# Asmi > Asmi is a hosted assistant that calls, texts and emails businesses and people to finish real-world chores, such as booking appointments, cancelling memberships or chasing refunds. It is reached by WhatsApp, the web or an MCP server. - Canonical: https://www.anchorterminal.com/tools/asmi - Markdown: https://www.anchorterminal.com/tools/asmi.md (~7,000 tokens) - Slim: https://www.anchorterminal.com/tools/asmi.min.md (~1,580 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/asmi.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: 2026-10-14 ## Overview **Grade F · 33.3/100 · rank #973 of 1010 · #19 in Personal assistants · not agent-ready · confidence medium** ## Assessment Asmi is a hosted errand service with a 12-tool MCP server for Claude, ChatGPT and Muse, using OAuth with separate scopes for tracking tasks and for contacting people. Tool schemas sit behind sign-in, the outreach scope is ticked by default, and no status page, changelog or security contact was found. ## Facts | Field | Value | | --- | --- | | Vendor | Humint Labs, Inc. (https://www.asmiai.com) | | Kind | Platform | | Category | Personal assistants (https://www.anchorterminal.com/categories/personal-assistants) | | Transport | Streamable HTTP | | Endpoint | `https://prod.asmiai.com/mcp/claude/` | | Auth | OAuth · Each assistant has its own MCP endpoint (https://prod.asmiai.com/mcp/claude/, /mcp/openai/ and /mcp/meta/), and a token issued for one is refused at the others (RFC 8707 audience binding). Sign-in opens Asmi's page, where the person enters a phone number or email, confirms a 6-digit code and chooses scopes. Claude and ChatGPT identify with a client metadata document and other clients use dynamic client registration. Access tokens last 30 days, refresh tokens rotate, and Asmi stores only SHA-256 hashes (https://www.asmiai.com/docs/mcp). Protected-resource metadata lists scopes tasks and outreach (https://prod.asmiai.com/.well-known/oauth-protected-resource/mcp/claude/). For clients that only take a static credential, support issues a key that lasts 60 days. | | Pricing | Freemium ($10 / mo) · Plans are $10 a month ($99 a year) for 20 tasks and $49 a month ($499 a year) for 100, per the MCP docs, and the terms state the monthly prices (https://www.asmiai.com/docs/mcp and https://www.asmiai.com/terms-and-conditions, checked 14 October 2026). The Free plan covers search, task lists and status, and a trial gives "One free task that contacts a third party". Each task that calls, texts or emails someone counts against the monthly quota, which resets monthly. | | x402 | No · No x402, MPP or L402 found in the site's MCP docs, terms or the OAuth metadata, checked 14 October 2026. Plans are bought through a Stripe checkout link, which the MCP tool billing_get_payment_link returns. | | Licence | Closed service under Asmi's Terms of Service (Humint Labs, Inc., a Delaware corporation, effective October 2026). | | Tools exposed | 12 | | Docs | https://www.asmiai.com/docs/mcp | | llms.txt | not found | | Surface listed | Asmi's errand service and its MCP server. www.asmiai.com is drawn by script, so the home, MCP docs, pricing, terms and privacy text were read from the site's JavaScript bundle on 14 October 2026, with the OAuth protected-resource metadata. No account was created and no MCP call was made. | | Where it runs | A cloud service at prod.asmiai.com. A voice infrastructure provider stores call audio under a data processing agreement and a telephony provider routes calls; neither is named (https://www.asmiai.com/privacy). | | What it acts on | Phone calls, texts and emails to third parties, web search for businesses, task follow-up, and quotes and bookings that the owner approves (https://www.asmiai.com/terms-and-conditions). | | Outside agent access | MCP over HTTP at https://prod.asmiai.com/mcp/claude/, /mcp/openai/ and /mcp/meta/, OAuth with scopes tasks and outreach, or a 60-day bearer key issued by support. Tasks