# NanoClaw > Open-source personal assistant that the owner runs on their own machine. It answers on messaging apps, runs each agent session in a Docker container, keeps Markdown memory on disk and runs scheduled tasks. - Canonical: https://www.anchorterminal.com/tools/nanoclaw - Markdown: https://www.anchorterminal.com/tools/nanoclaw.md (~8,300 tokens) - Slim: https://www.anchorterminal.com/tools/nanoclaw.min.md (~1,930 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/nanoclaw.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - Updated: 2026-10-12 ## Overview **Grade B · 68.3/100 · rank #229 of 986 · #2 in Personal assistants · not agent-ready · confidence medium** ## Assessment Each session runs in an unprivileged Docker container and API keys stay in a credential gateway on the host, so a manipulated agent cannot read them. Inside the container the agent runs with permission prompts off, network egress is open by default, and it can message any chat it is wired to without approval. ## Facts | Field | Value | | --- | --- | | Vendor | NanoCo, Inc. (https://nanoclaw.dev) | | Kind | Agent harness | | Category | Personal assistants (https://www.anchorterminal.com/categories/personal-assistants) | | Auth | None · No account is needed to run it. Owners and admins are rows in a local `user_roles` table, and strangers are handled by each chat's `unknown_sender_policy` (https://docs.nanoclaw.dev/concepts/security). Model and service credentials are registered with a credential gateway on the host, OneCLI Agent Vault by default, which adds them to outbound HTTPS requests. Containers receive placeholders such as `onecli-managed` (https://docs.nanoclaw.dev/operate/credentials). Channel tokens stay in the host's `.env`. An optional free NanoClaw account, used for a prebuilt agent image and a managed Slack app, keeps its token in `~/.config/nanoclaw/account.json` with mode 0600 (https://github.com/nanocoai/nanoclaw/blob/main/README.md). | | Pricing | Free (Free · OSS) · Free under the MIT licence, with nothing on sale. The optional NanoClaw account, the Echo image and the managed Slack app are free of charge per the terms of 31 July 2026 (https://nanoclaw.dev/terms). The owner pays the model provider through a Claude subscription, an API key or another provider, and any service a channel or tool uses, such as Dial. Since 2.4.0 Claude groups default to Opus 5.5 (checked 2026-10-12). | | x402 | No · No x402, MPP or L402 in the docs or the source (checked 2026-10-12). | | Licence | MIT | | Source | https://github.com/nanocoai/nanoclaw | | Docs | https://docs.nanoclaw.dev | | llms.txt | https://docs.nanoclaw.dev/llms.txt | | Last release | 2026-10-09 | | GitHub stars | 30,929 (as of 2026-10-12) | | Runs on | The owner's macOS or Linux machine, or Windows through WSL2. One Node host process and one Docker container per active session. Installed by `git clone` and `bash nanoclaw.sh` | | Acts without asking | Inside its container the agent runs shell, file, web and browser tools with permission prompts off. It can send messages and files to any chat or agent its group is wired to, and call any API its group was granted a credential for, unless that secret is set to need approval | | Needs approval | Installing apt or npm packages, adding an MCP server, `ncl` writes from inside a container, creating an agent (unless the group has global CLI scope), admitting a new chat or unknown sender, and credential use where the secret is set to manual approval. No reachable approver means denial | | Accounts and credentials | No first-party Gmail or Google Calendar integration on trunk. API keys and OAuth connections are stored in a credential gateway on the host (OneCLI Agent Vault by default, Iron Proxy as the alternative) and granted per agent group. Channel tokens such as `TELEGRAM_BOT_TOKEN` stay in the host's `.env` | | Memory | Markdown files in `groups//memory/`, shared by every session of an agent group. Two files, each capped at 16,000 characters, are loaded into every new context window. Session history is in SQLite under `data/v2-sessions/` | | Deletion | Edit or delete memory files on the host. `bash nanoclaw.sh --uninstall` removes the service, data and agents' files in three groups, each asked separately with No as the default, and leaves the shared gateway and its credentials in place | | Models | Claude through the Claude Agent SDK by default, with a subscription token or an API