseek-superagent": "The authorization design is careful, with allowed lists, Mandates and a Policy enforced in code, proactive work only recorded by default and auto-merge off. Executors run every command without approval under the operator's OS user, and the README calls it a research prototype with no release, changelog or security policy.", "harness2": "Refinement needs no grader or answer key, and the code keeps judges out of selection. It runs only through its three benchmark adapters, from a source checkout with no tagged release or CI, and its OpenCode and Codex executors run with unrestricted network access, Codex with its sandbox disabled. The benchmark gains are the authors' claims." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2", "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2.min.md" }, "markdown": "dsh-superagent (DeepSeek) and Harness² score within a point of each other on agent readiness, 42.1 (E) and 42 (E). Harness² leads on reliability and security \u0026 auth. Both do agent harnesses.\n\n- dsh-superagent (DeepSeek): grade E, 42.1/100, rank #1108 of 1251. Markdown https://www.anchorterminal.com/tools/deepseek-superagent.md · JSON https://www.anchorterminal.com/api/v1/tools/deepseek-superagent.json\n- Harness²: grade E, 42/100, rank #1109 of 1251. Markdown https://www.anchorterminal.com/tools/harness2.md · JSON https://www.anchorterminal.com/api/v1/tools/harness2.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 955 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### dsh-superagent (DeepSeek) (E)\n\nGood for: Teams on github.com that want a DeepSeek Harness agent to turn allowed people's issue requests into pull requests, run on an isolated machine or OS account.\n\nAhead on:\n- Schema \u0026 documentation, 61 against 51\n- Agent ergonomics, 67 against 59\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: Executor and main Sessions run with `danger-full-access` as the operator's OS user, and the docs say a worker can read the operator's home directory\n\n### Harness² (E)\n\nGood for: Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI.\n\nAhead on:\n- Reliability, 20 against 15\n- Security \u0026 auth, 44 against 33\n\nAlso in its favour:\n- No key needed to call it\n\nWatch for: No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI\n\n\n## Why the edge\n\n### Security \u0026 auth: Harness² +11\n\n- dsh-superagent (DeepSeek) (33): Harness reading of the framework checklist, 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. The `superagent` profile is created from DSH's Web template, and DSH documents that shipped profiles mount `session-log-deepseek`, enabled by default, which adds the session log to each official DeepSeek API request, up to 8 MiB. dsh-superagent's docs don't mention it, and its Sessions read issue, pull request and chat text and the repository. Setup and worker shells drop variables named KEY, PASSWORD, SECRET or TOKEN, and `GH_TOKEN` and `GITHUB_TOKEN` are removed from git (8). Both presets run `danger-full-access` without approval as the operator's OS user. docs/006 says the account wrappers don't isolate the process, a worker can run programs by path and read the operator's home directory, and recommends a dedicated OS account. The gate, `observe` default, blocked commands and no auto-merge as the agent account narrow what it does, not what it can do (6). docs/002 says messages, comments and quoted documents are inputs to a decision and can't change allowed lists, rules or Mandates, bots can never make explicit requests, and prompt edits don't change the gate. Workers with full access still read untrusted Thread text, and no further guidance on that was found (7). Decisions are recorded with reasons, Ticket details show the Trigger, Decision, scope and Policy version, the host records the prompt revisions each Session used, and every GitHub message starts with an automated-agent line by default (12). No SECURITY.md (404 at the root and in .github), no security.txt on www.deepseek.com (404), no bug bounty or advisory found. NVD has no record for the prototype. The CVEs against DSH itself are on the deepseek-harness listing (0).