{ "data": { "similar": [ { "grade": "B", "json": "https://www.anchorterminal.com/tools/nanoclaw.json", "name": "NanoClaw", "score": 68.3, "shared": [ "assistant.proactive", "assistant.messaging", "assistant.memory", "assistant.self-hosted", "agent.mcp-client", "assistant.accounts" ], "slug": "nanoclaw" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/hermes-agent.json", "name": "Hermes Agent", "score": 67.9, "shared": [ "assistant.proactive", "assistant.messaging", "assistant.accounts", "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "slug": "hermes-agent" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/openclaw.json", "name": "OpenClaw", "score": 67.1, "shared": [ "assistant.proactive", "assistant.messaging", "assistant.accounts", "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "slug": "openclaw" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/ironclaw.json", "name": "IronClaw", "score": 66.7, "shared": [ "assistant.proactive", "assistant.messaging", "assistant.accounts", "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "slug": "ironclaw" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/nanobot.json", "name": "nanobot", "score": 62.4, "shared": [ "assistant.proactive", "assistant.messaging", "assistant.memory", "assistant.self-hosted", "assistant.accounts", "agent.mcp-client" ], "slug": "nanobot" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/qwenpaw.json", "name": "QwenPaw", "score": 62.2, "shared": [ "assistant.proactive", "assistant.messaging", "assistant.accounts", "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "slug": "qwenpaw" } ], "tool": { "slug": "zeroclaw", "name": "ZeroClaw", "vendor": "ZeroClaw Labs", "vendorUrl": "https://www.zeroclaw.com", "kind": "harness", "category": "personal-assistants", "summary": "Open-source personal AI assistant from ZeroClaw Labs, shipped as one Rust binary the owner runs. It answers on chat, email and voice channels, calls tools and MCP servers, and keeps memory in local SQLite.", "url": "https://www.anchorterminal.com/tools/zeroclaw", "markdownUrl": "https://www.anchorterminal.com/tools/zeroclaw.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/zeroclaw.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/zeroclaw.json", "repo": "https://github.com/zeroclaw-labs/zeroclaw", "license": "MIT OR Apache-2.0", "transports": [], "packages": [ { "registry": "oci", "name": "ghcr.io/zeroclaw-labs/zeroclaw" } ], "auth": "none", "authNotes": "No account with the vendor. Model keys, bot tokens and mail passwords go in `~/.zeroclaw/config.toml` as encrypted secret fields, set through `zeroclaw config set`, the dashboard or the terminal UI. OpenAI Codex and Claude subscription tokens are accepted in place of API keys. Gateway clients pair first and then send `Authorization: Bearer \u003ctoken\u003e`, with token hashes kept in config (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/authentication.md).", "pricing": "free", "pricingNotes": "Free under MIT or Apache-2.0, with no subscription and no hosted seat (https://www.zeroclaw.com/). The owner pays the model provider, or nothing with a local model. ZeroRouter, the vendor's hosted beta model gateway, is optional and its prices were not read (checked 2026-10-12).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or the source at commit 6c0b1f9 (checked 2026-10-12).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 32965, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://docs.zeroclaw.com/master/en/introduction.html", "llmsTxt": "https://www.zeroclaw.com/llms.txt", "capabilities": [ "assistant.proactive", "assistant.messaging", "assistant.memory", "assistant.self-hosted", "assistant.accounts", "agent.mcp-client" ], "tags": [ "open-source", "self-hosted", "local", "free", "no-card", "rust", "mit", "apache-2.0", "pre-1.0", "no-telemetry", "mcp-client", "approvals", "acp", "docker", "llms-txt" ], "lastRelease": "2026-09-05", "graded": true, "anchor": { "graded": true, "score": 70.2, "grade": "BB", "agentReady": true, "rank": 161, "ranked": true, "rankOf": 986, "categoryRank": 1, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 80, "payments": 60, "reliability": 74, "schema": 82, "security": 76, "transparency": 64 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 74, "points": 14.8, "reason": "Read with the local-software lines, as software the owner runs. An install script that fetches a prebuilt binary, Homebrew, a ghcr.io image and source builds on Rust 1.96, with setup pages for Linux, macOS, Windows, FreeBSD, NixOS and Docker (20). The CI workflow runs on every push to master, and the three latest runs, on 11 October 2026, passed (25). 576 open issues and 384 open pull requests. The 30 newest bug reports carry labels and at least one comment within days, and several P1 reports from that week are open, among them a Telegram listener that can hang (#11608) and a memory leak in config paths (#11614) (15 of 25). Release notes carry a Breaking Changes section, but 0.8.4 and 0.8.5 are patch-level versions that removed settings and skill sources (10 of 15). Version 0.8.5, with v1.0 shown as planned on the home page (4 of 15)." }, { "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": 82, "points": 13.33, "reason": "Harness reading of the six lines, as the Goose dossier used. A running gateway serves an OpenAPI document at `/api/openapi.json` for what the docs call the currently documented subset, and `zeroclaw config schema` prints the full config schema, from which the published config reference is generated. We read neither from a running copy (18 of 25). An llms.txt on www.zeroclaw.com, and the docs are Markdown in the repository (10). The autonomy, sandboxing and YOLO pages say what each setting allows, when to use it and when not to (16 of 20). Typed TOML with enumerated levels, validation warnings and rejection of unknown values such as `read_only` (12 of 15). Worked config examples on most pages and a troubleshooting page, with no single error reference (12 of 15). Dated release notes, a blog post a release and a versioned config schema with automatic migration (14 of 15)." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 72, "points": 11.7, "reason": "Harness reading. MCP servers reach an agent only through its `mcp_bundles`, skills can load on demand in compact mode, and most built-in integrations are off until configured, though the built-in tool list is long (18 of 25). Daily and monthly cost budgets, history trimming and a 1 MB cap on Google Workspace output (15 of 20). A blocked call returns a tool error that names the policy, and the docs describe each failure path (15 of 20). Provider fallback chains, resumable procedure runs and approval timeouts that deny, with no idempotency guidance for sends (14 of 20). One binary and a guided quickstart, and `zeroclaw agent -a \u003calias\u003e -m` for one-shot runs, but a working config needs four sections and there is no SDK (10 of 15)." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 76, "points": 13.3, "reason": "Harness reading, with 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 docs state no telemetry, we found no vendor host in the source apart from the optional ZeroRouter provider, secrets are encrypted with ChaCha20-Poly1305 beside a 0600 key file on the same disk, and the gateway binds 127.0.0.1 with pairing on. Web search and page fetches run without approval (27). Supervised mode is the default, `always_ask` outranks full autonomy, prompts time out to a denial, and an OS sandbox is auto-detected, but sandboxed tools keep network egress, unattended runs skip the shell prompt and rely on the command policy, and an open report says `firejail_args` is never applied (#11594) (17). A guard scans for injection patterns with a default action of warn, trigger payloads are framed as untrusted, a leak detector redacts credentials in replies by default, and an empty peer set denies all senders. No guidance page on injection through mail or web content was found (10). Approval events and a runtime trace are logged, tool receipts are opt-in and not durable, and the docs state command execution is not audited (8). SECURITY.md with private reporting and response times, one advisory published, CodeQL, cargo-deny, a daily audit and build attestations. No bounty and no security.txt, and SECURITY.md and the README name different contacts (14)." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 60, "points": 7.5, "reason": "Read with the self-hosted rule. No payment protocol (0). Free under MIT or Apache-2.0 with nothing to buy for the assistant, so 20, 20 and 20 on the last three lines. It runs local models with no sign-up. ZeroRouter, the vendor's optional hosted model gateway, was not graded and its prices were not read." }, { "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": 80, "points": 7, "reason": "v0.8.5 was released on 5 September 2026, 37 days before this check (20 of 30). Three releases in the 90 days to 12 October, v0.8.3 on 16 July, v0.8.4 on 2 August and v0.8.5 on 5 September (20). Master had 200 commits between 25 September and 11 October, and bug reports from the last week carry priority labels, comments and linked fix pull requests, against 576 open issues and 384 open pull requests (20 of 25). Not an MCP server and no SDK. Release workflows publish the binary, a ghcr.io image and crates, AUR and Scoop packages, which we read as workflow files and did not confirm on the registries (11 of 15). cargo-deny, a daily advisory audit, a monthly outdated-dependency job, CodeQL, Trivy and SBOM workflows, with CI passing (9 of 10)." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 64, "points": 5.6, "note": "editorial 74, provenance 53", "reason": "MIT or Apache-2.0, with a CLA that leaves copyright with contributors (30). The docs map every state store, say what is sent to a model provider and list what to back up, and the site says there is no ZeroClaw cloud in between. There is no privacy policy or terms on zeroclaw.com, and no data statement was read for the hosted ZeroRouter beta that the `zerorouter` slot defaults to (16 of 30). Release notes name removed and deprecated settings, and SECURITY.md says only the latest minor line gets fixes. No deprecation policy with notice periods was found (10 of 20). The docs state there is no telemetry, and our source search found no vendor host beyond ZeroRouter. We did not audit every outbound call (18 of 20)." } ], "assessment": { "date": "2026-10-12", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "Harness reading. MCP servers reach an agent only through its `mcp_bundles`, skills can load on demand in compact mode, and most built-in integrations are off until configured, though the built-in tool list is long (18 of 25). Daily and monthly cost budgets, history trimming and a 1 MB cap on Google Workspace output (15 of 20). A blocked call returns a tool error that names the policy, and the docs describe each failure path (15 of 20). Provider fallback chains, resumable procedure runs and approval timeouts that deny, with no idempotency guidance for sends (14 of 20). One binary and a guided quickstart, and `zeroclaw agent -a \u003calias\u003e -m` for one-shot runs, but a working config needs four sections and there is no SDK (10 of 15).", "maintenance": "v0.8.5 was released on 5 September 2026, 37 days before this check (20 of 30). Three releases in the 90 days to 12 October, v0.8.3 on 16 July, v0.8.4 on 2 August and v0.8.5 on 5 September (20). Master had 200 commits between 25 September and 11 October, and bug reports from the last week carry priority labels, comments and linked fix pull requests, against 576 open issues and 384 open pull requests (20 of 25). Not an MCP server and no SDK. Release workflows publish the binary, a ghcr.io image and crates, AUR and Scoop packages, which we read as workflow files and did not confirm on the registries (11 of 15). cargo-deny, a daily advisory audit, a monthly outdated-dependency job, CodeQL, Trivy and SBOM workflows, with CI passing (9 of 10).", "payments": "Read with the self-hosted rule. No payment protocol (0). Free under MIT or Apache-2.0 with nothing to buy for the assistant, so 20, 20 and 20 on the last three lines. It runs local models with no sign-up. ZeroRouter, the vendor's optional hosted model gateway, was not graded and its prices were not read.", "reliability": "Read with the local-software lines, as software the owner runs. An install script that fetches a prebuilt binary, Homebrew, a ghcr.io image and source builds on Rust 1.96, with setup pages for Linux, macOS, Windows, FreeBSD, NixOS and Docker (20). The CI workflow runs on every push to master, and the three latest runs, on 11 October 2026, passed (25). 576 open issues and 384 open pull requests. The 30 newest bug reports carry labels and at least one comment within days, and several P1 reports from that week are open, among them a Telegram listener that can hang (#11608) and a memory leak in config paths (#11614) (15 of 25). Release notes carry a Breaking Changes section, but 0.8.4 and 0.8.5 are patch-level versions that removed settings and skill sources (10 of 15). Version 0.8.5, with v1.0 shown as planned on the home page (4 of 15).", "schema": "Harness reading of the six lines, as the Goose dossier used. A running gateway serves an OpenAPI document at `/api/openapi.json` for what the docs call the currently documented subset, and `zeroclaw config schema` prints the full config schema, from which the published config reference is generated. We read neither from a running copy (18 of 25). An llms.txt on www.zeroclaw.com, and the docs are Markdown in the repository (10). The autonomy, sandboxing and YOLO pages say what each setting allows, when to use it and when not to (16 of 20). Typed TOML with enumerated levels, validation warnings and rejection of unknown values such as `read_only` (12 of 15). Worked config examples on most pages and a troubleshooting page, with no single error reference (12 of 15). Dated release notes, a blog post a release and a versioned config schema with automatic migration (14 of 15).", "security": "Harness reading, with 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 docs state no telemetry, we found no vendor host in the source apart from the optional ZeroRouter provider, secrets are encrypted with ChaCha20-Poly1305 beside a 0600 key file on the same disk, and the gateway binds 127.0.0.1 with pairing on. Web search and page fetches run without approval (27). Supervised mode is the default, `always_ask` outranks full autonomy, prompts time out to a denial, and an OS sandbox is auto-detected, but sandboxed tools keep network egress, unattended runs skip the shell prompt and rely on the command policy, and an open report says `firejail_args` is never applied (#11594) (17). A guard scans for injection patterns with a default action of warn, trigger payloads are framed as untrusted, a leak detector redacts credentials in replies by default, and an empty peer set denies all senders. No guidance page on injection through mail or web content was found (10). Approval events and a runtime trace are logged, tool receipts are opt-in and not durable, and the docs state command execution is not audited (8). SECURITY.md with private reporting and response times, one advisory published, CodeQL, cargo-deny, a daily audit and build attestations. No bounty and no security.txt, and SECURITY.md and the README name different contacts (14).", "transparency": "MIT or Apache-2.0, with a CLA that leaves copyright with contributors (30). The docs map every state store, say what is sent to a model provider and list what to back up, and the site says there is no ZeroClaw cloud in between. There is no privacy policy or terms on zeroclaw.com, and no data statement was read for the hosted ZeroRouter beta that the `zerorouter` slot defaults to (16 of 30). Release notes name removed and deprecated settings, and SECURITY.md says only the latest minor line gets fixes. No deprecation policy with notice periods was found (10 of 20). The docs state there is no telemetry, and our source search found no vendor host beyond ZeroRouter. We did not audit every outbound call (18 of 20)." }, "sources": [ { "what": "repository master at commit 6c0b1f9 (shallow clone, 200 commits)", "url": "https://github.com/zeroclaw-labs/zeroclaw", "seen": "2026-10-12" }, { "what": "README", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/README.md", "seen": "2026-10-12" }, { "what": "security policy", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/SECURITY.md", "seen": "2026-10-12" }, { "what": "autonomy levels", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/autonomy.md", "seen": "2026-10-12" }, { "what": "security model and default posture", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/model.md", "seen": "2026-10-12" }, { "what": "sandboxing", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/sandboxing.md", "seen": "2026-10-12" }, { "what": "tool