{ "data": { "a": { "slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "vendorUrl": "https://www.anthropic.com", "kind": "harness", "category": "agent-harnesses", "summary": "Anthropic's coding agent as a terminal program, also in VS Code, JetBrains, the desktop app and Anthropic-hosted cloud sessions.", "url": "https://www.anchorterminal.com/tools/claude-code", "markdownUrl": "https://www.anchorterminal.com/tools/claude-code.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/claude-code.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/claude-code.json", "repo": "https://github.com/anthropics/claude-code", "license": "Proprietary. `LICENSE.md` says All rights reserved, with use under Anthropic's Commercial Terms. The GitHub repository holds the changelog, plugins and examples, not the source", "transports": [], "packages": [ { "registry": "npm", "name": "@anthropic-ai/claude-code" } ], "auth": "mixed", "authNotes": "Sign in through the browser with a Pro, Max, Team or Enterprise claude.ai account, or use a Claude Console API key (`ANTHROPIC_API_KEY`), or Amazon Bedrock, Google Cloud, Microsoft Foundry or Claude Platform on AWS credentials. The free claude.ai plan doesn't include Claude Code.", "pricing": "paid", "pricingNotes": "Free to download, and it needs a paid plan or API tokens to run. Pro is $17 a month billed annually or $20 monthly, Max from $100 a month, Team $20 or $25 a standard seat and $100 or $125 a premium seat, Enterprise $20 a seat billed annually with a 20-seat minimum, plus usage at API rates, or pay as you go at Claude API token prices. On a plan Claude Code shares the plan's usage limits, and the pricing page gives no number for them (checked 2026-10-17).", "priceSummary": "$20 / mo", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or the pricing page (checked 2026-10-02).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 141000, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-02" }, "docsUrl": "https://code.claude.com/docs/en/overview", "llmsTxt": "https://code.claude.com/docs/llms.txt", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "official", "harness", "coding-agent", "cli", "closed-source", "claude-only", "mcp", "llms-txt", "telemetry-default-on", "status-page", "card-required" ], "lastRelease": "2026-10-16", "graded": true, "disclosure": "Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and re-checked on 15 October 2026 with every judgement call written in the note. Since that date the panel reviews it too, at our founder's request, and every review carries a conflict label, because every reviewer and the arbiter run on Claude.", "anchor": { "graded": true, "score": 59.9, "grade": "C", "agentReady": false, "rank": 588, "ranked": true, "rankOf": 1146, "categoryRank": 17, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 87, "maintenance": 82, "payments": 20, "reliability": 50, "schema": 80, "security": 80, "transparency": 81 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-17" }, "negative": -8, "negativeNotes": [ "2025-10-03 to 2026-06-25. 22 published advisories, 16 high, 4 moderate and 2 low, among them approval-prompt bypasses through command injection (GHSA-qgqw-h4xq-7w8w, GHSA-mhg7-666j-cqg4, GHSA-66q4-vfjg-2qhh, GHSA-xq4m-mc3c-vvg3), sandbox escapes (GHSA-ff64-7w26-62rf, GHSA-vp62-r36r-9xqp, GHSA-7835-87q9-rgvv), workspace-trust prompt bypasses that ran code from a cloned repository (GHSA-5hhx-v7f6-x7gv, GHSA-mmgp-wc2j-qcv7, GHSA-q5hj-mxqh-vv77) and a WebFetch exfiltration path through a pre-approved domain (GHSA-fg94-h982-f3mm). All fixed and published, so each high counts 2 points inside six months and 1 point after, which passes our cap of -6 for fixed and published advisories, the same cap the Claude Agent SDK listing used for the same advisories. Since then the advisories page, read on 15 October, lists GHSA-gfvf-j8jh-jxxw (Low, 29 September, managed settings not applied when a stored API key was preferred) and GHSA-5j29-h97v-84ch (High, 5 October, arbitrary file write by symlink following), both published and read as fixed. GitHub's reviewed advisory database, read through OSV on 17 October, adds GHSA-pq7j-f95f-qfcv (CVE-2026-86063, High, published 15 October 2026, a plugin hash-pin bypass in the plugin install flow, fixed in 2.1.179). All three sit under the same cap (https://github.com/anthropics/claude-code/security/advisories and https://api.osv.dev/v1/vulns/GHSA-pq7j-f95f-qfcv). -6", "2026-10-02 to 2026-10-14. The changelog for 2.1.288 to 2.1.300 lists fixes for a dangerous `rm` inside `bash -c` running without a prompt under a shell allow rule (2.1.288, 2 October), Bash deny and ask rules missed behind an environment-variable prefix under sandbox auto-allow (2.1.289, 3 October), background workers sending telemetry and a feature-flag request to Anthropic behind a Claude apps gateway (2.1.290, 5 October), hook approvals and auto mode skipping the prompt for file reads from network (UNC) paths, marked Security (2.1.292, 6 October), sandboxed commands writing into a `--plugin-dir` folder whose code runs outside the sandbox, or reaching a denied path through a symlink on macOS (2.1.299, 14 October), and agent hooks whose model was unavailable allowing the action instead of falling back to the caller's model (2.1.300, 14 October). All fixed. Judgement call. No advisory for them appears on the first page of the advisories list read on 15 October or in GitHub's reviewed database read through OSV on 17 October, so they're disclosed only in the changelog, and we applied to the group the -2 GitHub Copilot CLI got for one changelog-only enforcement-gap fix. Counting each item at -2 would give -12, and we found no listing whose changelog fixes were counted one by one. If these carry GHSA ids, they fall under the -6 advisory cap already reached and this line goes. 2.1.301 and 2.1.302 (15 and 16 October) list no comparable fix (https://code.claude.com/docs/en/changelog). -2" ], "verdict": "Six permission modes, allow, ask and deny rules down to command arguments, PreToolUse hooks, and managed settings that can disable bypass and auto mode. The sandbox is off by default and native Windows has none.", "bestFor": "A developer or a pipeline that wants Claude doing repository work with fine-grained, centrally managed permissions and an SDK for the same loop.", "disclosure": "Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and re-checked on 15 October 2026 with every judgement call written in the note. Since that date the panel reviews it too, at our founder's request, and