{ "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" }, "tool": { "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 ยท 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" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 15, "points": 3, "reason": "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).", "checked": "2026-11-01" }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 61, "points": 9.91, "reason": "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).", "checked": "2026-11-01" }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 67, "points": 10.89, "reason": "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).", "checked": "2026-11-01" }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 33, "points": 5.78, "reason": "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).", "checked": "2026-11-01" }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 40, "points": 5, "reason": "Self-hosted rule, as for the other open-source harnesses. No payment protocol (0). Free under MIT with nothing to buy (20). No card for the software (20). An agent can't get started alone, because the setup needs a person to create a dedicated GitHub user account, accept the repository invitation and run `auth login` for the wrappers, which SETUP.md lists as operator steps. 0, as the other harnesses that need an account were read (0). The model provider is a separate purchase.", "checked": "2026-11-01" }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 34, "points": 2.98, "reason": "Published on 31 October 2026, within 30 days, read as the last published change since no tag or release was found (30). One publication, so not three releases in 90 days (0). Issues, pull requests and Discussions couldn't be read, and the README frames the code as a reference prototype adapted from an internal version (0). No official SDK or registry entry (0). Exact dependency pins and a lockfile, but no CI workflow found, and the docs pin DSH 0.2.1-rc.3 (23 October 2026) while npm `latest` is 0.2.1-rc.5 (29 October 2026) (4).", "checked": "2026-11-01" }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 52, "points": 4.55, "note": "editorial 51, provenance 52", "reason": "MIT, Copyright (c) 2026 DeepSeek Harness Team (30). The prototype has no data statement of its own. DeepSeek Harness's privacy policy (last updated 20 September 2026) names Hangzhou DeepSeek Artificial Intelligence Co., Ltd., says session logs are collected with official model services and may be used to train models with a right to opt out, and says custom model services aren't stored server-side. It agrees with DSH's session-log README, but neither is referred to from the prototype (12). No deprecation policy. The README says the published code differs from DeepSeek's internal version, and docs/006 warns that database migrations are one-way (3). Telemetry and the session-log upload are disclosed with opt-outs in DSH's own reference pages, not in this repository (6).", "checked": "2026-11-01" } ], "assessment": { "date": "2026-11-01", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "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).", "maintenance": "Published on 31 October 2026, within 30 days, read as the last published change since no tag or release was found (30). One publication, so not three releases in 90 days (0). Issues, pull requests and Discussions couldn't be read, and the README frames the code as a reference prototype adapted from an internal version (0). No official SDK or registry entry (0). Exact dependency pins and a lockfile, but no CI workflow found, and the docs pin DSH 0.2.1-rc.3 (23 October 2026) while npm `latest` is 0.2.1-rc.5 (29 October 2026) (4).", "payments": "Self-hosted rule, as for the other open-source harnesses. No payment protocol (0). Free under MIT with nothing to buy (20). No card for the software (20). An agent can't get started alone, because the setup needs a person to create a dedicated GitHub user account, accept the repository invitation and run `auth login` for the wrappers, which SETUP.md lists as operator steps. 