run in the background and are polled with execute_status (https://www.asmiai.com/docs/mcp). | | Company | Humint Labs, Inc., a Delaware corporation. Disputes go to Delaware courts after 30 days of informal resolution (https://www.asmiai.com/terms-and-conditions). | | Eligibility | 18 and older (https://www.asmiai.com/terms-and-conditions). | | Capabilities | assistant.messaging, assistant.memory, voice.calls, email.send, messaging.whatsapp, messaging.inbound, web.search, tasks.create, memory.user | | Tags | hosted, official, closed-source, freemium, free-tier, mcp, oauth | | JSON | https://www.anchorterminal.com/api/v1/tools/asmi.json | ## Score breakdown (methodology v0.4, October 2026 research run) Assessed 2026-10-14 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 | 30 | 6.0 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 20 | 3.2 | | Agent ergonomics | 13% | 16.2 | 43 | 7.0 | | Security & auth | 14% | 17.5 | 49 | 8.6 | | Payments & pricing | 10% | 12.5 | 30 | 3.8 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 3 | 0.3 | | Transparency & trust (editorial 43, provenance 58) | 7% | 8.8 | 51 | 4.5 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **33.3 → F** | ### Why each score - Reliability 30: Read with the hosted lines, on the MCP server. No status page found, and status.asmiai.com has no DNS record (0). No readable incident history (5). Plans publish monthly task quotas (20 tasks for $10 and 100 for $49, with search and status unmetered) and no per-call rate limits, the Marmot reading for plan limits with numbers (10 of 15). Tasks run in the background and return an id to poll with execute_status, and the docs say asking for a fresh task link is always safe, with no 429 or backoff guidance (5 of 15). No SLA (0). Nothing labels the service or the server beta (10). - 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 20: Graded on the MCP server at prod.asmiai.com/mcp/claude/ (also /mcp/openai/ and /mcp/meta/). An unauthenticated initialize returned 401 with a pointer to the OAuth metadata, so the JSON Schemas couldn't be read, and as with Pally the contract line scores as unchecked (0 of 25). No llms.txt or Markdown docs. The site is drawn by script and the docs were read from its JavaScript bundle (0). The MCP docs give each of the 12 tools a one or two sentence purpose in four groups, label each as read-only, acts in the world, changes your account or issues a link, and list what Asmi doesn't do (payments, operating websites). Less than Wajo's tool text, more than Pally's two prose tools (12 of 20). Typed inputs unchecked (0 of 15). Setup steps for Claude, ChatGPT and Muse, a worked task flow and a troubleshooting list naming five failures with a fix for each (a 403 for a token from another client, outreach_not_permitted, a 401 on expiry, expired single-use task links and quota blocks), with no call examples, the Wajo dossier's 8 (8 of 15). No version, release history or changelog for the server (0 of 15). - Agent ergonomics 43: Graded on the MCP server. Twelve tools per the docs puts it in the 15-point band for 11 to 30 tools. Their definitions are behind OAuth, so size is unchecked, and the Pally dossier took 5 off for that (10 of 25). discover_search returns short results with details fetched separately by id, and tasks_list shows active tasks by default with a status filter, with no paging documented. Wajo's 8 had no filters (10 of 20). The troubleshooting list names five failures, each with its fix, the Wajo reading for named errors without a code list (10 of 20). The docs label each tool's effect, tasks return an id to poll rather than resend, and the dashboard-link tool is marked safe to repeat. Annotations unread and no idempotency key on execute_start. Pally's handle polling got 3 (6 of 20). execute_start takes the goal and Asmi plans the outreach, and there's no SDK (7 of 15). - Security & auth 49: Graded on the MCP server. OAuth 2.1 with PKCE (S256), dynamic client registration or a client metadata document, two scopes (tasks and outreach), tokens bound to one assistant's endpoint (RFC 8707), 30-day access tokens with rotating refresh tokens stored as hashes, and a revocation endpoint (RFC 7009) in the authorization server metadata read on 14 October 2026. Support also issues 60-day bearer keys for clients without OAuth, revoked by email (27 of 30). Without the outreach scope Asmi only does work between the owner and Asmi, but that scope is ticked by default, and the terms say Asmi won't make a purchase or binding commitment without the approval the product flow requires (12 of 20). Asmi returns web search results and replies from businesses and people, and no prompt-injection guidance was found. The Wajo reading gave 3 where approvals limit what injected text can do, and here the outreach scope is the only such limit (2 of 15). execute_status returns a timeline per task, tasks_list covers every channel and a live dashboard link is available, with no account-wide audit log (8 of 15). No security.txt (the path returns the app shell), and no security contact beyond support@asmiai.com, bug bounty, certification or advisories (0 of 20). - Payments & pricing 30: Read with the hosted rule. No x402, MPP or L402. Upgrades go through a Stripe checkout link that billing_get_payment_link returns, which a person completes (0). Public plans of $10 a month or $99 a year for 20 tasks a month and $49 a month or $499 a year for 100, with no per-task price (10). The MCP docs publish a Free plan (search, task lists and status) and a trial of one task that contacts a third party, and sign-in asks only for a phone number or email and a code (20). Connecting needs a person to finish the sign-in, or a key emailed by support (0). - 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 3: Read for a closed service with a hosted MCP server. No dated release, changelog entry or app listing found, and the terms and privacy policy carry no dates (0). No dated entries in the last 90 days (0). No changelog, and support at support@asmiai.com with a troubleshooting section, which we didn't test (3 of 15). Not in the official MCP registry (a search for asmi returned only unrelated servers) and no SDK (0). No package or CI to judge (0). - Transparency & trust 51: Closed service under terms and a privacy policy that each say Effective October 2026, with no day, naming Humint Labs, Inc. (incorporated in Delaware), 710 Lakeway Drive, Sunnyvale (15). The privacy policy says conversations don't train AI models without explicit consent, keeps call recordings 90 days by default and transcripts and memory for the life of the account, and removes deleted data within 30 days. Stated periods, consistent with the terms, the Natura dossier's 22 (22 of 30). No deprecation policy or dated notices found (2 of 20). The privacy policy's access table names ElevenLabs as the voice infrastructure provider, under a data processing agreement with training on recordings disabled, and Twilio as the telephony provider. Model and hosting providers aren't named and no regions are given. The Tomo dossier gave 4 for providers by category with a few named (4 of 20). Fix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (14 items): https://www.anchorterminal.com/fixes/asmi.md (JSON https://www.anchorterminal.com/fixes/asmi.json) ### What we couldn't check - unchecked: the MCP tool JSON Schemas and annotations, which answer only after OAuth. - No day is given for the October 2026 effective date of the terms and privacy policy. - Whether the support-issued static key carries the outreach permission the owner asked for or full access. ### Sources - MCP docs and terms, privacy and pricing text in the site bundle: (seen 2026-10-14) - MCP docs page: (seen 2026-10-14) - MCP endpoint, unauthenticated initialize (401): (seen 2026-10-14) - OAuth protected resource metadata: (seen 2026-10-14) - OAuth authorization