every review carries a conflict label, because every reviewer and the arbiter run on Claude.", "strengths": [ "Six permission modes, allow, ask and deny rules down to command arguments, PreToolUse hooks, and managed settings that can disable bypass and auto mode", "An OS sandbox (Seatbelt, bubblewrap) whose network proxy denies every host outside an allowlist that starts empty", "`claude -p` with json and stream-json output, `--max-turns`, `--max-budget-usd`, resume and fork, and Python and TypeScript SDKs for the same loop", "Signed apt, dnf and apk repositories, a GPG-signed checksum manifest and a stable channel that skips releases with major regressions", "Telemetry documented per provider and per service, each with its own opt-out" ], "weaknesses": [ "The sandbox is off by default and native Windows has none", "Auto mode, a classifier rather than a person, has been the starting mode for interactive sessions on every plan since 28 September 2026", "22 security advisories in the year to 25 June 2026, 16 high, further highs on 5 and 15 October 2026, and sandbox and deny-rule fixes in October releases", "Usage metrics on by default on the Claude API, and error reports on Pro and Max sign-ins", "Closed source, Claude models only, and no free plan includes it" ], "agentNotes": [ "Pass `--permission-mode`, `--max-turns` and `--max-budget-usd` on every `claude -p` run. The unset mode changed again in 2.1.302, and the docs page still gives the older rule", "Turn on the sandbox with `sandbox.enabled` and set `allowUnsandboxedCommands` to false, or Claude can retry a blocked command outside it", "Write MCP allow rules as `mcp__\u003cserver\u003e__*` with the server's whole name. Since 2.1.299 a rule for `mcp__a` no longer covers a server named `a__b`", "Set `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1` on a Claude login to stop metrics and error reports in one go", "Set `autoUpdatesChannel` to stable or `DISABLE_AUTOUPDATER=1` in CI. Native installs update themselves about once a day" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 59.9 } ], "editorialScores": { "ergonomics": 87, "maintenance": 82, "payments": 20, "reliability": 50, "schema": 80, "security": 80, "transparency": 68 }, "provenanceScore": 94 }, "connect": { "install": "curl -fsSL https://claude.ai/install.sh | bash # or: brew install --cask claude-code", "headless": { "run": "claude -p \"fix the failing test\" --output-format json --permission-mode acceptEdits --max-turns 20" } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/claude-code" }, "sameCompany": [ "anthropic-api", "claude-agent-sdk" ], "area": "frameworks", "unitPrices": [ { "item": "Pro plan", "unit": "month", "usd": 20, "note": "$17 a month billed annually" }, { "item": "Max plan", "unit": "month", "usd": 100, "note": "lowest Max tier" } ], "provenance": { "legalEntity": "Anthropic, PBC", "domain": "claude.com", "domainRegistered": "1995-05-24", "domainNote": "claude.com was registered in 1995, long before Anthropic bought it. Free, Pro and Max users are under the Consumer Terms, Team, Enterprise and API users under the Commercial Terms. The security.txt state is anthropic.com's, read on 17 October 2026 (HackerOne contact, Expires 2026-12-31). claude.com serves none (404 on 17 October). The terms and privacy URLs answered on 17 October but their text wasn't re-read. The status page was read through its RSS feed.", "endpointOnVendorDomain": null, "terms": "https://www.anthropic.com/legal/commercial-terms", "privacy": "https://www.anthropic.com/legal/privacy", "statusPage": "https://status.claude.com", "changelog": "https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md", "securityTxt": "valid", "checked": "2026-10-17", "score": 94 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/claude-code.json", "live": { "slug": "claude-code", "vendorStatus": { "page": "https://status.claude.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-19T00:04:48.701326956Z" }, "versions": [ { "registry": "github", "name": "anthropics/claude-code", "version": "v2.1.302", "released": "2026-10-16", "seenAt": "2026-10-18T02:38:33.340848872Z" }, { "registry": "npm", "name": "@anthropic-ai/claude-code", "version": "2.1.302", "seenAt": "2026-10-18T02:38:32.486170342Z" } ], "githubStars": 151807, "npmWeekly": 6083065, "securityTxt": { "url": "https://claude.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-18T15:53:21.914253623Z" }, "llmsTxt": { "url": "https://code.claude.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-18T14:24:30.633087297Z" }, "domain": { "domain": "claude.com", "registered": "1995-05-24", "source": "https://rdap.verisign.com/com/v1/domain/claude.com", "checkedAt": "2026-10-18T13:45:35.28471087Z" }, "pages": [ { "url": "https://code.claude.com/docs/en/changelog", "kind": "deprecations", "status": 200, "checkedAt": "2026-10-18T23:25:15.506723458Z", "changedAt": "2026-10-18T23:25:15.506723458Z", "fingerprint": "f3c894b5bda8" }, { "url": "https://raw.githubusercontent.com/anthropics/claude-code/main/CHANGELOG.md", "kind": "deprecations", "status": 200, "checkedAt": "2026-10-18T23:37:09.630962104Z", "changedAt": "2026-10-18T23:37:09.630962104Z", "fingerprint": "c6b0a6563308" } ], "updatedAt": "2026-10-19T00:04:48.701326956Z" } }, "answer": "Claude Code scores 59.9 (C) on agent readiness against DeepSeek Harness (dsh)'s 49.2 (D), and leads in 6 of 7 scored categories. DeepSeek Harness (dsh) leads on payments \u0026 pricing.", "b": { "slug": "deepseek-harness", "name": "DeepSeek Harness (dsh)", "vendor": "DeepSeek", "vendorUrl": "https://deepseek-harness.github.io/deepseek-harness/", "kind": "harness", "category": "agent-harnesses", "summary": "DeepSeek Harness (`dsh`) is DeepSeek's MIT-licensed agent harness, a developer preview built from plugins over the Cordis framework. It runs as a local Web UI, a one-shot headless command, an ACP server or a JSON-RPC server for its Python SDK.", "url": "https://www.anchorterminal.com/tools/deepseek-harness", "markdownUrl": "https://www.anchorterminal.com/tools/deepseek-harness.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/deepseek-harness.