0, as the other harnesses that need an account were read (0). The model provider is a separate purchase.", "reliability": "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).", "schema": "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).", "security": "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).", "transparency": "MIT, Copyright (c) 2026 DeepSeek Harness Team (30). The prototype has no data statement of its own. DeepSeek Harness's privacy policy (last updated 20 September 2026) names Hangzhou DeepSeek Artificial Intelligence Co., Ltd., says session logs are collected with official model services and may be used to train models with a right to opt out, and says custom model services aren't stored server-side. It agrees with DSH's session-log README, but neither is referred to from the prototype (12). No deprecation policy. The README says the published code differs from DeepSeek's internal version, and docs/006 warns that database migrations are one-way (3). Telemetry and the session-log upload are disclosed with opt-outs in DSH's own reference pages, not in this repository (6)." }, "sources": [ { "what": "README (research prototype notice, setup)", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/README.md", "seen": "2026-11-01" }, { "what": "SETUP.md (setup written for a coding agent)", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/SETUP.md", "seen": "2026-11-01" }, { "what": "LICENSE", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/LICENSE", "seen": "2026-11-01" }, { "what": "package.json (version, engines, dependencies)", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/package.json", "seen": "2026-11-01" }, { "what": "bundle patch (worker and router presets)", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/cordis.patch.yml", "seen": "2026-11-01" }, { "what": "example profile configuration", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/examples/profile.cordis.patch.yml", "seen": "2026-11-01" }, { "what": "docs/000 Philosophy", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/docs/000-philosophy.md", "seen": "2026-11-01" }, { "what": "docs/001 Domain model", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/docs/001-domain.md", "seen": "2026-11-01" }, { "what": "docs/002 Authorization", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/docs/002-authorization.md", "seen": "2026-11-01" }, { "what": "docs/003 Execution", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/docs/003-execution.md", "seen": "2026-11-01" }, { "what": "docs/004 Prompts", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/docs/004-prompts.md", "seen": "2026-11-01" }, { "what": "docs/005 Panel", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/docs/005-panel.md", "seen": "2026-11-01" }, { "what": "docs/006 Deployment (permissions, Management API, upgrades)", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/docs/006-deployment.md", "seen": "2026-11-01" }, { "what": "docs/007 Architecture (tests)", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/docs/007-architecture.md", "seen": "2026-11-01" }, { "what": "docs/008 Cookbook", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/docs/008-cookbook.md", "seen": "2026-11-01" }, { "what": "service script", "url": "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/scripts/dsh-superagent", "seen": "2026-11-01" }, { "what": "npm versions of @deepseek-ai/dsh", "url": "https://registry.npmjs.org/@deepseek-ai/dsh", "seen": "2026-11-01" }, { "what": "DSH session-log upload README", "url": "https://raw.githubusercontent.com/deepseek-ai/deepseek-harness/master/packages/session/session-log-deepseek/README.md", "seen": "2026-11-01" }, { "what": "DeepSeek Harness privacy policy", "url": "https://www.deepseek.com/en/harness/privacy/", "seen": "2026-11-01" }, { "what": "DeepSeek Harness terms of use", "url": "https://www.deepseek.com/en/harness/terms-of-use/", "seen": "2026-11-01" }, { "what": "DeepSeek Harness page", "url": "https://www.deepseek.com/en/harness/", "seen": "2026-11-01" }, { "what": "NVD keyword search", "url": "https://services.nvd.nist.gov/rest/json/cves/2.0?keywordSearch=superagent-prototype", "seen": "2026-11-01" }, { "what": "security.txt (404)", "url": "https://www.deepseek.com/.well-known/security.txt", "seen": "2026-11-01" }, { "what": "ChinaModelAPI report, repository creation time (secondary)", "url": "https://chinamodelapi.com/news/deepseek-superagent-open-source", "seen": "2026-11-01" }, { "what": "AlphaSignal report of 31 October 2026 (secondary)", "url": "https://alphasignal.ai/news/deepseek-releases-a-silent-coding-agent-that-works-without-bothering-you", "seen": "2026-11-01" } ], "openQuestions": [ "unchecked: the commit history, tags, stars, issues and CI results. github.com and api.github.com weren't reachable, so the listing check's one-commit finding stands unconfirmed", "firstReleased 2026-10-31 confirmed first-hand from the repository's git history (a bare clone, no checkout): one commit, 'feat: add the dsh-superagent research prototype', by DeepSeek Harness Team at 2026-10-31T20:05:39+08:00, no tags. GitHub's issues, pull requests and CI runs still couldn't be read", "unchecked: the companion article, Exploring Super-agent Design, published on WeChat (mp.weixin.qq.com), whose