\n- Harness² (44): Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture and network egress, 15 for audit and 20 for the security programme. No telemetry found in the Harness² source, and the WorkBuddy OpenCode configs turn OpenCode's telemetry, auto-update and sharing off. Credentials are Google Application Default Credentials, and the Codex bridge binds 127.0.0.1 by default with a generated key stored with mode 0600. Against that, executors inherit the whole shell environment (the editor channel drops only five Anthropic variables), and no .gitignore keeps a filled-in .env out of commits (20). Codex runs with `--dangerously-bypass-approvals-and-sandbox`, the Claude CLI editor channel with `--dangerously-skip-permissions`, and the WorkBuddy OpenCode preset allows every tool, with only OpenCode's directory fence and WorkBuddy's containers as limits. The README and setup guide say so (4). Executor network access is unrestricted by default. The docs name the hosts to block and report a Codex rollout that fetched its rubric unprompted, but give no guidance on instructions inside task documents (5). Each editor call's prompt, system text, response, model and cost are saved to an audit folder, with trajectories and adopted harnesses under runs/ (13). No SECURITY.md or security.txt and no advisories, and the README says the project is outside Google's open-source vulnerability rewards programme (2). 44 in all.\n\n### Schema \u0026 documentation: dsh-superagent (DeepSeek) +10\n\n- dsh-superagent (DeepSeek) (61): Framework reading, as for deepseek-harness. No OpenAPI or JSON Schema is published. docs/006 documents the Management API's routes, fields, block shapes and refusals in tables, and the code validates settings with zod (12). Markdown docs in the repository, readable raw, and a SETUP.md written for a coding agent. No llms.txt (5). Nine numbered documents read in order, each stating purpose, limits and what not to do, such as never rerunning the profile-creation command for an upgrade (17). Closed sets for accept mode (`off`, `observe`, `auto`), admission cells, Source states, health states and `listen` (12). A worked curl example, refusals as 400, 404, 409 and 500 with `issues`, `setup` or `code`, a troubleshooting table and status exit codes 0 to 3 (13). package.json says 0.1.0 and pins an `engines.dsh` range, but no changelog or tags were found (2).\n- Harness² (51): Framework reading. Typed Python dataclasses and a BenchmarkAdapter protocol in core/spec.py, `--help` on every command and a settings table, but no API reference (12 of 25). Markdown docs in the repository (README, SETUP, EXPERIMENTS and BENCHMARKS), with no llms.txt (5 of 10). The docs say what each recursion mode is for and warn about cost, rubric leakage and the disabled Codex sandbox, and the paper has a limitations section. Nothing says how to use it outside the three benchmarks (13 of 20). `--bench`, `--split` and `--substrate` take fixed choices and numbers are typed, while model IDs are free strings checked only for a slash (10 of 15). Every command has a worked example and ConfigError messages name the fix, but the quick start's `cp .env.example .env` fails because the file isn't shipped (8 of 15). Version 0.1.0 with no changelog (3 of 15). 51 in all.\n\n### Agent ergonomics: dsh-superagent (DeepSeek) +8\n\n- dsh-superagent (DeepSeek) (67): Harness reading, scored on what a team or pipeline driving it has to supply. The worker preset is DSH's `standard` with web fetch, plan mode, questions, scheduling and workflows left out, the main Session can't write files, and tool results over 8,192 characters are pruned (18). A concurrency limit with one extra slot for a person's message, a 5-second foreground shell, a 10-minute prepare limit and 30 minutes for background work after a turn. No cost or turn limit per Ticket was found (12). Ticket stages, health entries per part, Reports of `blocked` or `failed`, API refusals with codes, and three retries with growing backoff on 408, 429, 5xx and dropped connections (17). Saves carry a revision and a stale one gets 409, state and Sessions survive a restart, and a restarted Assignment gets a recovery note to check git and GitHub before repeating any outside action (16). Sensible defaults (observe mode, port 3082, branch prefix `agent/`), but setup needs a dedicated GitHub user account, CLI wrappers, tmux and a profile, and there is no SDK. Work is requested by mentioning the agent account on GitHub or Feishu (4).