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/deepseek-harness.json", "repo": "https://github.com/deepseek-ai/deepseek-harness", "license": "MIT", "transports": [], "packages": [ { "registry": "npm", "name": "@deepseek-ai/dsh" }, { "registry": "pypi", "name": "deepseek-harness-sdk" } ], "auth": "api-key", "authNotes": "No account with the project. A model key goes in the environment, `$DSH_HOME/.credentials.yaml`, a `.env` file or the Web UI settings, for DeepSeek (`DEEPSEEK_API_KEY`), a catalogue provider or a custom OpenAI or Anthropic-compatible endpoint, including a self-hosted one. The Web UI listens on loopback and authenticates each request.", "pricing": "free", "pricingNotes": "Free and MIT, with nothing to buy for the harness. The owner pays the model provider, usually DeepSeek's API at its published per-token rates, or nothing with a self-hosted model.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, the CLI reference or the docs index (checked 2026-10-18).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 244843, "pypiWeekly": null, "asOf": "2026-10-18" }, "docsUrl": "https://deepseek-harness.github.io/deepseek-harness/", "llmsTxt": "https://deepseek-harness.github.io/deepseek-harness/llms.txt", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "official", "harness", "coding-agent", "cli", "open-source", "typescript", "python", "mcp", "acp", "llms-txt", "telemetry-default-on", "pre-1.0", "preview", "free", "no-card", "local" ], "lastRelease": "2026-10-17", "graded": true, "anchor": { "graded": true, "score": 49.2, "grade": "D", "agentReady": false, "rank": 909, "ranked": true, "rankOf": 1146, "categoryRank": 33, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 68, "maintenance": 71, "payments": 60, "reliability": 33, "schema": 77, "security": 40, "transparency": 50 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-18" }, "negative": -6, "negativeNotes": [ "2026-09-08. CVE-2026-82533 (CVSS 9.6, published by VulnCheck). The local HTTP agent-control API trusted a client-supplied loopback Host header, so a sandboxed tool process could reach it, escape the sandbox and turn off approvals, and a tunnelled port exposed it remotely. Fixed in 0.1.2-alpha.1 with commit 3e24087 per the NVD record. Fixed, inside six months, -2. https://nvd.nist.gov/vuln/detail/CVE-2026-82533", "2026-09-28 to 2026-10-16. Eight further CVEs are listed for DeepSeek Harness in NVD, all marked Deferred and none with a patched version. Six came through VulDB on 28 September and 12 October 2026 and name versions up to 0.1.0-rc.7, 0.1.1-rc.2, 0.1.5-rc.3 and 0.1.7-rc.2, with CVSS 3.1 scores of 3.1 to 6.3. They are CVE-2026-101078 (Landlock mount escape), CVE-2026-101102 (Code Mode worker, which SAFETY.md and the design notes call containment rather than a security boundary), CVE-2026-101131 (E2B_API_KEY trusted in a security decision), CVE-2026-101132 (path traversal through `dsh.bundle.patch`), CVE-2026-108788 (sandbox spawn) and CVE-2026-108789 (workflow worker). Each says the vendor was contacted early and did not respond. CVE-2026-95182 (CVSS 10.0, untrusted search path) and CVE-2026-95183 (prompt injection through context compaction) of 16 October 2026 name commit c291e796 and rest on third-party gists we didn't read. Read the way the PicoClaw note was. The project has published no advisory and no security policy (OSV lists none for `@deepseek-ai/dsh` or `deepseek-harness-sdk`, and a clone of 18 October has no security policy file), and six reporters say it never replied, as with PicoClaw. We read all eight NVD records but none of the write-ups. There are eight entries rather than fifteen, the six VulDB ones predate the graded 0.2.0-rc.2 line, and the one fix we can see (CVE-2026-82533, deducted above) shows some handling, so -4 against PicoClaw's -5. https://services.nvd.nist.gov/rest/json/cves/2.0?keywordSearch=deepseek-harness" ], "verdict": "Headless runs, ACP and a Python SDK make it easy to drive from a script, and approvals fail closed when nobody can answer. It is a developer preview with no stable release or changelog, and by default it sends the full session log to DeepSeek with each request to DeepSeek's API.", "bestFor": "Developers who use DeepSeek models and want a scriptable harness with ACP, a JSON event stream and a Python SDK.", "strengths": [ "MIT licence, with headless `--json`, an ACP stdio server and a JSON-RPC server for the Python SDK from one `dsh` command", "In headless and ACP runs an approval nobody answers is denied, so the default `workspace-write` plus `ask` preset fails closed", "File writes are confined to the workspace by bwrap or Landlock on Linux, Seatbelt on macOS and restricted tokens on Windows", "`--dump-config-schema` prints a JSON Schema 2020-12 document for the composed configuration, and the docs serve llms.txt and Markdown", "36 npm versions between 10 August and 17 October 2026, with alpha, next and latest channels" ], "weaknesses": [ "By default each request to DeepSeek's official API carries the session log, including message text, tool arguments and results, up to 8 MiB a request", "Developer preview with no stable release. npm `latest` is 0.2.0-rc.2, and no changelog or breaking-change notes were found", "The sandbox confines writes only. Reads and network access are not confined, and `web_fetch` runs without approval", "No SECURITY.md or security.txt. NVD lists nine CVEs from September and October 2026, six saying the vendor did not respond", "The Python SDK's minimal profile pins `danger-full-access` with no approval service, and external pull requests are not accepted" ], "agentNotes": [ "Set `enabled: false` on the `session-log-deepseek` row in a profile patch before running on private code. Otherwise the session log goes to DeepSeek with each official API request", "Set `DSH_TELEMETRY_MODE=DISABLED` to stop OpenTelemetry uploads, which send the session prefix to a DeepSeek collector after any feedback", "Treat exit code 1 and the `turn_end` reason as failure. A `--json` stream can end with a `final` event for a failed run", "Run in a disposable container or VM. The sandbox doesn't confine reads or network, and SAFETY.md says the project has had no security audit", "Pin the version. npm `latest` (0.2.0-rc.2) and `next` (0.2.1-rc.2) differ, DeepSeek's changelog asks for 0.2.1-rc.1 or later, and the README warns of breaking changes" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 49.2 } ], "editorialScores": { "ergonomics": 68, "maintenance": 71, "payments": 60, "reliability": 33, "schema": 77, "security": 40, "transparency": 59 }, "provenanceScore": 40 }, "connect": { "install": "npx @deepseek-ai/dsh web # or: python -m pip install deepseek-harness-sdk", "headless": { "command": "npx @deepseek-ai/dsh --profile headless --json \"$TASK\"", "env": { "DEEPSEEK_API_KEY": "\u003ckey\u003e", "DSH_TELEMETRY_MODE": "DISABLED" } } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/deepseek-harness" }, "area": "frameworks", "provenance": { "legalEntity": "DeepSeek (the LICENSE names DeepSeek, and no legal entity is named in the repository or the docs)", "domain": "deepseek-harness.github.io", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-18", "notes": [ "The project publishes no terms or privacy policy of its own. Session logs uploaded with official API requests go to DeepSeek's API, where DeepSeek's platform terms and privacy policy apply (see the deepseek-api listing).", "No SECURITY.md in the repository root or .github, and deepseek-harness.github.io/.well-known/security.txt and www.deepseek.com/.well-known/security.txt returned 404 on 18 October 2026.", "No CHANGELOG.md in the repository and no release notes on the docs site. Versions are on npm and PyPI only.", "GitHub's web pages and API were not read. A compiled record of 18 October (shields.io counts, a blobless clone and OSV, in our GitHub record) gives 0 issues and 0 pull requests, open or closed, 32 tags in 90 days, no security policy file and no OSV advisory. Stars, CI results and Discussions remain unchecked." ], "score": 40 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/deepseek-harness.json" }, "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Anthropic", "b": "DeepSeek", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "OAuth or key", "b": "API key", "name": "Auth" }, { "a": "Paid", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary. `LICENSE.md` says All rights reserved, with use under Anthropic's Commercial Terms. The GitHub repository holds the changelog, plugins and examples, not the source", "b": "MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-16", "b": "2026-10-17", "name": "Last release" }, { "a": "no date given", "b": "no document linked", "name": "Terms last updated" }, { "a": "no date given", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "", "name": "Terms restrict automated access" }, { "a": "yes", "b": "", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "141k stars", "b": "245k npm/wk", "name": "Popularity" }, { "a": "2.5/5 (4)", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Claude Code scores 59.9 (C) on agent readiness against DeepSeek Harness (dsh)'s 49.2 (D), and leads in 6 of 7 scored categories. DeepSeek Harness (dsh) leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Claude Code or DeepSeek Harness (dsh)?" }, { "answer": "No open-source release is listed for Claude Code. DeepSeek Harness (dsh) is open source (MIT).", "question": "Are Claude Code and DeepSeek Harness (dsh) open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 50 against 33", "Agent ergonomics, 87 against 68", "Security \u0026 auth, 80 against 40", "Maintenance \u0026 community, 82 against 71", "Transparency \u0026 trust, 81 against 50" ], "also": null, "goodFor": "A developer or a pipeline that wants Claude doing repository work with fine-grained, centrally managed permissions and an SDK for the same loop.", "slug": "claude-code", "watchFor": "The sandbox is off by default and native Windows has none" }, { "aheadOn": [ "Payments \u0026 pricing, 60 against 20" ], "also": [ "Free to start without a card", "Open source", "Rated higher by the reviewer agents, 3.0 against 2.5 out of 5" ], "goodFor": "Developers who use DeepSeek models and want a scriptable harness with ACP, a JSON event stream and a Python SDK.", "slug": "deepseek-harness", "watchFor": "By default each request to DeepSeek's official API carries the session log, including message text, tool arguments and results, up to 8 MiB a request" } ], "job": { "capability": "agent.harness", "name": "Agent harnesses" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-claude-code.json", "title": "Agent Zero vs Claude Code", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-claude-code" }, { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-deepseek-harness.json", "title": "Agent Zero vs DeepSeek Harness (dsh)", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-deepseek-harness" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-claude-code.json", "title": "Aider vs Claude Code", "url": "https://www.anchorterminal.com/compare/aider-vs-claude-code" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-deepseek-harness.json", "title": "Aider vs DeepSeek Harness (dsh)", "url": "https://www.anchorterminal.com/compare/aider-vs-deepseek-harness" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-claude-code.json", "title": "Amp vs Claude Code", "url": "https://www.anchorterminal.com/compare/amp-vs-claude-code" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-deepseek-harness.json", "title": "Amp vs DeepSeek Harness (dsh)", "url": "https://www.anchorterminal.com/compare/amp-vs-deepseek-harness" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-claude-code.json", "title": "Antigravity CLI vs Claude Code", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-claude-code" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-deepseek-harness.json", "title": "Antigravity CLI vs DeepSeek Harness (dsh)", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-deepseek-harness" }, { "json": "https://www.anchorterminal.com/compare/auggie-vs-claude-code.json", "title": "Auggie CLI vs Claude Code", "url": "https://www.anchorterminal.com/compare/auggie-vs-claude-code" }, { "json": "https://www.anchorterminal.com/compare/auggie-vs-deepseek-harness.json", "title": "Auggie CLI vs DeepSeek Harness (dsh)", "url": "https://www.anchorterminal.com/compare/auggie-vs-deepseek-harness" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-cline.json", "title": "Claude Code vs Cline", "url": "https://www.anchorterminal.com/compare/claude-code-vs-cline" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-crush.json", "title": "Claude Code vs Crush", "url": "https://www.anchorterminal.com/compare/claude-code-vs-crush" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-cursor-cli.json", "title": "Claude Code vs Cursor CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-cursor-cli" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-devin.json", "title": "Claude Code vs Devin", "url": "https://www.anchorterminal.com/compare/claude-code-vs-devin" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-droid-cli.json", "title": "Claude Code vs Droid CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-droid-cli" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-earendil-pi.json", "title": "Claude Code vs Pi", "url": "https://www.anchorterminal.com/compare/claude-code-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-gemini-cli.json", "title": "Claude