key. Codex, OpenCode (OpenRouter, OpenAI, Google, DeepSeek and others) and Ollama through skills, set per agent group. Message content goes to the provider chosen | | Channels | A local CLI channel on trunk. WhatsApp, Telegram, Discord, Slack, Signal, iMessage, Microsoft Teams, Mattermost, Matrix, Google Chat, Webex, WeChat, Linear, GitHub, Delta Chat, email through Resend, and SMS and voice through Dial, each installed by an `/add-` skill | | Scheduled tasks | `ncl tasks create` with a cron expression or a one-time timestamp. A task runs an agent prompt in its own session, and a script gate can skip a run with nothing to do | | MCP client | stdio and remote Streamable HTTP servers per agent group, added by `ncl groups config add-mcp-server` or by the agent's `add_mcp_server` request, which needs approval. The built-in `nanoclaw` server has nine tools | | Sandbox | Non-root container, `--cap-drop=ALL`, `no-new-privileges`, a 2,048 process limit, and extra mounts refused unless listed in `~/.config/nanoclaw/mount-allowlist.json`. CPU and memory limits are unset by default | | Telemetry | Setup events go to PostHog under a random install id. `NANOCLAW_NO_DIAGNOSTICS=1` turns them off. No runtime telemetry was found in the host or container source | | Releases in 90 days | 5 stable (2.1.54 on 1 August to 2026.10.0 on 9 October 2026) and 2 release candidates | | Cost | Free under the MIT licence. The owner pays the model provider, and any third-party service a channel or tool uses. No monthly figure is published | | Capabilities | assistant.proactive, assistant.messaging, assistant.memory, assistant.self-hosted, agent.mcp-client, assistant.accounts | | Tags | open-source, local, free, no-card, docker, llms-txt | | JSON | https://www.anchorterminal.com/api/v1/tools/nanoclaw.json | ## Score breakdown (methodology v0.4, October 2026 research run) Assessed 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. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 78 | 15.6 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 82 | 13.3 | | Agent ergonomics | 13% | 16.2 | 70 | 11.4 | | Security & auth | 14% | 17.5 | 74 | 12.9 | | Payments & pricing | 10% | 12.5 | 60 | 7.5 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 78 | 6.8 | | Transparency & trust (editorial 77, provenance 53) | 7% | 8.8 | 65 | 5.7 | | Negative events | up to −15 | up to −15 | 2026-10-09. Release 2026.10.0 fixed four symlink flaws through which a manipulated agent could make the host read, write or delete files outside its folders, plus an admin-command bypass, a cross-group read through `ncl` and a command injection in Mattermost setup. Fixed and described in the changelog within the week, but the advisories it links (GHSA-frvf-5rf5-89fq and seven others) were not public on 12 October 2026. -5. https://github.com/nanocoai/nanoclaw/blob/main/CHANGELOG.md | -5 | | **Total** | | | | **68.3 → B** | ### Why each score - Reliability 78: Read as software the owner runs. Installed by `git clone` and `bash nanoclaw.sh`, with no registry package. macOS, Linux and WSL2 with Docker are stated, but the home page says Node.js 20 or later and the README and `package.json` say 22 or later (13). The CI workflow runs formatting, type checks and host and container tests on Node 22 and 24, and the 14 completed runs on main from 5 to 11 October 2026 all passed (25). 294 open issues and 750 open pull requests on 12 October 2026, and 10 of the 12 newest open issues had no reply, among them a report that updates do not rebuild per-group images (12). The changelog marks breaking changes and opens each release with steps to take before updating, and versions moved from 2.4.0 to calendar numbering on 9 October 2026 (13). Version 2 since 22 April 2026, with stable, beta and edge update channels (15). - 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. - Schema & documentation 82: Harness reading, as for the agent programs we list. No HTTP API and no OpenAPI file. The docs carry references for the nine built-in MCP tools, the `ncl` CLI, the database schema, container configuration and the template format, and the tools declare JSON Schema inputs in the source (17). llms.txt at docs.nanoclaw.dev with a Markdown twin of every page (10). The security page says what each layer stops and lists four things it does not, and the hardening page gives the default of each setting (17). Tool parameters are tabled with types and required flags, and