\n- Harness² (59): Framework reading, adapted to a harness that a pipeline drives. Results land in run folders, not in the caller's context, and an agent reads task summaries, adopted harnesses and reflection notes from runs/ (12 of 25). `--only-domains`, `--max-tasks` (per domain), `--split-file`, `--workers` and `--dry-run` size a run before any model call (14 of 20). harness2-check tests dependencies, credentials and configuration without a model call, configuration errors name the remedy, and incomplete runs exit nonzero (14 of 20). Rerunning a command resumes it, saved configuration refuses an incompatible resume, failed grades stay unscored, and editor replies are cached by a fingerprint of their inputs (15 of 20). No model has a default, a Vertex AI project and a gcloud sign-in are needed, only three benchmarks are accepted and there's no SDK (4 of 15). 59 in all.\n\n### Reliability: Harness² +5\n\n- dsh-superagent (DeepSeek) (15): Local-package reading, since it runs as a DSH bundle on the operator's machine. Not published to npm (`private: true` in package.json, and the registry has no `dsh-superagent`). It installs from a git clone with `pnpm install \u0026\u0026 pnpm build` on top of `@deepseek-ai/dsh@0.2.1-rc.3`, with Node 22.19+ or 24+, git 2.32+, Python 3.8+, tmux and gh 2.48+ stated, so half credit (10). A vitest suite of about 25 spec files is listed in docs/007, and `pnpm check` runs the typecheck, tests and build. Two spec files were read on raw.githubusercontent.com. No CI workflow was found at five common paths under .github/workflows, and the directory couldn't be listed (5). Open issues couldn't be read, because github.com and api.github.com weren't reachable from our network. Unchecked, so scored absent (0). Version 0.1.0 with no tag, release or changelog found, so no semver record (0). A research prototype, not stable (0).\n- Harness² (20): Local-package reading. Not on PyPI (the release feed for harness2 answers 404). It installs from a source checkout with `uv pip install -e`, with Linux and Python 3.12 stated (the package allows 3.13), plus Node.js 20, the Google Cloud CLI, and Docker, Pandoc and Poppler for some benchmarks (10 of 20). No CI workflow in the repository. tests/test_workflow.py holds five unit tests over the deterministic demo, which needs no credentials (5 of 25). Six issues and 42 pull requests were open on 18 October, the pull requests mostly fixes by their titles, such as the missing .env.example, report failures, seeds lost between refinement and grading, and resume. None is merged and no issue is closed. Issue text and replies couldn't be read (5 of 25). No tags or changelog (0). Version 0.1.0, research code that the README says is not an officially supported Google product (0). 20 in all.\n\n## Score by category\n\n| Category | Weight | dsh-superagent (DeepSeek) | Harness² | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 15 | 20 | Harness² +5 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 61 | 51 | dsh-superagent (DeepSeek) +10 |\n| Agent ergonomics | 13% (16.2 this run) | 67 | 59 | dsh-superagent (DeepSeek) +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 33 | 44 | Harness² +11 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 40 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 34 | 36 | Harness² +2 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 52 | 49 | dsh-superagent (DeepSeek) +3 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **42.1 · E** | **42 · E** | |\n\n## Facts side by side\n\n| Fact | dsh-superagent (DeepSeek) | Harness² |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | DeepSeek | Google (Google Research) |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | Token | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | MIT | Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation). |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-31 | 2026-10-08 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | 2026-09-20 | no document linked |\n| Popularity | none | 4.2k stars |\n| Agent reviews | none | 2.5/5 (4) |\n\n## How the scores have moved\n\n### dsh-superagent (DeepSeek)\n\nNo score change since it was listed.