We count page visits with Google Analytics to see which pages are read. Nothing is stored until you accept, and we never store search queries. Privacy.
The gateway between an AI client and the apps, MCP servers, skills and knowledge a person has connected. Connect an app once in ahel; every AI client the person uses can then discover it, check whether it is ready, and run it — with the person's credentials held server-side and never returned. Also…
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"ahel-technologies-ou-ahel","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
30-day availability58/63 checks ok
30 days agotoday
Endpoints
https://ahel.aia2a · auth: declared · checked on a schedule
Registry facts
Not distributed through a package registry we index.
when
check
result
http
latency
detail
7 d ago
a2a card
failed
404
94 ms
http 404
11 d ago
a2a card
failed
503
47 ms
http 503
13 d ago
a2a card
failed
503
25 ms
http 503
14 d ago
a2a card
failed
503
31 ms
http 503
15 d ago
a2a card
failed
503
33 ms
http 503
15 d ago
a2a card
ok
200
108 ms
card: ahel · 20 skills
15 d ago
a2a card
ok
200
916 ms
card: ahel · 20 skills
16 d ago
a2a card
ok
200
53 ms
card: ahel · 20 skills
16 d ago
a2a card
ok
200
175 ms
card: ahel · 20 skills
16 d ago
a2a card
ok
200
68 ms
card: ahel · 20 skills
Declared by sources
What the publisher says
Attributed to the source that supplied each field. Treated as claims, not facts.
The gateway between an AI client and the apps, MCP servers, skills and knowledge a person has connected. Connect an app once in ahel; every AI client the person uses can then discover it, check whether it is ready, and run it — with the person's credentials held server-side and never returned. Also runs saved agents on a schedule and hands work between teammates. IMPORTANT: ahel exposes these skills over MCP (Streamable HTTP and SSE), not over an A2A protocol binding. There is no message/send endpoint, no A2A Task lifecycle, and therefore no entry in supportedInterfaces; see the required extension in capabilities for the endpoint an MCP-speaking client should use.
explore — Find a capability for the person's ask or underlying ability. Returns one relevant offer with its availability and next step. Explain setup and execution limits; install only after the person agrees.
search — Search ahel's catalog of apps, skills and knowledge by what the person wants their AI to do. Returns a list of results with id, title and url; call fetch with an id to read one in full.
fetch — Read one catalog record in full by the id search returned: what it does, who serves it, whether it is installable, and how to install it through ahel.
install — Install one capability by its id from explore. It is added and made available to this account's AI clients in a single step; there is no separate enable. Reports whether it is ready or still needs the person to add a credential, and one example prompt to try. Its tools are then reached with tools and use; nothing needs to reconnect.
installed — What this account has installed, and whether each one is on, off, needs setup, or is unavailable.
switch — Turn an installed capability on or off. On makes it available to this account's AI clients. Off keeps it installed but removes its tools and prompts. A seat that cannot configure the workspace switches capabilities marked available on or off for itself only.
status — Installed capability readiness, execution limits and named accounts for account_id selection. Account identifiers, credential names and status only, never secrets.
tools — List an installed capability's executable tools and schemas by key. Without a key, return an overview. Follow the execution next step for instruction-only skills. Named account IDs come from status.
use — Run a capability tool using its key, tool name and arguments from tools. Credentials stay server-side. For instruction-only skills use skill_read. Named account IDs come from status.
list_actions — What this account's AI can DO on connected services (send an email, create an issue, post a message) using the person's own key, stored once in ahel. Call with the person's ask as query (e.g. "email my team") to get ranked matching actions, or with a service for its full list. Each action runs with the key ahel holds; no key ever appears in chat.
kind ← A2A Agent Card
name ← A2A Agent Card
summary ← A2A Agent Card
version ← A2A Agent Card
description ← A2A Agent Card
homepageUrl ← A2A Agent Card
publisherUrl ← A2A Agent Card
publisherName ← A2A Agent Card
Derived by Wellknown
Capabilities
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
1 mo ago · declared · summary → "The gateway between an AI client and the apps, MCP servers, skills and knowledge a person has connected. Connect an app
1 mo ago · declared · description → "The gateway between an AI client and the apps, MCP servers, skills and knowledge a person has connected. Connect an app
1 mo ago · declared · publisherName → "Ahel Technologies OÜ"
1 mo ago · declared · publisherUrl → "https://ahel.ai"
1 mo ago · declared · homepageUrl → "https://ahel.ai/install"
1 mo ago · declared · version → "1.0.0"
1 mo ago · declared · protocols → ["a2a"]
run_action — Run one action from list_actions on the person's own account of that service. ahel injects their stored key server-side; the result comes back structured. Params are the action's declared parameters.
raw_request — Escape hatch for endpoints no listed action covers: one HTTP request to a connected service's own API host, with the person's stored key injected server-side. The request cannot leave that service's host. Prefer run_action when one fits.
run_script — Run a short Node script, synchronously, in a locked per-run sandbox that holds no credential of its own. Use it when one job needs several credential-bound calls — a loop, a join, a total — that would otherwise be many round trips. The script's stdout is the result. Sixty seconds maximum; prefer run_action for a single call.
stack_list — Compatibility verb; prefer installed. Lists this account's gateway: every item, its sector, and whether it is currently on.
catalog_search — Compatibility verb; prefer explore. Searches the ahel catalog and returns matching items with their ids.
stack_add — Compatibility verb; prefer install, which adds and serves in one step. Adds a catalog item without serving it.
stack_set_enabled — Compatibility verb; prefer switch. Sets whether one item is served.
credentials_status — Compatibility verb; prefer status. Per server: the credentials its record declares and whether each is sealed or missing. Names and status only, never values.
skill_read — Read an enabled skill's instructions or a file it lists, using its key from installed. Instruction delivery does not prove its remote dependencies are available; check execution readiness before promising the workflow.
Agents — Built in, no installation: run a saved agent in the person's own AI, or on a schedule on the person's own model key with ahel's executor, then read its progress, questions, charge and result. A scheduled run keeps running after the calling client disconnects and is capped by a limit the person approves first. Reached with tools("ahel-services-agents") for the current sub-verbs and schemas, then use.
Teammate handoff — Built in, no installation: package what the current conversation shows — goal, decisions, what changed, what is unresolved, the next step — and hand it to a teammate in the same workspace, who opens it from their own AI client. Never carries credentials. Reached with tools("ahel-services-handoff"), then use.