sender policies are a fixed set of four values, though message content is free text (11). Step-by-step guides and a troubleshooting page, with no error reference found (12). A dated CHANGELOG.md, mirrored on the docs site, and a written release process (15). - Agent ergonomics 70: Harness reading, scored on what an owner or pipeline driving it has to supply. The built-in MCP server has nine tools beside 16 allowed Claude Code tools, and the two memory files loaded into each new context are capped at 16,000 characters each (21). A 2,048 process limit is on by default, CPU and memory limits are unset, and no spending or turn cap was found (11). The `ncl` CLI and a local CLI channel work over a Unix socket, with no HTTP interface (12). Sessions, approvals and delivery retries persist in SQLite across host restarts, and the updater takes a snapshot and rolls back on failure (18). One script installs it, but it needs Docker, Node and a Claude or Codex credential, channel skills need Claude Code, and changing behaviour means editing a fork. No SDK (8). - Security & auth 74: 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. Setup events go to PostHog under a random install id unless `NANOCLAW_NO_DIAGNOSTICS=1` is set, which the README discloses, and no runtime telemetry was found in the host or container source. Message content goes to the model provider chosen (22). Sessions run in non-root containers with all capabilities dropped, extra mounts are denied without an allowlist, and API keys stay in a gateway on the host. Self-modification, new chats and `ncl` writes wait for an admin. But the Claude provider runs with permission prompts off, sending to wired chats needs no approval, per-request credential approval is opt-in and egress lockdown is off by default (15). The security page assumes injection succeeds and lists what a manipulated agent can still do. Sender policies and a command gate limit who can reach an agent, and no content screening was found (13). A dropped-messages log, an approvals list, task run logs and session history through `ncl`, and gateway activity in the OneCLI dashboard (11). SECURITY.md with private reporting, fixes credited to reporters in the changelog, signed image verification and pinned Actions in CI. The eight advisories the 9 October changelog links were not public on 12 October, and there is no security.txt and no bounty (13). - Payments & pricing 60: No payment protocol (0). Free under the MIT licence with nothing to buy, so the self-hosted rule gives 20, 20 and 20 on the last three lines. The optional account is free. The owner still needs a model credential, or a local model through the Ollama provider skill. - 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. - Maintenance & community 78: 2026.10.0 on 9 October 2026 (30). Five stable releases in the 90 days to 12 October, from 2.1.54 to 2026.10.0, and two release candidates (20). Reported security flaws were fixed and credited, but 294 issues and 750 pull requests were open, and 10 of the 12 newest open issues had no reply (11). No registry package. Channels and providers ship from registry branches through skills, and a prebuilt agent image is pinned by digest and checked with cosign in CI (8). CI on Node 22 and 24 with frozen lockfiles, Actions pinned to commit hashes and a three-day release-age gate on dependencies, which the 2.4.0 notes say had been ignored until 23 September 2026 (9). - Transparency & trust 65: MIT (30). The README has a section on what leaves the machine, and the privacy policy describes the optional account in detail, with IP addresses cut to a /24 network. The policy says it does not cover the software and says NanoClaw does not report back, without mentioning the setup events sent to PostHog, and gives no retention period for them (19). Breaking changes are marked with migration steps and a written release process, with no stated notice period (13). Setup diagnostics are disclosed in the README with an opt-out variable, and are on by default (15). Fix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (22 items): https://www.anchorterminal.com/fixes/nanoclaw.md (JSON https://www.anchorterminal.com/fixes/nanoclaw.json) ### What we couldn't check - Kind is recorded as harness, the closest kind the briefs define for an agent program the owner runs. NanoClaw has no HTTP API and is not an MCP server - `assistant.accounts` is claimed on the credential