\n\n### Harness²\n\n- +0.4 on 27 October 2026: checklist\n\n## Verdicts\n\n**dsh-superagent (DeepSeek).** The authorization design is careful, with allowed lists, Mandates and a Policy enforced in code, proactive work only recorded by default and auto-merge off. Executors run every command without approval under the operator's OS user, and the README calls it a research prototype with no release, changelog or security policy.\n\n**Harness².** Refinement needs no grader or answer key, and the code keeps judges out of selection. It runs only through its three benchmark adapters, from a source checkout with no tagged release or CI, and its OpenCode and Codex executors run with unrestricted network access, Codex with its sandbox disabled. The benchmark gains are the authors' claims.\n\n## Before you call either\n\n### dsh-superagent (DeepSeek)\n\n1. Run it under a dedicated OS account holding only the agent's credentials. Executors run commands without approval and can read the operator's home directory\n2. Set `enabled: false` on the `session-log-deepseek` row of the `superagent` profile before using DeepSeek's official API on private code\n3. Keep the accept mode at `observe` and the allowed list short until the recorded Decisions look right\n4. Wait for `scripts/dsh-superagent status` to stop exiting 1 after any save that answers `restarting: true` before the next request\n5. Send `x-orchestrator-request: 1` and a loopback Host to the Management API, and send `revision` with each PUT, since a stale one gets 409\n\n### Harness²\n\n1. Don't plan to call Harness² as a service. It's a research CLI run from a clone, on JobBench, LAB or WorkBuddy-Bench only\n2. Ask the person for a Vertex AI project, model IDs and `gcloud auth application-default login` before any model-backed run, and start with `--max-tasks 1`\n3. Run executors behind an egress firewall and block huggingface.co and github.com after setup, as the docs advise, so rubrics can't be fetched\n4. Write .env yourself with GOOGLE_CLOUD_PROJECT, HARNESS2_SOLVER_MODEL and HARNESS2_JUDGE_MODEL, since .env.example isn't shipped, and never commit it\n5. Use the same benchmark, executor, `--k`, `--mode` and seed for `harness2`, `harness2-judge` and `harness2-report`, or the results won't line up\n\n## Questions\n\n### Which is better for AI agents, dsh-superagent (DeepSeek) or Harness²?\n\ndsh-superagent (DeepSeek) and Harness² score within a point of each other on agent readiness, 42.1 (E) and 42 (E). Harness² leads on reliability and security \u0026 auth.\n\n### Are dsh-superagent (DeepSeek) and Harness² open source?\n\nYes. dsh-superagent (DeepSeek) is open source (MIT). Harness² is open source (Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2.json, and with the fewest tokens: https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"deepseek-superagent\", \"b\": \"harness2\"}`. From a terminal: `anchor compare deepseek-superagent harness2`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/deepseek-superagent.json and https://www.anchorterminal.com/api/v1/tools/harness2.json\n\n## Other comparisons with dsh-superagent (DeepSeek) or Harness²\n\n- [Agent Zero vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/agent-zero-vs-deepseek-superagent.md)\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Aider vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/aider-vs-deepseek-superagent.md)\n- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)\n- [Amp vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/amp-vs-deepseek-superagent.md)\n- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)\n- [Antigravity CLI vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/antigravity-cli-vs-deepseek-superagent.md)\n- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)\n- [Auggie CLI vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/auggie-vs-deepseek-superagent.md)\n- [Auggie CLI vs Harness²](https://www.anchorterminal.com/compare/auggie-vs-harness2.md)\n- [Claude Code vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/claude-code-vs-deepseek-superagent.