receipts", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/tool-receipts.md", "seen": "2026-10-12" }, { "what": "YOLO mode", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/getting-started/yolo.md", "seen": "2026-10-12" }, { "what": "authentication and principals", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/authentication.md", "seen": "2026-10-12" }, { "what": "channels overview", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/channels/overview.md", "seen": "2026-10-12" }, { "what": "email channels", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/channels/email.md", "seen": "2026-10-12" }, { "what": "peer groups", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/channels/peer-groups.md", "seen": "2026-10-12" }, { "what": "tools overview", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/tools/overview.md", "seen": "2026-10-12" }, { "what": "built-in tool inventory", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/developing/tool-inventory.md", "seen": "2026-10-12" }, { "what": "MCP client", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/tools/mcp.md", "seen": "2026-10-12" }, { "what": "runtime state and persistence", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/architecture/runtime-state-and-persistence.md", "seen": "2026-10-12" }, { "what": "memory and payload lifecycle", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/architecture/memory-payload-lifecycle.md", "seen": "2026-10-12" }, { "what": "memory backends decision record", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/architecture/decisions/ADR-005-pluggable-memory-backends.md", "seen": "2026-10-12" }, { "what": "provider catalogue, with ZeroRouter", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/providers/catalog.md", "seen": "2026-10-12" }, { "what": "network deployment and gateway binding", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/ops/network-deployment.md", "seen": "2026-10-12" }, { "what": "gateway API overview", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/gateway/api.md", "seen": "2026-10-12" }, { "what": "cost tracking", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/ops/cost-tracking.md", "seen": "2026-10-12" }, { "what": "ownership and telemetry statement", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/philosophy/you-own-it.md", "seen": "2026-10-12" }, { "what": "release verification", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/maintainers/release-verification.md", "seen": "2026-10-12" }, { "what": "config schema source, default auto-approve list and Google Workspace settings", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/crates/zeroclaw-config/src/schema.rs", "seen": "2026-10-12" }, { "what": "approval decision source", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/crates/zeroclaw-runtime/src/approval/mod.rs", "seen": "2026-10-12" }, { "what": "secret store source", "url": "https://github.com/zeroclaw-labs/zeroclaw/blob/master/crates/zeroclaw-config/src/secrets.rs", "seen": "2026-10-12" }, { "what": "releases and release notes", "url": "https://github.com/zeroclaw-labs/zeroclaw/releases", "seen": "2026-10-12" }, { "what": "published advisories, read from the GitHub API after the web page answered 504 twice", "url": "https://api.github.com/repos/zeroclaw-labs/zeroclaw/security-advisories", "seen": "2026-10-12" }, { "what": "repository metadata and star count (GitHub API)", "url": "https://api.github.com/repos/zeroclaw-labs/zeroclaw", "seen": "2026-10-12" }, { "what": "CI runs on master (GitHub API)", "url": "https://api.github.com/repos/zeroclaw-labs/zeroclaw/actions/workflows/ci.yml/runs?branch=master", "seen": "2026-10-12" }, { "what": "open bug reports (GitHub API)", "url": "https://api.github.com/repos/zeroclaw-labs/zeroclaw/issues?state=open\u0026labels=bug", "seen": "2026-10-12" }, { "what": "home page and FAQ", "url": "https://www.zeroclaw.com/", "seen": "2026-10-12" }, { "what": "llms.txt", "url": "https://www.zeroclaw.com/llms.txt", "seen": "2026-10-12" }, { "what": "security.txt, 404", "url": "https://www.zeroclaw.com/.well-known/security.txt", "seen": "2026-10-12" }, { "what": "blog index", "url": "https://www.zeroclaw.com/blog", "seen": "2026-10-12" }, { "what": "incident recap of 1 April 2026", "url": "https://www.zeroclaw.com/blog/community-and-stability", "seen": "2026-10-12" }, { "what": "domain registration (RDAP)", "url": "https://rdap.verisign.com/com/v1/domain/zeroclaw.com", "seen": "2026-10-12" } ], "openQuestions": [ "Kind is `harness`. ZeroClaw is a self-hosted agent program, and harness is the closest kind the briefs define. Reliability was read with the local-software lines and Payments with the self-hosted rule.", "The lead gave the licence as Apache-2.0. The repository is MIT or Apache-2.0 at the user's choice, and GitHub's API reports only Apache-2.0.", "unchecked: nothing was installed or run, so the approval prompts, the sandbox, the OpenAPI document and the quickstart defaults were read from docs and source only.", "unchecked: zerorouter.ai, the vendor's hosted beta model gateway, was not opened. Its prices, terms and data handling are unknown, as is whether quickstart preselects it.", "unchecked: the crates.io, Homebrew, AUR and Scoop packages were not looked up. Their existence rests on the docs and the release workflow files.", "unchecked: the advisories page on github.com answered 504 twice. The one published advisory was read from the GitHub API, and the full advisory text was not read.", "unchecked: the telemetry statement was checked by a search of the source for vendor hosts, not by an audit of every outbound call.", "The 1 April 2026 merge incident took 1 point. Whether any unreviewed merge reached a tagged release was not established.", "The site heading says shell access you can audit, while the docs say command execution is not audited and receipts are opt-in. Recorded as a weakness with no deduction.", "No company form or address for ZeroClaw Labs was found, and the site publishes no terms or privacy policy." ] }, "negative": -3, "negativeNotes": [ "2026-09-05. GHSA-93f6-34w8-5g98 (high), an unvalidated `wasm_path` let `zeroclaw plugin install` write an attacker-controlled file outside the plugins directory in 0.8.4 and earlier. Fixed in 0.8.5 and published the same day, inside six months, -2. https://github.com/zeroclaw-labs/zeroclaw/security/advisories/GHSA-93f6-34w8-5g98", "2026-04-01. The project lead wrote that a maintainer's AI automation merged pull requests that should not have gone through and that GitHub took enforcement action on the organisation. Disclosed, the maintainer removed and merge access tightened, over six months old, -1. https://www.zeroclaw.com/blog/community-and-stability" ], "verdict": "Supervised autonomy is the default, so tools outside a short read-only list wait for the owner's approval, and secrets are encrypted in the config file. The docs state that command execution is not written to an audit log, and the project publishes no privacy policy or terms.", "bestFor": "One person who wants an assistant on their own hardware that answers on Telegram, Discord, Matrix or email, asks before it writes or runs commands, and works with a local model.", "strengths": [ "Supervised mode is the default. Tools outside an eleven-item read-only and fetch list prompt the owner, and an unanswered prompt is a denial after 120 seconds", "Approval prompts arrive on the channel in use, and `approval_route` can send them to a separate approver channel that denies when unreachable", "Channel secrets and provider keys are encrypted with ChaCha20-Poly1305 in `config.toml`, with the key in `.secret_key` at mode 0600", "An empty peer set denies every inbound sender, and the gateway binds 127.0.0.1 with pairing required by default", "Three tagged releases in the 90 days to 12 October 2026, each with a Breaking Changes section, and CI passing on master on 11 October" ], "weaknesses": [ "The docs state that command execution is not audited. `[security.audit]` records certificate events only, and tool receipts are opt-in and not durable", "No privacy policy, terms or security.txt on zeroclaw.com, and the home page links none", "`web_fetch`, `web_search_tool` and `browser_open` run without approval by default, and sandboxed tools keep full network egress", "GHSA-93f6-34w8-5g98 (high) let a plugin install write outside the plugins directory in 0.8.4 and earlier, fixed in 0.8.5 on 5 September 2026", "Version 0.8.5 is pre-1.0, patch releases carry breaking changes, and 576 issues and 384 pull requests were open on 12 October 2026" ], "agentNotes": [ "Keep `[risk_profiles.