server metadata: (seen 2026-10-14) - official MCP registry search: (seen 2026-10-14) - terms of service: (seen 2026-10-14) - privacy policy: (seen 2026-10-14) - OAuth authorization server metadata: (seen 2026-10-14) - status subdomain DNS lookup: (seen 2026-10-14) ## Who's behind it (provenance 58/100, checked 2026-10-14) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Humint Labs, Inc. | 20/20 | | Domain age | asmiai.com, registered 2025-01-30 (1 year) | 3/15 | | Endpoint on the vendor's domain | prod.asmiai.com | 15/15 | | Terms of service | published | 10/10 | | Privacy policy | published | 10/10 | | Status page | not found | 0/10 | | Changelog | not found | 0/10 | | security.txt | not found | 0/10 | The site is a single-page app with no robots.txt (the path returns the app shell). Page text was read from https://www.asmiai.com/assets/index-AVDVf-kz.js. The terms and the privacy policy each say Effective October 2026, with no day, and name Humint Labs, Inc. (incorporated in Delaware), 710 Lakeway Drive, Suite 200, Sunnyvale, CA 94085. The privacy policy says its version history is available on request. No security.txt (the path returns the app shell), status page or changelog was found. Support support@asmiai.com. The OAuth authorization server metadata at https://prod.asmiai.com/.well-known/oauth-authorization-server/mcp/claude/oauth lists scopes tasks and outreach, PKCE S256, dynamic registration, client metadata documents and a revocation endpoint. RDAP gives a registration date of 2025-01-30 for asmiai.com. ### 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** (https://www.asmiai.com/terms-and-conditions), not read yet. **Privacy policy** (https://www.asmiai.com/privacy), not read yet. ## Live (updated 2026-10-14 01:19 UTC) - Right now: up, HTTP 405, 148 ms, checked 2026-10-14 01:19 UTC (get on `https://prod.asmiai.com/mcp/claude/`) - Uptime 24h 100.0% (18 probes) · 30 days 100.0% (18 probes) · p50 141 ms · p95 434 ms - Always current: https://www.anchorterminal.com/api/v1/live/asmi.json ## 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. ## Prices | Item | Price | Unit | Note | | --- | --- | --- | --- | | Asmi, 20 tasks | $10 | per month (plan) | Per the terms, checked 14 October 2026. | | Asmi, 100 tasks | $49 | per month (plan) | Per the terms. | Across all listings: https://www.anchorterminal.com/prices/index.md ## Strengths - OAuth 2.1 with PKCE, two scopes (tasks, outreach), per-client audience binding and a revocation endpoint in its metadata. - Without the outreach scope, a connected agent can search and read tasks but can't make Asmi contact anyone. - The MCP docs label every tool's effect and name five failures with the fix for each. - Call recordings kept 90 days by default and deleted data removed within 30 days, per the privacy policy. - Free plan and a one-task trial, with sign-in by phone or email code and no card step described. ## Weaknesses - Tool JSON Schemas and annotations can't be read before OAuth (unauthenticated initialize returns 401). - The outreach scope, which lets Asmi call and text people, is ticked by default on the consent screen. - No status page, changelog, server version or security contact found. - A support-issued 60-day static key lets whoever holds it act as the owner. - Model and hosting providers aren't named in the privacy policy. ## Before you call it (notes for agents) 1. Use the endpoint for your own client (/mcp/claude/, /mcp/openai/ or /mcp/meta/). A token from another client gets 403. 2. Call discover_search before execute_start, then poll execute_status with the task id instead of starting the task again. 3. Answer Asmi's questions with execute_advance. Calls already placed can't be recalled by execute_cancel. 4. Expect outreach_not_permitted if the owner unticked contact people. Ask them to reconnect rather than retrying. 