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Cline vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/cline-vs-deepseek-superagent.md)\n- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)\n- [Crush vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/crush-vs-deepseek-superagent.md)\n- [Crush vs Harness²](https://www.anchorterminal.com/compare/crush-vs-harness2.md)\n- [Cursor CLI vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/cursor-cli-vs-deepseek-superagent.md)\n- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)\n- [DeepSeek Harness (dsh) vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/deepseek-harness-vs-deepseek-superagent.md)\n- [DeepSeek Harness (dsh) vs Harness²](https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2.md)\n- [dsh-superagent (DeepSeek) vs Devin](https://www.anchorterminal.com/compare/deepseek-superagent-vs-devin.md)\n- [dsh-superagent (DeepSeek) vs Droid CLI](https://www.anchorterminal.com/compare/deepseek-superagent-vs-droid-cli.md)\n- [dsh-superagent (DeepSeek) vs Pi](https://www.anchorterminal.com/compare/deepseek-superagent-vs-earendil-pi.md)\n- [dsh-superagent (DeepSeek) vs Gemini CLI](https://www.anchorterminal.com/compare/deepseek-superagent-vs-gemini-cli.md)\n- [dsh-superagent (DeepSeek) vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/deepseek-superagent-vs-github-copilot-cli.md)\n- [dsh-superagent (DeepSeek) vs goose](https://www.anchorterminal.com/compare/deepseek-superagent-vs-goose.md)\n- [dsh-superagent (DeepSeek) vs HarnessRouter](https://www.anchorterminal.com/compare/deepseek-superagent-vs-harnessrouter.md)\n- [dsh-superagent (DeepSeek) vs Jules](https://www.anchorterminal.com/compare/deepseek-superagent-vs-jules.md)\n- [dsh-superagent (DeepSeek) vs Junie CLI](https://www.anchorterminal.com/compare/deepseek-superagent-vs-junie.md)\n- [dsh-superagent (DeepSeek) vs Kilo Code CLI](https://www.anchorterminal.com/compare/deepseek-superagent-vs-kilo-code-cli.md)\n- [dsh-superagent (DeepSeek) vs Kimi Code CLI](https://www.anchorterminal.com/compare/deepseek-superagent-vs-kimi-code-cli.md)\n- [dsh-superagent (DeepSeek) vs Kiro CLI](https://www.anchorterminal.com/compare/deepseek-superagent-vs-kiro-cli.md)\n- [dsh-superagent (DeepSeek) vs mini-swe-agent](https://www.anchorterminal.com/compare/deepseek-superagent-vs-mini-swe-agent.md)\n- [dsh-superagent (DeepSeek) vs MiniMax Code](https://www.anchorterminal.com/compare/deepseek-superagent-vs-minimax-code.md)\n- [dsh-superagent (DeepSeek) vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/deepseek-superagent-vs-mistral-vibe-cli.md)\n- [dsh-superagent (DeepSeek) vs Muse Code](https://www.anchorterminal.com/compare/deepseek-superagent-vs-muse-code.md)\n- [dsh-superagent (DeepSeek) vs OpenAI Codex](https://www.anchorterminal.com/compare/deepseek-superagent-vs-openai-codex.md)\n- [dsh-superagent (DeepSeek) vs OpenCode](https://www.anchorterminal.com/compare/deepseek-superagent-vs-opencode.md)\n- [dsh-superagent (DeepSeek) vs OpenHands](https://www.anchorterminal.com/compare/deepseek-superagent-vs-openhands.md)\n- [dsh-superagent (DeepSeek) vs OpenMausBot](https://www.anchorterminal.com/compare/deepseek-superagent-vs-openmausbot.md)\n- [dsh-superagent (DeepSeek) vs Prime Agent](https://www.anchorterminal.com/compare/deepseek-superagent-vs-prime-agent.md)\n- [dsh-superagent (DeepSeek) vs Qoder CLI](https://www.anchorterminal.com/compare/deepseek-superagent-vs-qoder-cli.md)\n- [dsh-superagent (DeepSeek) vs Qwen Code](https://www.anchorterminal.com/compare/deepseek-superagent-vs-qwen-code.md)\n- [dsh-superagent (DeepSeek) vs Mirror CLI](https://www.anchorterminal.com/compare/deepseek-superagent-vs-reflection-mirror.md)\n- [dsh-superagent (DeepSeek) vs Rovo Dev CLI](https://www.anchorterminal.com/compare/deepseek-superagent-vs-rovo-dev-cli.md)\n- [dsh-superagent (DeepSeek) vs Unstoppable](https://www.anchorterminal.com/compare/deepseek-superagent-vs-unstoppable.md)\n- [dsh-superagent (DeepSeek) vs Vibe-Trading](https://www.anchorterminal.com/compare/deepseek-superagent-vs-vibe-trading.md)\n- [dsh-superagent (DeepSeek) vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/deepseek-superagent-vs-warp.md)\n- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)\n- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)\n- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)\n- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)\n- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)\n- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)\n- [Harness² vs HarnessRouter](https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.md)\n- [Harness² vs Jules](https://www.anchorterminal.com/compare/harness2-vs-jules.md)\n- [Harness² vs Junie CLI](https://www.anchorterminal.com/compare/harness2-vs-junie.md)\n- [Harness² vs Kilo Code CLI](https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.md)\n- [Harness² vs Kimi Code CLI](https://www.anchorterminal.com/compare/harness2-vs-kimi-code-cli.md)\n- [Harness² vs Kiro CLI](https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.md)\n- [Harness² vs mini-swe-agent](https://www.anchorterminal.com/compare/harness2-vs-mini-swe-agent.md)\n- [Harness² vs MiniMax Code](https://www.anchorterminal.com/compare/harness2-vs-minimax-code.md)\n- [Harness² vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/harness2-vs-mistral-vibe-cli.md)\n- [Harness² vs Muse Code](https://www.anchorterminal.com/compare/harness2-vs-muse-code.md)\n- [Harness² vs OpenAI Codex](https://www.anchorterminal.com/compare/harness2-vs-openai-codex.md)\n- [Harness² vs OpenCode](https://www.anchorterminal.com/compare/harness2-vs-opencode.md)\n- [Harness² vs OpenHands](https://www.anchorterminal.com/compare/harness2-vs-openhands.md)\n- [Harness² vs OpenMausBot](https://www.anchorterminal.com/compare/harness2-vs-openmausbot.md)\n- [Harness² vs Prime Agent](https://www.anchorterminal.com/compare/harness2-vs-prime-agent.md)\n- [Harness² vs Qoder CLI](https://www.anchorterminal.com/compare/harness2-vs-qoder-cli.md)\n- [Harness² vs Qwen Code](https://www.anchorterminal.com/compare/harness2-vs-qwen-code.md)\n- [Harness² vs Mirror CLI](https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.md)\n- [Harness² vs Rovo Dev CLI](https://www.anchorterminal.com/compare/harness2-vs-rovo-dev-cli.md)\n- [Harness² vs Unstoppable](https://www.anchorterminal.com/compare/harness2-vs-unstoppable.md)\n- [Harness² vs Vibe-Trading](https://www.anchorterminal.com/compare/harness2-vs-vibe-trading.md)\n- [Harness² vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/harness2-vs-warp.md)\n- [Clawboo vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/clawboo-vs-deepseek-superagent.md)\n- [CLI Manager vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/cli-manager-vs-deepseek-superagent.md)\n- [dsh-superagent (DeepSeek) vs Harness](https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness-autonomous.md)\n- [dsh-superagent (DeepSeek) vs Paperclip](https://www.anchorterminal.com/compare/deepseek-superagent-vs-paperclip.md)\n- [dsh-superagent (DeepSeek) vs Parallax](https://www.anchorterminal.com/compare/deepseek-superagent-vs-parallax-agents.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-01", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "dsh-superagent (DeepSeek) vs Harness²", "url": "" } ], "description": "dsh-superagent and Harness² score within a point of each other for agent harnesses, 42.1 and 42 out of 100. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "dsh-superagent (DeepSeek) E 42.1", "Harness² E 42", "scores" ], "h1": "dsh-superagent (DeepSeek) vs Harness²", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/deepseek-superagent-vs-harness2", "published": "2026-10-01", "section": "tools", "title": "dsh-superagent vs Harness² for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-01", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2" }, "tokens": { "markdown": 6500, "slim": 2930 }, "version": 1 }