\u003calias\u003e] level = \"supervised\"`. `full` runs every tool not listed in `always_ask`, and the YOLO preset removes the sandbox and path rules too", "Add sending and account tools such as `send_via`, `google_workspace` and `http_request` to `always_ask` so a session-level Always grant cannot skip the prompt", "List senders in `[peer_groups.\u003cname\u003e] external_peers`. `[\"*\"]` accepts anyone on that channel", "Set `[web_fetch].allowed_domains` and `[http_request].allowed_domains`. Fetches run unprompted and the OS sandbox does not block egress", "Run one-shot tasks with `zeroclaw agent -a \u003calias\u003e -m \"\u003ctask\u003e\"`. A cron or webhook turn has no prompt, so shell calls fall to the command policy" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 70.2 } ], "editorialScores": { "ergonomics": 72, "maintenance": 80, "payments": 60, "reliability": 74, "schema": 82, "security": 76, "transparency": 74 }, "provenanceScore": 53 }, "connect": { "install": "curl -fsSL https://raw.githubusercontent.com/zeroclaw-labs/zeroclaw/master/install.sh | sh # or: brew install zeroclaw", "headless": { "command": "zeroclaw agent -a \u003calias\u003e -m \"$TASK\"", "setup": "zeroclaw quickstart" } }, "letme": { "capability": "https://letme.dev/assistant.proactive", "tool": "https://letme.dev/zeroclaw" }, "notable": [ "Supervised autonomy is the default. Low-risk tools run, medium-risk tools ask the operator and high-risk calls are blocked (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/autonomy.md)", "The security model page says audit logging covers certificate issuance and renewal only and that command execution is not audited (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/model.md)", "One published advisory, GHSA-93f6-34w8-5g98 (high), published 5 September 2026. An unvalidated `wasm_path` let `zeroclaw plugin install` write outside the plugins directory in 0.8.4 and earlier, fixed in 0.8.5 (https://github.com/zeroclaw-labs/zeroclaw/security/advisories/GHSA-93f6-34w8-5g98)", "A post of 1 April 2026 by the project lead says a maintainer's AI automation merged pull requests that should not have gone through, that GitHub took enforcement action on the organisation, and that the maintainer was removed (https://www.zeroclaw.com/blog/community-and-stability)", "The licence is MIT or Apache-2.0 at the user's choice. GitHub's API reports only Apache-2.0 (https://github.com/zeroclaw-labs/zeroclaw/blob/master/README.md)", "Version 0.8.5 added a `zerorouter` provider slot that defaults to a hosted beta model gateway at zerorouter.ai (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/providers/catalog.md)", "The philosophy page says no telemetry, no cloud tenancy and no licence server (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/philosophy/you-own-it.md)", "The home page shows v1.0 as planned and says the v0.8.x line has shipped about monthly since June 2026 (https://www.zeroclaw.com/)" ], "area": "frameworks", "details": [ { "label": "Where it runs", "value": "One Rust binary on the owner's machine, VPS or single-board computer, as a CLI, a daemon or a system service. State lives under `~/.zeroclaw/` (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/architecture/runtime-state-and-persistence.md)" }, { "label": "Acts without asking", "value": "By default `file_read`, `memory_recall`, `web_search_tool`, `web_fetch`, `calculator`, `glob_search`, `content_search`, `image_info`, `weather`, `tool_search` and `browser_open` run unprompted. Replies to accepted senders are sent without a prompt. Every other tool asks (https://github.com/zeroclaw-labs/zeroclaw/blob/master/crates/zeroclaw-config/src/schema.rs)" }, { "label": "Approval controls", "value": "Three levels on a risk profile, `readonly`, `supervised` (default) and `full`. Per-tool `auto_approve`, `always_ask` and `excluded_tools`, a shell command allow list, optional one-time codes and `zeroclaw estop`. Prompts time out to a denial after 120 seconds (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/autonomy.md)" }, { "label": "Sandbox", "value": "Auto-detected. Landlock, Bubblewrap, Firejail or Docker on Linux, Seatbelt on macOS, AppContainer (experimental) on Windows. Files are confined to the workspace. Network egress stays open by default (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/sandboxing.md)" }, { "label": "Proactive work", "value": "Cron jobs the agent can create (`cron_add`), an optional heartbeat every 30 minutes that is off by default, and event-triggered procedures from MQTT, webhooks, cron and file changes" }, { "label": "Channels", "value": "The default build has ACP, webhook, email, Telegram, Discord and filesystem. Standard release builds add Git, Matrix, Lark and WhatsApp Web. Slack, Signal, LINE, Mattermost, iMessage, voice calls and others need compile-time flags. The site says 30+ (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/channels/overview.md)" }, { "label": "Who can message it", "value": "Senders are checked against `[peer_groups.\u003cname\u003e]`. An empty set denies everyone and `\"*\"` accepts anyone. The gateway requires a pairing token by default (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/channels/peer-groups.md)" }, { "label": "Accounts", "value": "Mail by IMAP and SMTP with an app password, or Gmail push with an OAuth token. Opt-in tools for Google Workspace (through the external `gws` CLI, all 14 services unless narrowed), Microsoft 365, Notion, Jira, LinkedIn and Composio" }, { "label": "Credential storage", "value": "Secret fields in `config.toml` are encrypted with ChaCha20-Poly1305. The key is `~/.zeroclaw/.secret_key`, mode 0600, on the same disk. Google Workspace credentials stay with the `gws` CLI (https://github.com/zeroclaw-labs/zeroclaw/blob/master/crates/zeroclaw-config/src/secrets.rs)" }, { "label": "Memory", "value": "SQLite under `data/memory/` by default, with Markdown, PostgreSQL, Qdrant and Lucid as alternatives. Conversation autosave is on by default. Session history is a separate SQLite file" }, { "label": "Deleting memory", "value": "`memory_forget` removes one entry and `memory_purge` a namespace or session. The Markdown backend is append-only and does not delete entries. Session history, logs and the cost ledger are separate files (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/architecture/decisions/ADR-005-pluggable-memory-backends.md)" }, { "label": "Model providers", "value": "Anthropic, OpenAI, Gemini, Bedrock, Azure OpenAI, Ollama and any OpenAI-compatible endpoint, with the owner's key. Prompts, recalled memory and tool results go to the chosen provider. The site says 70+ providers, the README about 20 others" }, { "label": "Other outbound traffic", "value": "The docs state no telemetry. Web search goes to DuckDuckGo by default. The `zerorouter` provider slot defaults to the vendor's hosted beta at zerorouter.ai when chosen" }, { "label": "MCP client", "value": "stdio, HTTP and SSE. A server reaches an agent only through that agent's `mcp_bundles`. Tools are named `\u003cserver\u003e__\u003ctool\u003e` (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/tools/mcp.md)" }, { "label": "Interfaces for other programs", "value": "Gateway REST and WebSocket on 127.0.0.1:42617 with an OpenAPI document at `/api/openapi.json`, ACP over stdio, and `zeroclaw agent -a \u003calias\u003e -m`" }, { "label": "Audit", "value": "Approval events and runtime logs go to `data/state/runtime-trace.jsonl`. Command execution is not audited. Tool receipts (HMAC-SHA256) are opt-in with an in-memory key (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/model.md)" }, { "label": "Cost", "value": "Free. The owner pays the model provider, or nothing with a local model. Daily and monthly budgets and a cost ledger are built in" }, { "label": "Releases in 90 days", "value": "3 (v0.8.3 on 16 July, v0.8.4 on 2 August, v0.8.5 on 5 September 2026)" } ], "provenance": { "legalEntity": "ZeroClaw Labs", "domain": "zeroclaw.com", "domainRegistered": "2026-03-02", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/zeroclaw-labs/zeroclaw/releases", "securityTxt": "none", "checked": "2026-10-12", "notes": [ "The NOTICE file reads Copyright 2025 ZeroClaw Labs and the blog signs posts as CEO, ZeroClaw Labs. No company form, registration or address was found