gateway, which holds API keys and OAuth connections per agent group. Trunk has no first-party mail or calendar integration, so a stricter reading would drop it - Why the eight advisories linked from the 2026.10.0 changelog were not public three days after the release. They may be unpublished drafts - Whether setup shows a consent prompt for diagnostics. We found only the `NANOCLAW_NO_DIAGNOSTICS` check in the setup scripts, and the README calls the diagnostics anonymous - What the OneCLI gateway flaw fixed in 1.42.0 allowed. The changelog calls it a credential-injection bypass and we did not read OneCLI's own notes - unchecked: how the OneCLI Agent Vault stores secrets at rest. We read NanoClaw's docs and not OneCLI's - unchecked: portal.nanoclaw.dev, nanoco.ai, the blog and the registration date of nanoclaw.dev - unchecked: what a month of use costs. No figure is published and no model provider's price page was read - unchecked: reply times on issues beyond the 50 newest open items, and the state of the channels and providers branches - The first-release date was not established. The repository was created on 31 January 2026 and the changelog's version 2.0.0 is dated 22 April 2026 - github.com's robots.txt closes tree, tags and commit pages to Anthropic agents, so the source was read from a shallow clone and blob pages, and release dates from the API. api.github.com answered 404 for robots.txt, read as no rules ### Sources - repository README: (seen 2026-10-12) - changelog: (seen 2026-10-12) - security model (repository copy): (seen 2026-10-12) - security policy: (seen 2026-10-12) - Claude provider execution policy: (seen 2026-10-12) - built-in MCP tools (source): (seen 2026-10-12) - setup diagnostics emitter: (seen 2026-10-12) - memory docs (repository): (seen 2026-10-12) - scheduled tasks docs (repository): (seen 2026-10-12) - hardened image docs (repository): (seen 2026-10-12) - CI workflow: (seen 2026-10-12) - release process: (seen 2026-10-12) - pnpm supply-chain settings: (seen 2026-10-12) - published advisories page (none listed): (seen 2026-10-12) - advisory linked from the changelog (404): (seen 2026-10-12) - GitHub API, repository record (stars, licence, open count): (seen 2026-10-12) - GitHub API, repository advisories (empty list): (seen 2026-10-12) - GitHub API, newest open issues: (seen 2026-10-12) - GitHub API, CI runs on main: (seen 2026-10-12) - GitHub API, releases: (seen 2026-10-12) - home page: (seen 2026-10-12) - terms of service, 31 July 2026: (seen 2026-10-12) - privacy policy, 31 July 2026: (seen 2026-10-12) - security.txt (404): (seen 2026-10-12) - docs index for agents: (seen 2026-10-12) - docs, security model: (seen 2026-10-12) - docs, credentials: (seen 2026-10-12) - docs, hardening: (seen 2026-10-12) - docs, agent MCP tools: (seen 2026-10-12) - docs, tools and the Gmail note: (seen 2026-10-12) - docs, agent providers: (seen 2026-10-12) - docs, uninstall: (seen 2026-10-12) - docs, release history: (seen 2026-10-12) ## Who's behind it (provenance 53/100, checked 2026-10-12) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | NanoCo, Inc. | 20/20 | | Domain age | nanoclaw.dev, no registry record we could read | 0/15 | | Endpoint on the vendor's domain | no hosted endpoint | n/a | | Terms of service | nothing hosted, so the MIT licence stands in | 10/10 | | Privacy policy | nothing hosted, not scored | n/a | | Status page | not found | 0/10 | | Changelog | published | 10/10 | | security.txt | not found | 0/10 | The terms and privacy policy at nanoclaw.dev name NanoCo, Inc. and Delaware law. Both say they cover the website and the optional account, not the software, so neither is linked and the MIT licence stands in. nanoclaw.dev/.well-known/security.txt returned 404 on 12 October 2026. The repository's SECURITY.md points to GitHub private vulnerability reporting. There is no hosted endpoint. The assistant runs on the owner's machine, and the optional account service is at portal.nanoclaw.dev, which we did not open. The registration date of nanoclaw.dev was not checked. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service**. Nothing is hosted by the vendor, so there are no terms of service to read. The MIT licence stands in and the check scores in full. **Privacy policy**. Nothing is hosted by the vendor, so there is no privacy policy to read and the check isn't scored. ## Probe metrics Not 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. ## Strengths - Each session runs in a non-root Docker container with all capabilities dropped, and the project root and `.env` are never mounted - API keys sit in a credential gateway on the host, which adds them to outbound requests, so the container holds only placeholders - Installing packages, adding an MCP server and admitting a new chat each wait for an admin's approval, and no reachable approver means denial - Memory is plain Markdown under `groups//memory/`, which the owner can read, edit or delete on the host - The security page states what the design does not stop, including messages to wired chats and spending through granted credentials ## Weaknesses - The Claude provider runs with `permissionMode: 'bypassPermissions'`, so shell, file and web tools run inside the container with no prompt - Egress lockdown is off by default, so a container can reach the internet directly unless `NANOCLAW_EGRESS_LOCKDOWN=true` is set - The 2026.10.0 changelog links eight advisories on the repository, and on 12 October 2026 the advisories page listed none and one linked advisory returned 404 - Setup sends events to PostHog unless `NANOCLAW_NO_DIAGNOSTICS=1` is set, and the privacy policy does not mention them - The docs say trunk has no Gmail or Google Calendar integration, while the GitHub repository description still names Gmail - 294 open issues and 750 open pull requests on 12 October 2026, and 10 of the 12 newest open issues had no reply ## Before you call it (notes for agents) 1. Install with `git clone` and `bash nanoclaw.sh`. There is no registry package, and setup needs Docker, Node 22 or later and a Claude or Codex credential 2. Set `NANOCLAW_EGRESS_LOCKDOWN=true` before giving an agent credentials or an audience of strangers. The default leaves egress open 3. Put chats with different audiences in separate agent groups. Every session of a group shares one read-write workspace and memory tree 4. Turn on per-request approval for a secret in the gateway when its use should wait for a person. It is off unless configured 5. On OneCLI installs, move the gateway to 1.42.0 by the upgrade guide before updating to 2026.10.0. The updater stops until that is done ## Connect Install: ```bash git clone https://github.com/nanocoai/nanoclaw.git nanoclaw-v2 && cd nanoclaw-v2 && bash nanoclaw.sh ``` ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | ZeroClaw | BB | 70.2 | 161 | assistant.proactive, assistant.messaging, assistant.memory, assistant.self-hosted, assistant.accounts, agent.mcp-client | no | https://www.anchorterminal.com/tools/zeroclaw.md | | 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 | | 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 | | 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 | | 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 | | 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 | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk 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 ## Notable - The Claude provider sets `permissionMode: 'bypassPermissions'` and `allowDangerouslySkipPermissions: true`, with a source comment that container isolation and the gateway allowlist are the boundary, not the SDK's prompts (source: ) - The security page assumes prompt injection succeeds and lists what a manipulated agent can still do. It can message anyone in its destinations, read and destroy its group workspace, spend through granted credentials and write to its own memory (source: ) - Egress lockdown is off by default. With `NANOCLAW_EGRESS_LOCKDOWN=true` containers join an internal Docker network where the gateway is the only reachable hop (source: ) - Release 2026.10.0 of 9 October 2026 fixed four symlink flaws that let a manipulated agent make the host read, write or delete files outside its folders, an admin-command bypass, a cross-group read through `ncl`, a command injection in Mattermost setup and an installer fetched without HTTPS (source: ) - That changelog links eight advisories under nanocoai/nanoclaw. On 12 October 2026 the repository's advisories page read that there are no published security advisories, GitHub's API listed none, and GHSA-frvf-5rf5-89fq returned 404 (source: ) - The same release tells OneCLI installs to move the gateway to 1.42.0, which the changelog says closes a credential-injection bypass. `/update-nanoclaw` does not upgrade a running gateway (source: ) - Setup posts events such as `setup_start`, `channel_chosen` and `agent_provider_chosen` to us.i.posthog.com under a random install id unless `NANOCLAW_NO_DIAGNOSTICS=1` is set. No PostHog call was found in `src/` or `container/` (source: ) - The README says agents, messages, files and keys never leave the machine and names setup diagnostics as the only thing reported. It ends with a tracking pixel from static.scarf.sh (source: ) - The terms of 31 July 2026 say they govern the website and the optional account, not the software, and the privacy policy says it does not cover the software. Neither mentions setup diagnostics (source: , ) - The docs say trunk has no Gmail or Google Calendar integration, after `/add-gmail-tool` and `/add-gcal-tool` were removed. The GitHub repository description still lists Gmail (source: ) - A free NanoClaw account is optional. It is used to fetch a prebuilt agent image built by Echo and to have NanoCo create a Slack app per agent, and NanoCo then stores the Slack workspace authorisation, encrypted (source: ) - Since 2.4.0 of 23 September 2026, Claude groups with no model set run on Opus 5.5, which the changelog says changes cost and usage-limit burn (source: ) - The 2.4.0 notes say pnpm's three-day `minimumReleaseAge` gate had been silently ignored because of where the setting sat, and takes effect from that release (source: ) - The home page banner says NanoCo raised $12M. The site states Node.js 20 or later, while the README and `package.json` state Node 22 or later (source: ) - #2 of 20 in Best AI personal assistants that act for one person: https://www.anchorterminal.com/best/personal-assistants/index.md - All 190 assistants comparisons: https://www.anchorterminal.com/compare/personal-assistants/index.md ## Compare - [AstrBot vs NanoClaw](https://www.anchorterminal.com/compare/astrbot-vs-nanoclaw.md): C 58.8 vs B 68.3 - [CowAgent vs NanoClaw](https://www.anchorterminal.com/compare/cowagent-vs-nanoclaw.md): C 58.5 vs B 68.3 - [GAIA vs NanoClaw](https://www.anchorterminal.com/compare/gaia-vs-nanoclaw.md): D 49.5 vs B 68.3 - [Gemini Spark vs NanoClaw](https://www.anchorterminal.com/compare/gemini-spark-vs-nanoclaw.md): F 24.5 vs B 68.3 - [Grok Bot vs NanoClaw](https://www.anchorterminal.com/compare/grok-bot-vs-nanoclaw.md): E 45.2 vs B 68.3 - [Haven vs NanoClaw](https://www.anchorterminal.com/compare/haven-vs-nanoclaw.md): F 22.2 vs B 68.3 - [Hermes Agent vs NanoClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-nanoclaw.md): B 67.9 vs B 68.3 - [Instinct vs NanoClaw](https://www.anchorterminal.com/compare/instinct-vs-nanoclaw.md): F 11.4 vs B 68.3 - [IronClaw vs NanoClaw](https://www.anchorterminal.com/compare/ironclaw-vs-nanoclaw.md): B 66.7 vs B 68.3 - [Leon vs NanoClaw](https://www.anchorterminal.com/compare/leon-vs-nanoclaw.md): E 41 vs B 68.3 - [Lindy vs NanoClaw](https://www.anchorterminal.com/compare/lindy-vs-nanoclaw.md): F 32.3 vs B 68.3 - [nanobot vs NanoClaw](https://www.anchorterminal.com/compare/nanobot-vs-nanoclaw.md): B 62.4 vs B 68.3 - [NanoClaw vs Dots](https://www.anchorterminal.com/compare/nanoclaw-vs-openai-dots.md): B 68.3 vs F 28.3 - [NanoClaw vs OpenClaw](https://www.anchorterminal.com/compare/nanoclaw-vs-openclaw.md): B 68.3 vs B 67.1 - [NanoClaw vs PicoClaw](https://www.anchorterminal.com/compare/nanoclaw-vs-picoclaw.md): B 68.3 vs D 46.1 - [NanoClaw vs Poke](https://www.anchorterminal.com/compare/nanoclaw-vs-poke.md): B 68.3 vs F 37.6 - [NanoClaw vs QwenPaw](https://www.anchorterminal.com/compare/nanoclaw-vs-qwenpaw.md): B 68.3 vs B 62.2 - [NanoClaw vs ZeroClaw](https://www.anchorterminal.com/compare/nanoclaw-vs-zeroclaw.md): B 68.3 vs BB 70.2 - [NanoClaw vs Zo Computer](https://www.anchorterminal.com/compare/nanoclaw-vs-zo-computer.md): B 68.3 vs E 43.1 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on nanoclaw.dev or one of its subdomains, or the README of github.com/nanocoai/nanoclaw. 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": "nanoclaw", "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 HTML badge: ```html NanoClaw on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![NanoClaw on Anchor Terminal](https://www.anchorterminal.com/badges/nanoclaw.svg)](https://www.anchorterminal.com/tools/nanoclaw) ``` Plain link: ```html NanoClaw on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say NanoClaw is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/nanoclaw-dark.png - Light: https://www.anchorterminal.com/assets/share/nanoclaw-light.png