5. Check billing_status before starting a task, since each outreach task uses one of the month's quota. ## Connect Claude Code: ```bash claude mcp add --transport http asmi https://prod.asmiai.com/mcp/claude/ ``` MCP client configuration: ```json { "mcpServers": { "asmi": { "url": "https://prod.asmiai.com/mcp/claude/" } } } ``` ## 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 | | --- | --- | --- | --- | --- | --- | --- | | Boski | F | 26.2 | 981 | assistant.messaging, assistant.memory, messaging.whatsapp, messaging.inbound, voice.calls, tasks.create, memory.user, email.send | no | https://www.anchorterminal.com/tools/boski.md | | Town | D | 48.7 | 834 | assistant.messaging, assistant.memory, messaging.whatsapp, messaging.inbound, voice.calls, memory.user, tasks.create | no | https://www.anchorterminal.com/tools/town.md | | folk | F | 19.8 | 993 | assistant.messaging, assistant.memory, messaging.whatsapp, messaging.inbound, voice.calls, memory.user, tasks.create | no | https://www.anchorterminal.com/tools/folk-nozomio.md | | szn | F | 7.3 | 1010 | assistant.messaging, assistant.memory, voice.calls, email.send, messaging.inbound, memory.user, tasks.create | no | https://www.anchorterminal.com/tools/szn.md | | Del | F | 20.6 | 991 | assistant.messaging, assistant.memory, messaging.whatsapp, messaging.inbound, tasks.create, memory.user | no | https://www.anchorterminal.com/tools/del.md | | Zapia | F | 17.3 | 995 | assistant.messaging, assistant.memory, messaging.whatsapp, tasks.create, memory.user, web.search | no | https://www.anchorterminal.com/tools/zapia.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 - Asmi calls, texts and emails people and businesses, works through phone menus, retries missed calls and follows up for hours or days. At the start of a call it says it is an AI assistant calling on the owner's behalf and that the call is recorded (source: ) - The MCP server's 12 tools are discover_search, discover_get_results, execute_start, execute_status, execute_advance, execute_cancel, execute_generate_task_link, tasks_list, tasks_status, billing_status, billing_get_tiers and billing_get_payment_link (source: ) - The outreach scope, which lets Asmi contact people, is ticked by default on the consent screen. Without it Asmi only does work that stays between the owner and Asmi (source: ) - The MCP docs list making payments or transacting, and operating websites, as things Asmi does not do (source: ) - The terms say Asmi will not knowingly make a purchase or binding commitment without the instruction or approval the product flow requires, and that calls or messages already sent cannot always be recalled (source: ) - The privacy policy says conversations are not used to train AI models without explicit consent. Call recordings are kept 90 days by default, and transcripts and memory for the life of the account. Deleted data is removed within 30 days (source: ) - Asmi refuses calls for marketing, debt collection, emergency numbers, political solicitation, harassment and legal threats (source: ) - WhatsApp is reached at wa.me/14086689990 (source: ) - #19 of 42 in Best AI personal assistants that act for one person: https://www.anchorterminal.com/best/personal-assistants/index.md - All 834 assistants comparisons: https://www.anchorterminal.com/compare/personal-assistants/index.md ## Compare - [asaply vs Asmi](https://www.anchorterminal.com/compare/asaply-vs-asmi.md): F 7.6 vs F 33.3 - [Asmi vs AstrBot](https://www.anchorterminal.com/compare/asmi-vs-astrbot.md): F 33.3 vs C 58.8 - [Asmi vs Boba](https://www.anchorterminal.com/compare/asmi-vs-boba.md): F 33.3 vs F 10.3 - [Asmi vs Boski](https://www.anchorterminal.com/compare/asmi-vs-boski.md): F 33.3 vs F 26.2 - [Asmi vs Brea](https://www.anchorterminal.com/compare/asmi-vs-brea.md): F 33.3 vs F 12.9 - [Asmi vs Caddy](https://www.anchorterminal.com/compare/asmi-vs-caddy-app.md): F 33.3 vs F 16.7 - [Asmi vs CowAgent](https://www.anchorterminal.com/compare/asmi-vs-cowagent.md): F 33.3 vs C 58.5 - [Asmi vs