on the site or in the repository.", "The home page of www.zeroclaw.com links no terms and no privacy policy, so both fields are empty and the MIT or Apache-2.0 licence stands in.", "www.zeroclaw.com/.well-known/security.txt answered 404 on 12 October 2026. SECURITY.md asks for GitHub private vulnerability reporting and the README gives security@zeroclaw.dev.", "RDAP gives zeroclaw.com a registration date of 2026-03-02, registrar Atom.com Domains LLC. The repository was created on 13 February 2026.", "There is no hosted endpoint for the assistant. A gateway answers on its owner's own host." ], "score": 53, "checks": [ { "check": "Legal entity named", "value": "ZeroClaw Labs", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "zeroclaw.com, registered 2026-03-02 (under a year)", "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 OR Apache-2.0 licence stands in", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "nothing hosted, not scored", "points": 0, "max": 0, "state": "na" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/zeroclaw.json" }, "verify": { "accepts": "a page on zeroclaw.com or one of its subdomains, or the README of github.com/zeroclaw-labs/zeroclaw", "badgeUrl": "https://www.anchorterminal.com/badges/zeroclaw.svg", "body": { "slug": "zeroclaw", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/zeroclaw", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/zeroclaw\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/zeroclaw.svg\" alt=\"ZeroClaw on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![ZeroClaw on Anchor Terminal](https://www.anchorterminal.com/badges/zeroclaw.svg)](https://www.anchorterminal.com/tools/zeroclaw)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/zeroclaw\"\u003eZeroClaw on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/zeroclaw", "json": "https://www.anchorterminal.com/tools/zeroclaw.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/zeroclaw.md", "slim": "https://www.anchorterminal.com/tools/zeroclaw.min.md" }, "markdown": "## Overview\n\n**Grade BB · 70.2/100 · rank #161 of 986 · #1 in Personal assistants · agent-ready · confidence medium**\n\n\n## Assessment\n\nSupervised autonomy is the default, so tools outside a short read-only list wait for the owner's approval, and secrets are encrypted in the config file. The docs state that command execution is not written to an audit log, and the project publishes no privacy policy or terms.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | ZeroClaw Labs (https://www.zeroclaw.com) |\n| Kind | Agent harness |\n| Category | Personal assistants (https://www.anchorterminal.com/categories/personal-assistants) |\n| Auth | None · No account with the vendor. Model keys, bot tokens and mail passwords go in `~/.zeroclaw/config.toml` as encrypted secret fields, set through `zeroclaw config set`, the dashboard or the terminal UI. OpenAI Codex and Claude subscription tokens are accepted in place of API keys. Gateway clients pair first and then send `Authorization: Bearer \u003ctoken\u003e`, with token hashes kept in config (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/authentication.md). |\n| Pricing | Free (Free · OSS) · Free under MIT or Apache-2.0, with no subscription and no hosted seat (https://www.zeroclaw.com/). The owner pays the model provider, or nothing with a local model. ZeroRouter, the vendor's hosted beta model gateway, is optional and its prices were not read (checked 2026-10-12). |\n| x402 | No · No x402, MPP or L402 in the docs or the source at commit 6c0b1f9 (checked 2026-10-12). |\n| Licence | MIT OR Apache-2.0 |\n| Packages | oci: `ghcr.io/zeroclaw-labs/zeroclaw` |\n| Source | https://github.com/zeroclaw-labs/zeroclaw |\n| Docs | https://docs.zeroclaw.com/master/en/introduction.html |\n| llms.txt | https://www.zeroclaw.com/llms.txt |\n| Last release | 2026-09-05 |\n| GitHub stars | 32,965 (as of 2026-10-12) |\n| Where it runs | One Rust binary on the owner's machine, VPS or single-board computer, as a CLI, a daemon or a system service. State lives under `~/.zeroclaw/` (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/architecture/runtime-state-and-persistence.md) |\n| Acts without asking | By default `file_read`, `memory_recall`, `web_search_tool`, `web_fetch`, `calculator`, `glob_search`, `content_search`, `image_info`, `weather`, `tool_search` and `browser_open` run unprompted. Replies to accepted senders are sent without a prompt. Every other tool asks (https://github.com/zeroclaw-labs/zeroclaw/blob/master/crates/zeroclaw-config/src/schema.rs) |\n| Approval controls | Three levels on a risk profile, `readonly`, `supervised` (default) and `full`. Per-tool `auto_approve`, `always_ask` and `excluded_tools`, a shell command allow list, optional one-time codes and `zeroclaw estop`. Prompts time out to a denial after 120 seconds (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/autonomy.md) |\n| Sandbox | Auto-detected. Landlock, Bubblewrap, Firejail or Docker on Linux, Seatbelt on macOS, AppContainer (experimental) on Windows. Files are confined to the workspace. Network egress stays open by default (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/sandboxing.md) |\n| Proactive work | Cron jobs the agent can create (`cron_add`), an optional heartbeat every 30 minutes that is off by default, and event-triggered procedures from MQTT, webhooks, cron and file changes |\n| Channels | The default build has ACP, webhook, email, Telegram, Discord and filesystem. Standard release builds add Git, Matrix, Lark and WhatsApp Web. Slack, Signal, LINE, Mattermost, iMessage, voice calls and others need compile-time flags. The site says 30+ (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/channels/overview.md) |\n| Who can message it | Senders are checked against `[peer_groups.\u003cname\u003e]`. An empty set denies everyone and `\"*\"` accepts anyone. The gateway requires a pairing token by default (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/channels/peer-groups.md) |\n| Accounts | Mail by IMAP and SMTP with an app password, or Gmail push with an OAuth token. Opt-in tools for Google Workspace (through the external `gws` CLI, all 14 services unless narrowed), Microsoft 365, Notion, Jira, LinkedIn and Composio |\n| Credential storage | Secret fields in `config.toml` are encrypted with ChaCha20-Poly1305. The key is `~/.zeroclaw/.secret_key`, mode 0600, on the same disk. Google Workspace credentials stay with the `gws` CLI (https://github.com/zeroclaw-labs/zeroclaw/blob/master/crates/zeroclaw-config/src/secrets.rs) |\n| Memory | SQLite under `data/memory/` by default, with Markdown, PostgreSQL, Qdrant and Lucid as alternatives. Conversation autosave is on by default. Session history is a separate SQLite file |\n| Deleting memory | `memory_forget` removes one entry and `memory_purge` a namespace or session. The Markdown backend is append-only and does not delete entries. Session history, logs and the cost ledger are separate files (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/architecture/decisions/ADR-005-pluggable-memory-backends.md) |\n| Model providers | Anthropic, OpenAI, Gemini, Bedrock, Azure OpenAI, Ollama and any OpenAI-compatible endpoint, with the owner's key. Prompts, recalled memory and tool results go to the chosen provider. The site says 70+ providers, the README about 20 others |\n| Other outbound traffic | The docs state no telemetry. Web search goes to DuckDuckGo by default. The `zerorouter` provider slot defaults to the vendor's hosted beta at zerorouter.ai when chosen |\n| MCP client | stdio, HTTP and SSE. A server reaches an agent only through that agent's `mcp_bundles`. Tools are named `\u003cserver\u003e__\u003ctool\u003e` (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/tools/mcp.md) |\n| Interfaces for other programs | Gateway REST and WebSocket on 127.0.0.1:42617 with an OpenAPI document at `/api/openapi.json`, ACP over stdio, and `zeroclaw agent -a \u003calias\u003e -m` |\n| Audit | Approval events and runtime logs go to `data/state/runtime-trace.jsonl`. Command execution is not audited. Tool receipts (HMAC-SHA256) are opt-in with an in-memory key (https://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/model.md) |\n| Cost | Free. The owner pays the model provider, or nothing with a local model. Daily and monthly budgets and a cost ledger are built in |\n| Releases in 90 days | 3 (v0.8.3 on 16 July, v0.8.4 on 2 August, v0.8.5 on 5 September 2026) |\n| Capabilities | assistant.proactive, assistant.messaging, assistant.memory, assistant.self-hosted, assistant.accounts, agent.mcp-client |\n| Tags | open-source, self-hosted, local, free, no-card, rust, mit, apache-2.0, pre-1.0, no-telemetry, mcp-client, approvals, acp, docker, llms-txt |\n| JSON | https://www.anchorterminal.com/api/v1/tools/zeroclaw.json |\n\n## Score breakdown (methodology v0.4, October 2026 research run)\n\nAssessed 2026-10-12 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 74 | 14.8 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 82 | 13.3 |\n| Agent ergonomics | 13% | 16.2 | 72 | 11.7 |\n| Security \u0026 auth | 14% | 17.5 | 76 | 13.3 |\n| Payments \u0026 pricing | 10% | 12.5 | 60 | 7.5 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 80 | 7.0 |\n| Transparency \u0026 trust (editorial 74, provenance 53) | 7% | 8.8 | 64 | 5.6 |\n| Negative events | up to −15 | up to −15 | 2026-09-05. GHSA-93f6-34w8-5g98 (high), an unvalidated `wasm_path` let `zeroclaw plugin install` write an attacker-controlled file outside the plugins directory in 0.8.4 and earlier. Fixed in 0.8.5 and published the same day, inside six months, -2. https://github.com/zeroclaw-labs/zeroclaw/security/advisories/GHSA-93f6-34w8-5g98 2026-04-01. The project lead wrote that a maintainer's AI automation merged pull requests that should not have gone through and that GitHub took enforcement action on the organisation. Disclosed, the maintainer removed and merge access tightened, over six months old, -1. https://www.zeroclaw.com/blog/community-and-stability | -3 |\n| **Total** | | | | **70.2 → BB** |\n\n### Why each score\n\n- Reliability 74: Read with the local-software lines, as software the owner runs. An install script that fetches a prebuilt binary, Homebrew, a ghcr.io image and source builds on Rust 1.96, with setup pages for Linux, macOS, Windows, FreeBSD, NixOS and Docker (20). The CI workflow runs on every push to master, and the three latest runs, on 11 October 2026, passed (25). 576 open issues and 384 open pull requests. The 30 newest bug reports carry labels and at least one comment within days, and several P1 reports from that week are open, among them a Telegram listener that can hang (#11608) and a memory leak in config paths (#11614) (15 of 25). Release notes carry a Breaking Changes section, but 0.8.4 and 0.8.5 are patch-level versions that removed settings and skill sources (10 of 15). Version 0.8.5, with v1.0 shown as planned on the home page (4 of 15).\n- Performance: 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.\n- Schema \u0026 documentation 82: Harness reading of the six lines, as the Goose dossier used. A running gateway serves an OpenAPI document at `/api/openapi.json` for what the docs call the currently documented subset, and `zeroclaw config schema` prints the full config schema, from which the published config reference is generated. We read neither from a running copy (18 of 25). An llms.txt on www.zeroclaw.com, and the docs are Markdown in the repository (10). The autonomy, sandboxing and YOLO pages say what each setting allows, when to use it and when not to (16 of 20). Typed TOML with enumerated levels, validation warnings and rejection of unknown values such as `read_only` (12 of 15). Worked config examples on most pages and a troubleshooting page, with no single error reference (12 of 15). Dated release notes, a blog post a release and a versioned config schema with automatic migration (14 of 15).\n- Agent ergonomics 72: Harness reading. MCP servers reach an agent only through its `mcp_bundles`, skills can load on demand in compact mode, and most built-in integrations are off until configured, though the built-in tool list is long (18 of 25). Daily and monthly cost budgets, history trimming and a 1 MB cap on Google Workspace output (15 of 20). A blocked call returns a tool error that names the policy, and the docs describe each failure path (15 of 20). Provider fallback chains, resumable procedure runs and approval timeouts that deny, with no idempotency guidance for sends (14 of 20). One binary and a guided quickstart, and `zeroclaw agent -a \u003calias\u003e -m` for one-shot runs, but a working config needs four sections and there is no SDK (10 of 15).\n- Security \u0026 auth 76: Harness reading, with 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 docs state no telemetry, we found no vendor host in the source apart from the optional ZeroRouter provider, secrets are encrypted with ChaCha20-Poly1305 beside a 0600 key file on the same disk, and the gateway binds 127.0.0.1 with pairing on. Web search and page fetches run without approval (27). Supervised mode is the default, `always_ask` outranks full autonomy, prompts time out to a denial, and an OS sandbox is auto-detected, but sandboxed tools keep network egress, unattended runs skip the shell prompt and rely on the command policy, and an open report says `firejail_args` is never applied (#11594) (17). A guard scans for injection patterns with a default action of warn, trigger payloads are framed as untrusted, a leak detector redacts credentials in replies by default, and an empty peer set denies all senders. No guidance page on injection through mail or web content was found (10). Approval events and a runtime trace are logged, tool receipts are opt-in and not durable, and the docs state command execution is not audited (8). SECURITY.md with private reporting and response times, one advisory published, CodeQL, cargo-deny, a daily audit and build attestations. No bounty and no security.txt, and SECURITY.md and the README name different contacts (14).\n- Payments \u0026 pricing 60: Read with the self-hosted rule. No payment protocol (0). Free under MIT or Apache-2.0 with nothing to buy for the assistant, so 20, 20 and 20 on the last three lines. It runs local models with no sign-up. ZeroRouter, the vendor's optional hosted model gateway, was not graded and its prices were not read.\n- Task success: 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.\n- Maintenance \u0026 community 80: v0.8.5 was released on 5 September 2026, 37 days before this check (20 of 30). Three releases in the 90 days to 12 October, v0.8.3 on 16 July, v0.8.4 on 2 August and v0.8.5 on 5 September (20). Master had 200 commits between 25 September and 11 October, and bug reports from the last week carry priority labels, comments and linked fix pull requests, against 576 open issues and 384 open pull requests (20 of 25). Not an MCP server and no SDK. Release workflows publish the binary, a ghcr.io image and crates, AUR and Scoop packages, which we read as workflow files and did not confirm on the registries (11 of 15). cargo-deny, a daily advisory audit, a monthly outdated-dependency job, CodeQL, Trivy and SBOM workflows, with CI passing (9 of 10).\n- Transparency \u0026 trust 64: MIT or Apache-2.0, with a CLA that leaves copyright with contributors (30). The docs map every state store, say what is sent to a model provider and list what to back up, and the site says there is no ZeroClaw cloud in between. There is no privacy policy or terms on zeroclaw.com, and no data statement was read for the hosted ZeroRouter beta that the `zerorouter` slot defaults to (16 of 30). Release notes name removed and deprecated settings, and SECURITY.md says only the latest minor line gets fixes. No deprecation policy with notice periods was found (10 of 20). The docs state there is no telemetry, and our source search found no vendor host beyond ZeroRouter. We did not audit every outbound call (18 of 20).\n\nFix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (22 items): https://www.anchorterminal.com/fixes/zeroclaw.md (JSON https://www.anchorterminal.com/fixes/zeroclaw.json)\n\n### What we couldn't check\n\n- Kind is `harness`. ZeroClaw is a self-hosted agent program, and harness is the closest kind the briefs define. Reliability was read with the local-software lines and Payments with the self-hosted rule.\n- The lead gave the licence as Apache-2.0. The repository is MIT or Apache-2.0 at the user's choice, and GitHub's API reports only Apache-2.0.\n- unchecked: nothing was installed or run, so the approval prompts, the sandbox, the OpenAPI document and the quickstart defaults were read from docs and source only.\n- unchecked: zerorouter.ai, the vendor's hosted beta model gateway, was not opened. Its prices, terms and data handling are unknown, as is whether quickstart preselects it.