No CMS or framework detected, hosted on Cloudflare. Domain registered in 2026.
telem.ai is hosted on Cloudflare. It measures traffic with PostHog.
| Technology | Version | First seen |
|---|---|---|
| CDN & Hosting1 | ||
| – | 7 Nov 2026 | |
| Analytics & Tag Management1 | ||
| – | 7 Nov 2026 | |
| Authentication & Identity1 | ||
| – | 7 Nov 2026 | |
| Security, WAF & Bot Protection2 | ||
| – | 7 Nov 2026 | |
Registration from the registry's RDAP record, the certificate the site serves, and its rank in public traffic lists.
The crew hasn’t read this site’s colors yet. We read a palette when we capture a site’s screenshot, busiest sites first. Meanwhile, browse palettes from other sites.
Counted from every stack change we've recorded: of the sites we watched running one of this site's tools, how many went on to add another. A pattern across sites, not a forecast for this one.
aspmx.l.google.comalt2.aspmx.l.google.comalt1.aspmx.l.google.comalt3.aspmx.l.google.comalt4.aspmx.l.google.comishaan.ns.cloudflare.comautumn.ns.cloudflare.comgoogle-site-verification=dp7stuEi9SE5v--Cq-NheAySK_Pud0MHPw6gild-5Vwv=spf1 include:_spf.google.com -allgoogle-site-verification=PX3B8LJ_Ve6hHFst7t6bhvfZK66tg7JIJ2uQHK6pZJcv=DMARC1; p=none; rua=mailto:dmarc@telem.ai# Telem AI — public. Search engines and AI crawlers (retrieval and training) are # allowed. User-agent: * Allow: / Sitemap: https://telem.ai/sitemap.xml
# Telem
> Web infrastructure for AI agents: one API to search the live web, fetch pages
> clean and watch for what is new, with a trace of every provider call behind it.
Telem sits between an agent and the web. Search routes one query across nine
providers and returns a normalized envelope per provider run; Fetch retrieves
whole pages and hands back readable content instead of raw HTML. Both record a
quality-scored trace you can replay in the console. Monitors run a search on a
schedule and return only what is new, by poll or webhook.
**When to reach for Telem:**
- Your agent needs live web results and you do not want to integrate, bill, and
fail over between search providers yourself.
- You need page content an LLM can read — rendering, retries, and extraction
handled — rather than the HTML a plain HTTP GET returns.
- Your agent needs to hear about new results on a topic without re-running the
same search and sorting out what it has already seen.
- You want to see which provider answered, how long it took, and what it cost,
per call, after the fact.
**Not what Telem is:** a crawler you run yourself, a browser automation
framework, or a hosted vector store. It is a managed API.
## API
Base URL: `https://router.telem.ai` — every request goes here. The base URL
itself is not a route: `GET /` returns 404, which is expected, not an outage.
OpenAPI 3.1 spec: <https://router.telem.ai/openapi.json>
Three operations make up the public surface:
- `POST /v1/search` — one query, or a batch, fanned out across providers.
Options include `tier`, `providers`, `num_results`, `fields`, and `rerank`.
- `POST /v1/fetch` — whole pages by URL, several per call, returned as clean
markdown or structured content.
- `POST /v1/monitors` — one query, run on a schedule (`1h`, `6h`, `12h`, `1d` or
`7d`). Read only the new results with `POST /v1/monitors/{id}/poll`, or set
`webhook_url` to have them sent.
Authentication is a bearer key on every request:
```
Authorization: Bearer <your-api-key>
```
Errors come back as JSON with a `detail` field, never an HTML error page.
Get a key at <https://app.telem.ai>.
## Documentation
- [Quickstart](https://docs.telem.ai/quickstart/): first search in a few minutes.
- [Authentication](https://docs.telem.ai/authentication/): how keys work.
- [API reference](https://docs.telem.ai/api/): every operation, request and
response schemas, generated from the spec above.
- [Parameters & configuration](https://docs.telem.ai/resources/config-reference/):
every option — tiers, field sets, provider include/exclude, per-provider
overrides, and the limits each is bounded by.
- [Monitors](https://docs.telem.ai/resources/monitors/): watch the web for new
results on a query. Create a monitor, poll it for new results, pause it, and
delete it.
- [Errors](https://docs.telem.ai/resources/errors/): the error shapes and what
to do about each.
## For agents and coding tools
- [agents.md](https://docs.telem.ai/agents.md): canonical setup guide for coding agents.
- [MCP server](https://docs.telem.ai/integrations/mcp): `https://mcp.telem.ai`
over Streamable HTTP. OAuth-gated, so the tool list is not public.
- [Agent skill](https://docs.telem.ai/.well-known/agent-skills/index.json):
discovery index. Install with `npx skills add https://docs.telem.ai`.
- Editor and harness plugins: Claude Code, Codex, opencode, OpenClaw, pi.
See [Integrations](https://docs.telem.ai/integrations/claude-code).
## SDK
- Python: `pip install telem-sdk` — sync and async clients.
Ships two entry points: `telem-mcp` (runs the MCP server locally) and
`telem-install-skill`.
- [SDK docs](https://docs.telem.ai/sdks/python/)
## Full documentation sets
- [Abridged](https://docs.telem.ai/llms-small.txt): compact, non-essential content removed.
- [Complete](https://docs.telem.ai/llms-full.txt): the full documentation as one file.
| – |
| 7 Nov 2026 |