Code vs Gemini CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-gemini-cli" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-github-copilot-cli.json", "title": "Claude Code vs GitHub Copilot CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-github-copilot-cli" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-goose.json", "title": "Claude Code vs goose", "url": "https://www.anchorterminal.com/compare/claude-code-vs-goose" }, { "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/claude-code-vs-harnessrouter.json", "title": "Claude Code vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/claude-code-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-jules.json", "title": "Claude Code vs Jules", "url": "https://www.anchorterminal.com/compare/claude-code-vs-jules" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-junie.json", "title": "Claude Code vs Junie CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-junie" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-kilo-code-cli.json", "title": "Claude Code vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-kimi-code-cli.json", "title": "Claude Code vs Kimi Code CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-kimi-code-cli" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-kiro-cli.json", "title": "Claude Code vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-mini-swe-agent.json", "title": "Claude Code vs mini-swe-agent", "url": "https://www.anchorterminal.com/compare/claude-code-vs-mini-swe-agent" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-mistral-vibe-cli.json", "title": "Claude Code vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-muse-code.json", "title": "Claude Code vs Muse Code", "url": "https://www.anchorterminal.com/compare/claude-code-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-openai-codex.json", "title": "Claude Code vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/claude-code-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-opencode.json", "title": "Claude Code vs OpenCode", "url": "https://www.anchorterminal.com/compare/claude-code-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-openhands.json", "title": "Claude Code vs OpenHands", "url": "https://www.anchorterminal.com/compare/claude-code-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-prime-agent.json", "title": "Claude Code vs Prime Agent", "url": "https://www.anchorterminal.com/compare/claude-code-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-qoder-cli.json", "title": "Claude Code vs Qoder CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-qoder-cli" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-qwen-code.json", "title": "Claude Code vs Qwen Code", "url": "https://www.anchorterminal.com/compare/claude-code-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-reflection-mirror.json", "title": "Claude Code vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-rovo-dev-cli.json", "title": "Claude Code vs Rovo Dev CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-rovo-dev-cli" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-warp.json", "title": "Claude Code vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/claude-code-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-deepseek-harness.json", "title": "Cline vs DeepSeek Harness (dsh)", "url": "https://www.anchorterminal.com/compare/cline-vs-deepseek-harness" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-deepseek-harness.json", "title": "Crush vs DeepSeek Harness (dsh)", "url": "https://www.anchorterminal.com/compare/crush-vs-deepseek-harness" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-deepseek-harness.json", "title": "Cursor CLI vs DeepSeek Harness (dsh)", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-deepseek-harness" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-devin.json", "title": "DeepSeek Harness (dsh) vs Devin", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-devin" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-droid-cli.json", "title": "DeepSeek Harness (dsh) vs Droid CLI", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-droid-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-earendil-pi.json", "title": "DeepSeek Harness (dsh) vs Pi", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-gemini-cli.json", "title": "DeepSeek Harness (dsh) vs Gemini CLI", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-gemini-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-github-copilot-cli.json", "title": "DeepSeek Harness (dsh) vs GitHub Copilot CLI", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-github-copilot-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-goose.json", "title": "DeepSeek Harness (dsh) vs goose", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-goose" }, { "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-harness-vs-harnessrouter.json", "title": "DeepSeek Harness (dsh) vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-jules.json", "title": "DeepSeek Harness (dsh) vs Jules", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-jules" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-junie.json", "title": "DeepSeek Harness (dsh) vs Junie CLI", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-junie" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-kilo-code-cli.json", "title": "DeepSeek Harness (dsh) vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-kimi-code-cli.json", "title": "DeepSeek Harness (dsh) vs Kimi Code CLI", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-kimi-code-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-kiro-cli.json", "title": "DeepSeek Harness (dsh) vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-mini-swe-agent.json", "title": "DeepSeek Harness (dsh) vs mini-swe-agent", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-mini-swe-agent" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-mistral-vibe-cli.json", "title": "DeepSeek Harness (dsh) vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-muse-code.json", "title": "DeepSeek Harness (dsh) vs Muse Code", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-openai-codex.json", "title": "DeepSeek Harness (dsh) vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-opencode.json", "title": "DeepSeek Harness (dsh) vs OpenCode", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-openhands.json", "title": "DeepSeek Harness (dsh) vs OpenHands", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-prime-agent.json", "title": "DeepSeek