\n- unchecked: the crates.io, Homebrew, AUR and Scoop packages were not looked up. Their existence rests on the docs and the release workflow files.\n- unchecked: the advisories page on github.com answered 504 twice. The one published advisory was read from the GitHub API, and the full advisory text was not read.\n- unchecked: the telemetry statement was checked by a search of the source for vendor hosts, not by an audit of every outbound call.\n- The 1 April 2026 merge incident took 1 point. Whether any unreviewed merge reached a tagged release was not established.\n- The site heading says shell access you can audit, while the docs say command execution is not audited and receipts are opt-in. Recorded as a weakness with no deduction.\n- No company form or address for ZeroClaw Labs was found, and the site publishes no terms or privacy policy.\n\n### Sources\n\n- repository master at commit 6c0b1f9 (shallow clone, 200 commits): \u003chttps://github.com/zeroclaw-labs/zeroclaw\u003e (seen 2026-10-12)\n- README: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/README.md\u003e (seen 2026-10-12)\n- security policy: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/SECURITY.md\u003e (seen 2026-10-12)\n- autonomy levels: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/autonomy.md\u003e (seen 2026-10-12)\n- security model and default posture: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/model.md\u003e (seen 2026-10-12)\n- sandboxing: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/sandboxing.md\u003e (seen 2026-10-12)\n- tool receipts: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/tool-receipts.md\u003e (seen 2026-10-12)\n- YOLO mode: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/getting-started/yolo.md\u003e (seen 2026-10-12)\n- authentication and principals: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/authentication.md\u003e (seen 2026-10-12)\n- channels overview: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/channels/overview.md\u003e (seen 2026-10-12)\n- email channels: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/channels/email.md\u003e (seen 2026-10-12)\n- peer groups: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/channels/peer-groups.md\u003e (seen 2026-10-12)\n- tools overview: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/tools/overview.md\u003e (seen 2026-10-12)\n- built-in tool inventory: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/developing/tool-inventory.md\u003e (seen 2026-10-12)\n- MCP client: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/tools/mcp.md\u003e (seen 2026-10-12)\n- runtime state and persistence: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/architecture/runtime-state-and-persistence.md\u003e (seen 2026-10-12)\n- memory and payload lifecycle: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/architecture/memory-payload-lifecycle.md\u003e (seen 2026-10-12)\n- memory backends decision record: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/architecture/decisions/ADR-005-pluggable-memory-backends.md\u003e (seen 2026-10-12)\n- provider catalogue, with ZeroRouter: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/providers/catalog.md\u003e (seen 2026-10-12)\n- network deployment and gateway binding: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/ops/network-deployment.md\u003e (seen 2026-10-12)\n- gateway API overview: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/gateway/api.md\u003e (seen 2026-10-12)\n- cost tracking: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/ops/cost-tracking.md\u003e (seen 2026-10-12)\n- ownership and telemetry statement: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/philosophy/you-own-it.md\u003e (seen 2026-10-12)\n- release verification: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/maintainers/release-verification.md\u003e (seen 2026-10-12)\n- config schema source, default auto-approve list and Google Workspace settings: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/crates/zeroclaw-config/src/schema.rs\u003e (seen 2026-10-12)\n- approval decision source: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/crates/zeroclaw-runtime/src/approval/mod.rs\u003e (seen 2026-10-12)\n- secret store source: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/crates/zeroclaw-config/src/secrets.rs\u003e (seen 2026-10-12)\n- releases and release notes: \u003chttps://github.com/zeroclaw-labs/zeroclaw/releases\u003e (seen 2026-10-12)\n- published advisories, read from the GitHub API after the web page answered 504 twice: \u003chttps://api.github.com/repos/zeroclaw-labs/zeroclaw/security-advisories\u003e (seen 2026-10-12)\n- repository metadata and star count (GitHub API): \u003chttps://api.github.com/repos/zeroclaw-labs/zeroclaw\u003e (seen 2026-10-12)\n- CI runs on master (GitHub API): \u003chttps://api.github.com/repos/zeroclaw-labs/zeroclaw/actions/workflows/ci.yml/runs?branch=master\u003e (seen 2026-10-12)\n- open bug reports (GitHub API): \u003chttps://api.github.com/repos/zeroclaw-labs/zeroclaw/issues?state=open\u0026labels=bug\u003e (seen 2026-10-12)\n- home page and FAQ: \u003chttps://www.zeroclaw.com/\u003e (seen 2026-10-12)\n- llms.txt: \u003chttps://www.zeroclaw.com/llms.txt\u003e (seen 2026-10-12)\n- security.txt, 404: \u003chttps://www.zeroclaw.com/.well-known/security.txt\u003e (seen 2026-10-12)\n- blog index: \u003chttps://www.zeroclaw.com/blog\u003e (seen 2026-10-12)\n- incident recap of 1 April 2026: \u003chttps://www.zeroclaw.com/blog/community-and-stability\u003e (seen 2026-10-12)\n- domain registration (RDAP): \u003chttps://rdap.verisign.com/com/v1/domain/zeroclaw.com\u003e (seen 2026-10-12)\n\n## Who's behind it (provenance 53/100, checked 2026-10-12)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | ZeroClaw Labs | 20/20 |\n| Domain age | zeroclaw.com, registered 2026-03-02 (under a year) | 0/15 |\n| Endpoint on the vendor's domain | no hosted endpoint | n/a |\n| Terms of service | nothing hosted, so the MIT OR Apache-2.0 licence stands in | 10/10 |\n| Privacy policy | nothing hosted, not scored | n/a |\n| Status page | not found | 0/10 |\n| Changelog | published | 10/10 |\n| security.txt | not found | 0/10 |\n\nThe NOTICE file reads Copyright 2025 ZeroClaw Labs and the blog signs posts as CEO, ZeroClaw Labs. No company form, registration or address was found on the site or in the repository.\n\nThe home page of www.zeroclaw.com links no terms and no privacy policy, so both fields are empty and the MIT or Apache-2.0 licence stands in.\n\nwww.zeroclaw.com/.well-known/security.txt answered 404 on 12 October 2026. SECURITY.md asks for GitHub private vulnerability reporting and the README gives security@zeroclaw.dev.\n\nRDAP gives zeroclaw.com a registration date of 2026-03-02, registrar Atom.com Domains LLC. The repository was created on 13 February 2026.\n\nThere is no hosted endpoint for the assistant. A gateway answers on its owner's own host.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service**. Nothing is hosted by the vendor, so there are no terms of service to read. The MIT OR Apache-2.0 licence stands in and the check scores in full.\n\n\n**Privacy policy**. Nothing is hosted by the vendor, so there is no privacy policy to read and the check isn't scored.\n\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Strengths\n\n- Supervised mode is the default. Tools outside an eleven-item read-only and fetch list prompt the owner, and an unanswered prompt is a denial after 120 seconds\n- Approval prompts arrive on the channel in use, and `approval_route` can send them to a separate approver channel that denies when unreachable\n- Channel secrets and provider keys are encrypted with ChaCha20-Poly1305 in `config.toml`, with the key in `.secret_key` at mode 0600\n- An empty peer set denies every inbound sender, and the gateway binds 127.0.0.1 with pairing required by default\n- Three tagged releases in the 90 days to 12 October 2026, each with a Breaking Changes section, and CI passing on master on 11 October\n\n## Weaknesses\n\n- The docs state that command execution is not audited. `[security.audit]` records certificate events only, and tool receipts are opt-in and not durable\n- No privacy policy, terms or security.txt on zeroclaw.com, and the home page links none\n- `web_fetch`, `web_search_tool` and `browser_open` run without approval by default, and sandboxed tools keep full network egress\n- GHSA-93f6-34w8-5g98 (high) let a plugin install write outside the plugins directory in 0.8.4 and earlier, fixed in 0.8.5 on 5 September 2026\n- Version 0.8.5 is pre-1.0, patch releases carry breaking changes, and 576 issues and 384 pull requests were open on 12 October 2026\n\n## Before you call it (notes for agents)\n\n1. Keep `[risk_profiles.