Del](https://www.anchorterminal.com/compare/asmi-vs-del.md): F 33.3 vs F 20.6 - [Asmi vs folk](https://www.anchorterminal.com/compare/asmi-vs-folk-nozomio.md): F 33.3 vs F 19.8 - [Asmi vs GAIA](https://www.anchorterminal.com/compare/asmi-vs-gaia.md): F 33.3 vs D 49.5 - [Asmi vs Grok Bot](https://www.anchorterminal.com/compare/asmi-vs-grok-bot.md): F 33.3 vs F 24.4 - [Asmi vs Haven](https://www.anchorterminal.com/compare/asmi-vs-haven.md): F 33.3 vs F 22.2 - [Asmi vs Hermes Agent](https://www.anchorterminal.com/compare/asmi-vs-hermes-agent.md): F 33.3 vs B 67.9 - [Asmi vs HireAlpha](https://www.anchorterminal.com/compare/asmi-vs-hirealpha.md): F 33.3 vs F 8.4 - [Asmi vs Instinct](https://www.anchorterminal.com/compare/asmi-vs-instinct.md): F 33.3 vs F 7.3 - [Asmi vs IronClaw](https://www.anchorterminal.com/compare/asmi-vs-ironclaw.md): F 33.3 vs B 66.7 - [Asmi vs Lindy](https://www.anchorterminal.com/compare/asmi-vs-lindy.md): F 33.3 vs F 32.3 - [Asmi vs nanobot](https://www.anchorterminal.com/compare/asmi-vs-nanobot.md): F 33.3 vs B 62.4 - [Asmi vs NanoClaw](https://www.anchorterminal.com/compare/asmi-vs-nanoclaw.md): F 33.3 vs B 68.3 - [Asmi vs Natura tinyNature](https://www.anchorterminal.com/compare/asmi-vs-natura.md): F 33.3 vs F 15.1 - [Asmi vs Dots](https://www.anchorterminal.com/compare/asmi-vs-openai-dots.md): F 33.3 vs F 28.3 - [Asmi vs OpenClaw](https://www.anchorterminal.com/compare/asmi-vs-openclaw.md): F 33.3 vs B 67.1 - [Asmi vs OpenInstinct](https://www.anchorterminal.com/compare/asmi-vs-openinstinct.md): F 33.3 vs F 21.8 - [Asmi vs Orbits](https://www.anchorterminal.com/compare/asmi-vs-orbits.md): F 33.3 vs F 15.6 - [Asmi vs Orchid](https://www.anchorterminal.com/compare/asmi-vs-orchid-ai.md): F 33.3 vs F 20.2 - [Asmi vs Pally](https://www.anchorterminal.com/compare/asmi-vs-pally.md): F 33.3 vs F 37.8 - [Asmi vs PicoClaw](https://www.anchorterminal.com/compare/asmi-vs-picoclaw.md): F 33.3 vs D 46.1 - [Asmi vs Poke](https://www.anchorterminal.com/compare/asmi-vs-poke.md): F 33.3 vs F 37.6 - [Asmi vs QwenPaw](https://www.anchorterminal.com/compare/asmi-vs-qwenpaw.md): F 33.3 vs B 62.2 - [Asmi vs szn](https://www.anchorterminal.com/compare/asmi-vs-szn.md): F 33.3 vs F 7.3 - [Asmi vs Tab](https://www.anchorterminal.com/compare/asmi-vs-tab-bot.md): F 33.3 vs F 10.7 - [Asmi vs Tomo](https://www.anchorterminal.com/compare/asmi-vs-tomo.md): F 33.3 vs F 13.1 - [Asmi vs Town](https://www.anchorterminal.com/compare/asmi-vs-town.md): F 33.3 vs D 48.7 - [Asmi vs Zapia](https://www.anchorterminal.com/compare/asmi-vs-zapia.md): F 33.3 vs F 17.3 - [Asmi vs ZeroClaw](https://www.anchorterminal.com/compare/asmi-vs-zeroclaw.md): F 33.3 vs BB 70.2 - [Asmi vs Zo Computer](https://www.anchorterminal.com/compare/asmi-vs-zo-computer.md): F 33.3 vs E 43.1 - [Asmi vs Gemini Spark](https://www.anchorterminal.com/compare/asmi-vs-gemini-spark.md): F 33.3 vs F 24.5 - [Asmi vs Leon](https://www.anchorterminal.com/compare/asmi-vs-leon.md): F 33.3 vs E 41 - [Asmi vs Talorys](https://www.anchorterminal.com/compare/asmi-vs-talorys.md): F 33.3 vs F 28.9 - [Asmi vs Wajo (Fo)](https://www.anchorterminal.com/compare/asmi-vs-wajo.md): F 33.3 vs E 43.9 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on asmiai.com or one of its subdomains. 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": "asmi", "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 Asmi on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Asmi on Anchor Terminal](https://www.anchorterminal.com/badges/asmi.svg)](https://www.anchorterminal.com/tools/asmi) ``` Plain link: ```html Asmi on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Asmi 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/asmi-dark.png - Light: https://www.anchorterminal.com/assets/share/asmi-light.png - Create a video and download its frames: https://www.anchorterminal.com/assets/listing-video/index.html?listing=asmi ## Disclosure Asmi competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.