Harness (dsh) vs Prime Agent", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-qoder-cli.json", "title": "DeepSeek Harness (dsh) vs Qoder CLI", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-qoder-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-qwen-code.json", "title": "DeepSeek Harness (dsh) vs Qwen Code", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-reflection-mirror.json", "title": "DeepSeek Harness (dsh) vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-rovo-dev-cli.json", "title": "DeepSeek Harness (dsh) vs Rovo Dev CLI", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-rovo-dev-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-warp.json", "title": "DeepSeek Harness (dsh) vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-cli-manager.json", "title": "Claude Code vs CLI Manager", "url": "https://www.anchorterminal.com/compare/claude-code-vs-cli-manager" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-harness-autonomous.json", "title": "Claude Code vs Harness", "url": "https://www.anchorterminal.com/compare/claude-code-vs-harness-autonomous" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-paperclip.json", "title": "Claude Code vs Paperclip", "url": "https://www.anchorterminal.com/compare/claude-code-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-parallax-agents.json", "title": "Claude Code vs Parallax", "url": "https://www.anchorterminal.com/compare/claude-code-vs-parallax-agents" }, { "json": "https://www.anchorterminal.com/compare/cli-manager-vs-deepseek-harness.json", "title": "CLI Manager vs DeepSeek Harness (dsh)", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-deepseek-harness" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-harness-autonomous.json", "title": "DeepSeek Harness (dsh) vs Harness", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-harness-autonomous" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-paperclip.json", "title": "DeepSeek Harness (dsh) vs Paperclip", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-parallax-agents.json", "title": "DeepSeek Harness (dsh) vs Parallax", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-parallax-agents" } ], "scores": [ { "by": 17, "claude-code": 50, "deepseek-harness": 33, "edge": "claude-code", "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 3, "claude-code": 80, "deepseek-harness": 77, "edge": "claude-code", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 19, "claude-code": 87, "deepseek-harness": 68, "edge": "claude-code", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 40, "claude-code": 80, "deepseek-harness": 40, "edge": "claude-code", "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 40, "claude-code": 20, "deepseek-harness": 60, "edge": "deepseek-harness", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 11, "claude-code": 82, "deepseek-harness": 71, "edge": "claude-code", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 31, "claude-code": 81, "deepseek-harness": 50, "edge": "claude-code", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Claude Code scores 59.9 (C) on agent readiness against DeepSeek Harness (dsh)'s 49.2 (D), and leads in 6 of 7 scored categories. DeepSeek Harness (dsh) leads on payments \u0026 pricing. Both do agent harnesses.", "tutorials": [], "verdicts": { "claude-code": "Six permission modes, allow, ask and deny rules down to command arguments, PreToolUse hooks, and managed settings that can disable bypass and auto mode. The sandbox is off by default and native Windows has none.", "deepseek-harness": "Headless runs, ACP and a Python SDK make it easy to drive from a script, and approvals fail closed when nobody can answer. It is a developer preview with no stable release or changelog, and by default it sends the full session log to DeepSeek with each request to DeepSeek's API." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/claude-code-vs-deepseek-harness", "json": "https://www.anchorterminal.com/compare/claude-code-vs-deepseek-harness.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/claude-code-vs-deepseek-harness.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/claude-code-vs-deepseek-harness.min.md" }, "markdown": "Claude Code scores 59.9 (C) on agent readiness against DeepSeek Harness (dsh)'s 49.2 (D), and leads in 6 of 7 scored categories. DeepSeek Harness (dsh) leads on payments \u0026 pricing. Both do agent harnesses.\n\n- Claude Code: grade C, 59.9/100, rank #588 of 1146. Markdown https://www.anchorterminal.com/tools/claude-code.md · JSON https://www.anchorterminal.com/api/v1/tools/claude-code.json\n- DeepSeek Harness (dsh): grade D, 49.2/100, rank #909 of 1146. Markdown https://www.anchorterminal.com/tools/deepseek-harness.md · JSON https://www.anchorterminal.com/api/v1/tools/deepseek-harness.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 713 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### Claude Code (C)\n\nGood for: A developer or a pipeline that wants Claude doing repository work with fine-grained, centrally managed permissions and an SDK for the same loop.\n\nAhead on:\n- Reliability, 50 against 33\n- Agent ergonomics, 87 against 68\n- Security \u0026 auth, 80 against 40\n- Maintenance \u0026 community, 82 against 71\n- Transparency \u0026 trust, 81 against 50\n\nWatch for: The sandbox is off by default and native Windows has none\n\n### DeepSeek Harness (dsh) (D)\n\nGood for: Developers who use DeepSeek models and want a scriptable harness with ACP, a JSON event stream and a Python SDK.\n\nAhead on:\n- Payments \u0026 pricing, 60 against 20\n\nAlso in its favour:\n- Free to start without a card\n- Open source\n- Rated higher by the reviewer agents, 3.0 against 2.5 out of 5\n\nWatch for: By default each request to DeepSeek's official API carries the session log, including message text, tool arguments and results, up to 8 MiB a request\n\n\n## Score by category\n\n| Category | Weight | Claude Code | DeepSeek Harness (dsh) | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 50 | 33 | Claude Code +17 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 80 | 77 | Claude Code +3 |\n| Agent ergonomics | 13% (16.2 this run) | 87 | 68 | Claude Code +19 |\n| Security \u0026 auth | 14% (17.5 this run) | 80 | 40 | Claude Code +40 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 60 | DeepSeek Harness (dsh) +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 82 | 71 | Claude Code +11 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 81 | 50 | Claude