\u003calias\u003e] level = \"supervised\"`. `full` runs every tool not listed in `always_ask`, and the YOLO preset removes the sandbox and path rules too\n2. Add sending and account tools such as `send_via`, `google_workspace` and `http_request` to `always_ask` so a session-level Always grant cannot skip the prompt\n3. List senders in `[peer_groups.\u003cname\u003e] external_peers`. `[\"*\"]` accepts anyone on that channel\n4. Set `[web_fetch].allowed_domains` and `[http_request].allowed_domains`. Fetches run unprompted and the OS sandbox does not block egress\n5. Run one-shot tasks with `zeroclaw agent -a \u003calias\u003e -m \"\u003ctask\u003e\"`. A cron or webhook turn has no prompt, so shell calls fall to the command policy\n\n## Connect\n\nInstall:\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/zeroclaw-labs/zeroclaw/master/install.sh | sh # or: brew install zeroclaw\n```\n\nHeadless / CI:\n\n```json\n{\n \"command\": \"zeroclaw agent -a \\u003calias\\u003e -m \\\"$TASK\\\"\",\n \"setup\": \"zeroclaw quickstart\"\n}\n```\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| NanoClaw | B | 68.3 | 229 | assistant.proactive, assistant.messaging, assistant.memory, assistant.self-hosted, agent.mcp-client, assistant.accounts | no | https://www.anchorterminal.com/tools/nanoclaw.md |\n| Hermes Agent | B | 67.9 | 244 | assistant.proactive, assistant.messaging, assistant.accounts, assistant.memory, assistant.self-hosted, agent.mcp-client | no | https://www.anchorterminal.com/tools/hermes-agent.md |\n| OpenClaw | B | 67.1 | 270 | assistant.proactive, assistant.messaging, assistant.accounts, assistant.memory, assistant.self-hosted, agent.mcp-client | no | https://www.anchorterminal.com/tools/openclaw.md |\n| IronClaw | B | 66.7 | 288 | assistant.proactive, assistant.messaging, assistant.accounts, assistant.memory, assistant.self-hosted, agent.mcp-client | no | https://www.anchorterminal.com/tools/ironclaw.md |\n| nanobot | B | 62.4 | 446 | assistant.proactive, assistant.messaging, assistant.memory, assistant.self-hosted, assistant.accounts, agent.mcp-client | no | https://www.anchorterminal.com/tools/nanobot.md |\n| QwenPaw | B | 62.2 | 454 | assistant.proactive, assistant.messaging, assistant.accounts, assistant.memory, assistant.self-hosted, agent.mcp-client | no | https://www.anchorterminal.com/tools/qwenpaw.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- Supervised autonomy is the default. Low-risk tools run, medium-risk tools ask the operator and high-risk calls are blocked (source: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/autonomy.md\u003e)\n- The security model page says audit logging covers certificate issuance and renewal only and that command execution is not audited (source: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/security/model.md\u003e)\n- One published advisory, GHSA-93f6-34w8-5g98 (high), published 5 September 2026. An unvalidated `wasm_path` let `zeroclaw plugin install` write outside the plugins directory in 0.8.4 and earlier, fixed in 0.8.5 (source: \u003chttps://github.com/zeroclaw-labs/zeroclaw/security/advisories/GHSA-93f6-34w8-5g98\u003e)\n- A post of 1 April 2026 by the project lead says a maintainer's AI automation merged pull requests that should not have gone through, that GitHub took enforcement action on the organisation, and that the maintainer was removed (source: \u003chttps://www.zeroclaw.com/blog/community-and-stability\u003e)\n- The licence is MIT or Apache-2.0 at the user's choice. GitHub's API reports only Apache-2.0 (source: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/README.md\u003e)\n- Version 0.8.5 added a `zerorouter` provider slot that defaults to a hosted beta model gateway at zerorouter.ai (source: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/providers/catalog.md\u003e)\n- The philosophy page says no telemetry, no cloud tenancy and no licence server (source: \u003chttps://github.com/zeroclaw-labs/zeroclaw/blob/master/docs/book/src/philosophy/you-own-it.md\u003e)\n- The home page shows v1.0 as planned and says the v0.8.x line has shipped about monthly since June 2026 (source: \u003chttps://www.zeroclaw.com/\u003e)\n\n- #1 of 20 in Best AI personal assistants that act for one person: https://www.anchorterminal.com/best/personal-assistants/index.md\n- All 190 assistants comparisons: https://www.anchorterminal.com/compare/personal-assistants/index.md\n\n## Compare\n\n- [AstrBot vs ZeroClaw](https://www.anchorterminal.com/compare/astrbot-vs-zeroclaw.md): C 58.8 vs BB 70.2\n- [CowAgent vs ZeroClaw](https://www.anchorterminal.com/compare/cowagent-vs-zeroclaw.md): C 58.5 vs BB 70.2\n- [GAIA vs ZeroClaw](https://www.anchorterminal.com/compare/gaia-vs-zeroclaw.md): D 49.5 vs BB 70.2\n- [Gemini Spark vs ZeroClaw](https://www.anchorterminal.com/compare/gemini-spark-vs-zeroclaw.md): F 24.5 vs BB 70.2\n- [Grok Bot vs ZeroClaw](https://www.anchorterminal.com/compare/grok-bot-vs-zeroclaw.md): E 45.2 vs BB 70.2\n- [Haven vs ZeroClaw](https://www.anchorterminal.com/compare/haven-vs-zeroclaw.md): F 22.2 vs BB 70.2\n- [Hermes Agent vs ZeroClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-zeroclaw.md): B 67.9 vs BB 70.2\n- [Instinct vs ZeroClaw](https://www.anchorterminal.com/compare/instinct-vs-zeroclaw.md): F 11.4 vs BB 70.2\n- [IronClaw vs ZeroClaw](https://www.anchorterminal.com/compare/ironclaw-vs-zeroclaw.md): B 66.7 vs BB 70.2\n- [Leon vs ZeroClaw](https://www.anchorterminal.com/compare/leon-vs-zeroclaw.md): E 41 vs BB 70.2\n- [Lindy vs ZeroClaw](https://www.anchorterminal.com/compare/lindy-vs-zeroclaw.md): F 32.3 vs BB 70.2\n- [nanobot vs ZeroClaw](https://www.anchorterminal.com/compare/nanobot-vs-zeroclaw.md): B 62.4 vs BB 70.2\n- [NanoClaw vs ZeroClaw](https://www.anchorterminal.com/compare/nanoclaw-vs-zeroclaw.md): B 68.3 vs BB 70.2\n- [Dots vs ZeroClaw](https://www.anchorterminal.com/compare/openai-dots-vs-zeroclaw.md): F 28.3 vs BB 70.2\n- [OpenClaw vs ZeroClaw](https://www.anchorterminal.com/compare/openclaw-vs-zeroclaw.md): B 67.1 vs BB 70.2\n- [PicoClaw vs ZeroClaw](https://www.anchorterminal.com/compare/picoclaw-vs-zeroclaw.md): D 46.1 vs BB 70.2\n- [Poke vs ZeroClaw](https://www.anchorterminal.com/compare/poke-vs-zeroclaw.md): F 37.6 vs BB 70.2\n- [QwenPaw vs ZeroClaw](https://www.anchorterminal.com/compare/qwenpaw-vs-zeroclaw.md): B 62.2 vs BB 70.2\n- [ZeroClaw vs Zo Computer](https://www.anchorterminal.com/compare/zeroclaw-vs-zo-computer.md): BB 70.2 vs E 43.1\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on zeroclaw.com or one of its subdomains, or the README of github.com/zeroclaw-labs/zeroclaw. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"zeroclaw\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/zeroclaw\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/zeroclaw.svg\" alt=\"ZeroClaw on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![ZeroClaw on Anchor Terminal](https://www.anchorterminal.com/badges/zeroclaw.svg)](https://www.anchorterminal.com/tools/zeroclaw)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/zeroclaw\"\u003eZeroClaw on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say ZeroClaw is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/zeroclaw-dark.png\n- Light: https://www.anchorterminal.com/assets/share/zeroclaw-light.png\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-12", "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" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Personal assistants", "url": "https://www.anchorterminal.com/categories/personal-assistants" }, { "name": "ZeroClaw", "url": "" } ], "description": "Open-source personal AI assistant from ZeroClaw Labs, shipped as one Rust binary the owner runs. It answers on chat, email and voice channels, calls tools and MCP servers, and keeps memory in local SQLite.", "facts": [ "rank #161 of 986", "None auth", "0 desk reviews" ], "h1": "ZeroClaw", "image": "https://www.anchorterminal.com/assets/og/tools-zeroclaw.png", "path": "/tools/zeroclaw", "published": "2026-10-01", "section": "tools", "title": "ZeroClaw review (2026): pricing, alternatives and grade BB", "toc": null, "updated": "2026-10-12", "url": "https://www.anchorterminal.com/tools/zeroclaw" }, "tokens": { "markdown": 8600, "slim": 2330 }, "version": 1 }