robots.txt disallows article paths. Benchmark figures reported from it are DeepSeek's and weren't read", "Whether the `superagent` profile created from the Web template keeps `session-log-deepseek` enabled. DSH says shipped profiles mount it, enabled by default, and the prototype's docs don't mention it. We didn't run the software", "Whether DSH's open CVEs (on the deepseek-harness listing) affect 0.2.1-rc.3, which the docs pin", "unchecked: whether a CI workflow exists under another file name in .github/workflows" ] }, "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 }, "scoreHistory": [ { "date": "2026-11-01", "grade": "E", "kind": "listed", "method": "0.7", "score": 42.1 } ] }, "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" ], "notable": [ "The README says it is a research prototype for reference only, not an official DeepSeek product, much of it written by coding agents, and not identical to DeepSeek's internal version (https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/README.md)", "docs/006 says both presets run with `danger-full-access` as the operator's OS user, that a worker can read the operator's home directory, and recommends a dedicated OS account (https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/docs/006-deployment.md)", "Proactive work defaults to `observe`, which records what the agent would accept without accepting it (https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/docs/002-authorization.md)", "The companion article, Exploring Super-agent Design, is on WeChat (mp.weixin.qq.com), whose robots.txt disallows article paths, so it wasn't read" ], "area": "frameworks", "details": [ { "label": "Roles", "value": "One main Session (`dsh-superagent-router` preset) evaluates Triggers and routes them. Each accepted Ticket gets an Executor Session (`worker-\u003cticket id\u003e`, `dsh-superagent-worker` preset) and its own directory, prepared by a team command such as `git worktree`" }, { "label": "Sources", "value": "GitHub (mentions of the agent account in Issues, pull requests and comments, with optional receive-all switches for new Issues, pull requests, comments and default-branch CI) and Feishu (optional, bot mentions and direct messages). github.com only; GitHub Enterprise Server isn't supported" }, { "label": "Authorization", "value": "Allowed lists per Source, an admission table, a bot list, rules for proactive work and an accept mode (`off`, `observe` by default, `auto`). Every Ticket records a Mandate under the Policy version that accepted it, revalidated before resuming" }, { "label": "Permissions", "value": "Both presets run `danger-full-access` as the operator's OS user. Command shims in `\u003cstateDir\u003e/worker-bin` route `gh` and `lark-cli` to the agent's accounts and block listed commands, which docs/003 calls defaults, not a security boundary" }, { "label": "Interfaces", "value": "Mentions on GitHub or Feishu, a web panel on 127.0.0.1 (port 3082 in the example), and a Management API under `/orchestrator/api/` that needs the `x-orchestrator-request: 1` header and a loopback Host" }, { "label": "Requirements", "value": "Node.js 22.19+ or 24+, pnpm, git 2.32+, Python 3.8+, tmux, GitHub CLI 2.48+, `@deepseek-ai/dsh@0.2.1-rc.3` (within `engines.dsh` ^0.2.1-alpha.2), a model provider for DSH, and a dedicated GitHub user account with write access" }, { "label": "Graded version", "value": "package.json 0.1.0 on the `main` branch, read on 1 November 2026. Not published to npm. No tag, release or changelog found" }, { "label": "Related listing", "value": "Runs on DeepSeek Harness (deepseek-harness), whose session-log upload, telemetry and CVE record apply to the runtime it runs on" } ], "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, "checks": [ { "check": "Legal entity named", "value": "DeepSeek (the LICENSE names the DeepSeek Harness Team; DeepSeek Harness's terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "github.com, no registry record we could read", "points": 0, "max": 15, "state": "no" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "nothing hosted, so the MIT licence stands in", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "read, states 8 of the 8 things a reader expects", "points": 10, "max": 10, "state": "ok" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "People named", "value": "1 named with their role, none with a public profile", "points": 7, "max": 10, "state": "part" }, { "check": "Support route", "value": "a support address, help pages", "points": 5, "max": 5, "state": "ok" } ], "policies": [ { "kind": "terms", "url": "", "state": "none-found", "points": 0, "max": 10 }, { "kind": "privacy", "url": "https://www.deepseek.com/en/harness/privacy/", "state": "read", "readAt": "2026-11-01", "statedDate": "2026-09-20", "words": 2648, "points": 10, "max": 10, "expected": [ { "key": "privacy.date", "label": "Gives the date it was last updated", "found": true, "quote": "Last Update: September 20th, 2026", "says": "Last updated 2026-09-20" }, { "key": "privacy.collected", "label": "Says what personal data is collected", "found": true, "quote": "We collect your Personal Data in three ways: Personal Data You Provide, Automatically Collected Personal Data, and Personal Data From Other Sources." }, { "key": "privacy.retention", "label": "Says how long data is kept", "found": true, "quote": "We retain Personal Data for as long as necessary to provide our Services and for the other purposes set out in this Privacy Policy.", "says": "For as long as needed, with no period named" }, { "key": "privacy.processors", "label": "Says who else receives the data", "found": true, "quote": "These tools and services are provided by third parties, and data is collected and processed directly by these third parties." }, { "key": "privacy.sale", "label": "Says whether personal data is sold or shared for advertising", "found": true, "quote": "Your Personal Data may be disclosed to third parties in connection with a corporate transaction, such as a merger, sale of assets or shares, reorganization, financing, change of control, or acquisition of all or a portion of our business." }, { "key": "privacy.rights", "label": "Says what rights people have over their data", "found": true, "quote": "the right to know whether and how we process your Personal Data;" }, { "key": "privacy.contact", "label": "Gives a privacy contact", "found": true, "quote": "If you have any questions about how we use your Personal Data, please contact harness-privacy@deepseek.com or click the \"Contact us\" button on the product interface.", "says": "harness-privacy@deepseek.com" }, { "key": "privacy.transfers", "label": "Says where data is transferred or stored", "found": true, "quote": "Where required, we will use appropriate safeguards for transferring Personal Data outside of certain countries, including for one or more of the purposes as set out in this Policy, we will do so in accordance with the requirements of applicable data protection laws." } ] } ] }, "humans": { "slug": "deepseek-superagent", "checked": "2026-11-01", "company": "DeepSeek", "people": [ { "name": "Liang Wenfeng", "role": "Founder and CEO, DeepSeek", "founder": true, "bio": "Liang Wenfeng is founder and chief executive of DeepSeek. Through High-Flyer, the quantitative hedge fund he co-founded, he built the large-scale computing infrastructure that later supported AI research and led to DeepSeek's creation in 2023. He studied at Zhejiang University, where his master's research was in machine vision.", "bioSources": [ "https://en.wikipedia.org/wiki/Liang_Wenfeng", "https://www.zju.edu.cn/english/2025/0313/c19573a3026836/page.htm" ], "page": "/people/liang-wenfeng/" } ], "peopleNote": "The repository names no people. The LICENSE says Copyright (c) 2026 DeepSeek Harness Team, and package.json gives the author as DeepSeek Harness Team with an address at dsh.dev, which didn't resolve on 1 November 2026, so it isn't listed. Liang Wenfeng is reused from the other DeepSeek listings (data/humans/deepseek-harness.json, checked 28 October 2026). Ownership and investors are left to be copied from those files. DeepSeek's news page and sitemap show nothing new since then. GitHub's pages weren't reachable, so contributors weren't read.", "companySocial": { "x": "https://x.com/deepseek_ai", "github": "https://github.com/deepseek-ai" }, "support": { "emails": [ "harness-service@deepseek.com" ], "urls": [ "https://github.com/deepseek-ai/dsh-superagent-prototype" ], "contactEmails": [ "harness-privacy@deepseek.com" ] }, "sources": [ "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/LICENSE", "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/package.json", "https://raw.githubusercontent.com/deepseek-ai/dsh-superagent-prototype/main/README.md", "https://www.deepseek.com/en/harness/terms-of-use/", "https://www.deepseek.com/en/harness/privacy/", "https://www.deepseek.com/sitemap.xml", "https://www.zju.edu.cn/english/2025/0313/c19573a3026836/page.htm" ], "ownership": { "status": "private", "checked": "2026-10-28", "sources": [ "https://www.deepseek.com/", "https://www.deepseek.com/news/", "https://the-decoder.com/deepseek-takes-outside-money-for-the-first-time-at-a-50-billion-valuation/", "https://eu.36kr.com/en/p/3856984071027329" ] } }, "pageJsonUrl": "https://www.anchorterminal.com/tools/deepseek-superagent.json" } }