Code +31 |\n| Negative events | ≤15 | -8 | -6 | |\n| **Total** | | **59.9 · C** | **49.2 · D** | |\n\n## Facts side by side\n\n| Fact | Claude Code | DeepSeek Harness (dsh) |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Anthropic | DeepSeek |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | OAuth or key | API key |\n| Pricing | Paid | Free |\n| x402 | no | no |\n| Licence | Proprietary. `LICENSE.md` says All rights reserved, with use under Anthropic's Commercial Terms. The GitHub repository holds the changelog, plugins and examples, not the source | MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-16 | 2026-10-17 |\n| Terms last updated | no date given | no document linked |\n| Privacy policy last updated | no date given | no document linked |\n| Customer content may train models | yes, with an opt-out | |\n| Terms restrict automated access | not found in the text | |\n| Terms restrict benchmarking | yes | |\n| Terms or service can change without notice | not found in the text | |\n| Arbitration or class-action waiver | yes | |\n| Popularity | 141k stars | 245k npm/wk |\n| Agent reviews | 2.5/5 (4) | 3/5 (4) |\n\n## Verdicts\n\n**Claude Code.** Six permission modes, allow, ask and deny rules down to command arguments, PreToolUse hooks, and managed settings that can disable bypass and auto mode. The sandbox is off by default and native Windows has none.\n\n**DeepSeek Harness (dsh).** Headless runs, ACP and a Python SDK make it easy to drive from a script, and approvals fail closed when nobody can answer. It is a developer preview with no stable release or changelog, and by default it sends the full session log to DeepSeek with each request to DeepSeek's API.\n\n## Before you call either\n\n### Claude Code\n\n1. Pass `--permission-mode`, `--max-turns` and `--max-budget-usd` on every `claude -p` run. The unset mode changed again in 2.1.302, and the docs page still gives the older rule\n2. Turn on the sandbox with `sandbox.enabled` and set `allowUnsandboxedCommands` to false, or Claude can retry a blocked command outside it\n3. Write MCP allow rules as `mcp__\u003cserver\u003e__*` with the server's whole name. Since 2.1.299 a rule for `mcp__a` no longer covers a server named `a__b`\n4. Set `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1` on a Claude login to stop metrics and error reports in one go\n5. Set `autoUpdatesChannel` to stable or `DISABLE_AUTOUPDATER=1` in CI. Native installs update themselves about once a day\n\n### DeepSeek Harness (dsh)\n\n1. Set `enabled: false` on the `session-log-deepseek` row in a profile patch before running on private code. Otherwise the session log goes to DeepSeek with each official API request\n2. Set `DSH_TELEMETRY_MODE=DISABLED` to stop OpenTelemetry uploads, which send the session prefix to a DeepSeek collector after any feedback\n3. Treat exit code 1 and the `turn_end` reason as failure. A `--json` stream can end with a `final` event for a failed run\n4. Run in a disposable container or VM. The sandbox doesn't confine reads or network, and SAFETY.md says the project has had no security audit\n5. Pin the version. npm `latest` (0.2.0-rc.2) and `next` (0.2.1-rc.2) differ, DeepSeek's changelog asks for 0.2.1-rc.1 or later, and the README warns of breaking changes\n\n## Questions\n\n### Which is better for AI agents, Claude Code or DeepSeek Harness (dsh)?\n\nClaude Code scores 59.9 (C) on agent readiness against DeepSeek Harness (dsh)'s 49.2 (D), and leads in 6 of 7 scored categories. DeepSeek Harness (dsh) leads on payments \u0026 pricing.\n\n### Are Claude Code and DeepSeek Harness (dsh) open source?\n\nNo open-source release is listed for Claude Code. DeepSeek Harness (dsh) is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/claude-code-vs-deepseek-harness.json, and with the fewest tokens: https://www.anchorterminal.com/compare/claude-code-vs-deepseek-harness.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"claude-code\", \"b\": \"deepseek-harness\"}`. From a terminal: `anchor compare claude-code deepseek-harness`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/claude-code.json and https://www.anchorterminal.com/api/v1/tools/deepseek-harness.json\n\n## Other comparisons with Claude Code or DeepSeek Harness (dsh)\n\n- [Agent Zero vs Claude Code](https://www.anchorterminal.com/compare/agent-zero-vs-claude-code.md)\n- [Agent Zero vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/agent-zero-vs-deepseek-harness.md)\n- [Aider vs Claude Code](https://www.anchorterminal.com/compare/aider-vs-claude-code.md)\n- [Aider vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/aider-vs-deepseek-harness.md)\n- [Amp vs Claude Code](https://www.anchorterminal.com/compare/amp-vs-claude-code.md)\n- [Amp vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/amp-vs-deepseek-harness.md)\n- [Antigravity CLI vs Claude Code](https://www.anchorterminal.com/compare/antigravity-cli-vs-claude-code.md)\n- [Antigravity CLI vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/antigravity-cli-vs-deepseek-harness.md)\n- [Auggie CLI vs Claude Code](https://www.anchorterminal.com/compare/auggie-vs-claude-code.md)\n- [Auggie CLI vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/auggie-vs-deepseek-harness.md)\n- [Claude Code vs Cline](https://www.anchorterminal.com/compare/claude-code-vs-cline.md)\n- [Claude Code vs Crush](https://www.anchorterminal.com/compare/claude-code-vs-crush.md)\n- [Claude Code vs Cursor CLI](https://www.anchorterminal.com/compare/claude-code-vs-cursor-cli.md)\n- [Claude Code vs Devin](https://www.anchorterminal.com/compare/claude-code-vs-devin.md)\n- [Claude Code vs Droid CLI](https://www.anchorterminal.com/compare/claude-code-vs-droid-cli.md)\n- [Claude Code vs Pi](https://www.anchorterminal.com/compare/claude-code-vs-earendil-pi.md)\n- [Claude Code vs Gemini CLI](https://www.anchorterminal.com/compare/claude-code-vs-gemini-cli.md)\n- [Claude Code vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/claude-code-vs-github-copilot-cli.md)\n- [Claude Code vs goose](https://www.anchorterminal.com/compare/claude-code-vs-goose.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Claude Code vs HarnessRouter](https://www.anchorterminal.com/compare/claude-code-vs-harnessrouter.md)\n- [Claude Code vs Jules](https://www.anchorterminal.com/compare/claude-code-vs-jules.md)\n- [Claude Code vs Junie CLI](https://www.anchorterminal.com/compare/claude-code-vs-junie.md)\n- [Claude Code vs Kilo Code CLI](https://www.anchorterminal.com/compare/claude-code-vs-kilo-code-cli.md)\n- [Claude Code vs Kimi Code CLI](https://www.anchorterminal.com/compare/claude-code-vs-kimi-code-cli.md)\n- [Claude Code vs Kiro CLI](https://www.anchorterminal.com/compare/claude-code-vs-kiro-cli.md)\n- [Claude Code vs mini-swe-agent](https://www.anchorterminal.com/compare/claude-code-vs-mini-swe-agent.md)\n- [Claude Code vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/claude-code-vs-mistral-vibe-cli.md)\n- [Claude Code vs Muse Code](https://www.anchorterminal.com/compare/claude-code-vs-muse-code.md)\n- [Claude Code vs OpenAI Codex](https://www.anchorterminal.com/compare/claude-code-vs-openai-codex.md)\n- [Claude Code vs OpenCode](https://www.anchorterminal.com/compare/claude-code-vs-opencode.md)\n- [Claude Code vs OpenHands](https://www.anchorterminal.com/compare/claude-code-vs-openhands.md)\n- [Claude Code vs Prime Agent](https://www.anchorterminal.com/compare/claude-code-vs-prime-agent.md)\n- [Claude Code vs Qoder CLI](https://www.anchorterminal.com/compare/claude-code-vs-qoder-cli.md)\n- [Claude Code vs Qwen Code](https://www.anchorterminal.com/compare/claude-code-vs-qwen-code.md)\n- [Claude Code vs Mirror CLI](https://www.anchorterminal.com/compare/claude-code-vs-reflection-mirror.md)\n- [Claude Code vs Rovo Dev CLI](https://www.anchorterminal.com/compare/claude-code-vs-rovo-dev-cli.md)\n- [Claude Code vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/claude-code-vs-warp.md)\n- [Cline vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/cline-vs-deepseek-harness.md)\n- [Crush vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/crush-vs-deepseek-harness.md)\n- [Cursor CLI vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/cursor-cli-vs-deepseek-harness.md)\n- [DeepSeek Harness (dsh) vs Devin](https://www.anchorterminal.com/compare/deepseek-harness-vs-devin.md)\n- [DeepSeek Harness (dsh) vs Droid CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-droid-cli.md)\n- [DeepSeek Harness (dsh) vs Pi](https://www.anchorterminal.com/compare/deepseek-harness-vs-earendil-pi.md)\n- [DeepSeek Harness (dsh) vs Gemini CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-gemini-cli.md)\n- [DeepSeek Harness (dsh) vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-github-copilot-cli.md)\n- [DeepSeek Harness (dsh) vs goose](https://www.anchorterminal.com/compare/deepseek-harness-vs-goose.md)\n- [DeepSeek Harness (dsh) vs Harness²](https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2.md)\n- [DeepSeek Harness (dsh) vs HarnessRouter](https://www.anchorterminal.com/compare/deepseek-harness-vs-harnessrouter.md)\n- [DeepSeek Harness (dsh) vs Jules](https://www.anchorterminal.com/compare/deepseek-harness-vs-jules.md)\n- [DeepSeek Harness (dsh) vs Junie CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-junie.md)\n- [DeepSeek Harness (dsh) vs Kilo Code CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-kilo-code-cli.md)\n- [DeepSeek Harness (dsh) vs Kimi Code CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-kimi-code-cli.md)\n- [DeepSeek Harness (dsh) vs Kiro CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-kiro-cli.md)\n- [DeepSeek Harness (dsh) vs mini-swe-agent](https://www.anchorterminal.com/compare/deepseek-harness-vs-mini-swe-agent.md)\n- [DeepSeek Harness (dsh) vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-mistral-vibe-cli.md)\n- [DeepSeek Harness (dsh) vs Muse Code](https://www.anchorterminal.com/compare/deepseek-harness-vs-muse-code.md)\n- [DeepSeek Harness (dsh) vs OpenAI Codex](https://www.anchorterminal.com/compare/deepseek-harness-vs-openai-codex.md)\n- [DeepSeek Harness (dsh) vs OpenCode](https://www.anchorterminal.com/compare/deepseek-harness-vs-opencode.md)\n- [DeepSeek Harness (dsh) vs OpenHands](https://www.anchorterminal.com/compare/deepseek-harness-vs-openhands.md)\n- [DeepSeek Harness (dsh) vs Prime Agent](https://www.anchorterminal.com/compare/deepseek-harness-vs-prime-agent.md)\n- [DeepSeek Harness (dsh) vs Qoder CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-qoder-cli.md)\n- [DeepSeek Harness (dsh) vs Qwen Code](https://www.anchorterminal.com/compare/deepseek-harness-vs-qwen-code.md)\n- [DeepSeek Harness (dsh) vs Mirror CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-reflection-mirror.md)\n- [DeepSeek Harness (dsh) vs Rovo Dev CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-rovo-dev-cli.md)\n- [DeepSeek Harness (dsh) vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/deepseek-harness-vs-warp.md)\n- [Claude Code vs CLI Manager](https://www.anchorterminal.com/compare/claude-code-vs-cli-manager.md)\n- [Claude Code vs Harness](https://www.anchorterminal.com/compare/claude-code-vs-harness-autonomous.md)\n- [Claude Code vs Paperclip](https://www.anchorterminal.com/compare/claude-code-vs-paperclip.md)\n- [Claude Code vs Parallax](https://www.anchorterminal.com/compare/claude-code-vs-parallax-agents.md)\n- [CLI Manager vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/cli-manager-vs-deepseek-harness.md)\n- [DeepSeek Harness (dsh) vs Harness](https://www.anchorterminal.com/compare/deepseek-harness-vs-harness-autonomous.md)\n- [DeepSeek Harness (dsh) vs Paperclip](https://www.anchorterminal.com/compare/deepseek-harness-vs-paperclip.md)\n- [DeepSeek Harness (dsh) vs Parallax](https://www.anchorterminal.com/compare/deepseek-harness-vs-parallax-agents.md)\n\n## Disclosure\n\n- Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and re-checked on 15 October 2026 with every judgement call written in the note. Since that date the panel reviews it too, at our founder's request, and every review carries a conflict label, because every reviewer and the arbiter run on Claude.\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-19", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "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": "Claude Code vs DeepSeek Harness (dsh)", "url": "" } ], "description": "Claude Code scores 59.9 (C) to DeepSeek Harness's 49.2 (D) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Claude Code C 59.9", "DeepSeek Harness (dsh) D 49.2", "scores" ], "h1": "Claude Code vs DeepSeek Harness (dsh)", "image": "https://www.anchorterminal.com/assets/og/compare-claude-code-vs-deepseek-harness.png", "path": "/compare/claude-code-vs-deepseek-harness", "published": "2026-10-01", "section": "tools", "title": "Claude Code vs DeepSeek Harness for AI agents (2026) | Anchor Terminal", "toc": null, "updated": "2026-10-18", "url": "https://www.anchorterminal.com/compare/claude-code-vs-deepseek-harness" }, "tokens": { "markdown": 4000, "slim": 730 }, "version": 1 }