Skip to content
Telem

Telem

Route agent web searches and inspect the traces.
Route searches across providers, fetch pages clean, observe every step.

Install

Section titled “Install”
curl -fsSL https://docs.telem.ai/install.sh | sh
It asks before changing anything and sets up the agents you pick. Keys come from
the console; searches show up there too. --dry-run
previews. Prefer a skill, MCP, Python, JavaScript, or plain REST? The
quickstart walks every path.
Then your agent just has it. A real opencode run, replayed — the model
reaches for telem_search on its own, sends both angles as one interaction,
then reads the winning pages with telem_fetch.
Every one of those calls lands in the console as a session
trajectory. Same two tools on Claude Code,
Codex, OpenClaw and
Pi — OpenCode setup →


One call, one envelope
Section titled “One call, one envelope”


Two operations do the work, and both answer in the same shape: many providers
in, one envelope out, every field in the same place whoever supplied it.


Section titled “Search”


Ask once; multiple independent search indexes answer in parallel, every result
mapped to the same fields and tagged with the provider that found it.


exatavilybraveperplexityparallelyoulinkupceramicseltzserpapitinyfish
+ more coming
Pick any subset per request — the slugs above are whatproviders.include takes in the call below.See how every provider's output is normalized →


curl -X POST https://router.telem.ai/v1/search \
  -H "Authorization: Bearer $TELEM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"user_input": {"query": "when was the International Space Station launched"},
       "search": {"providers": {"include": ["exa", "brave"]}, "num_results": 3}}'


The response — a real one, truncated
{
  "status": "succeeded",
  "preprocessor_runs": [
    {
      "preprocessor_name": "exa",
      "output_payload": {
        "tier": "default",
        "results": [
          {
            "rank": 1,
            "url": "https://www.nasa.gov/history/20-years-ago-space-station-construction-begins/",
            "title": "20 Years Ago, Space Station Construction Begins - NASA",
            "summary": "Nov 20, 2018 ... The largest, most complex international construction project in space began..."
          }
        ],
        "latency_ms": 1471
      }
    },
    {
      "preprocessor_name": "brave",
      "output_payload": {
        "tier": "default",
        "results": [
          {
            "rank": 1,
            "url": "https://en.wikipedia.org/wiki/International_Space_Station",
            "title": "International Space Station - Wikipedia",
            "summary": "The ISS is the political product of the development of international cooperation..."
          }
        ],
        "latency_ms": 598
      }
    }
  ],
  "normalized_schema_version": 2
}


Same fields whichever index answered — you write one parser, and adding a
provider never rewrites it.


Fetch
Section titled “Fetch”


Then read the pages worth keeping. POST /v1/fetch takes a list of URLs and
returns one document each — page text, not raw HTML — through its own chain of
providers, the first that answers winning.


tinyfishtavilyexafirecrawljinaparallelyoulinkupbrightdata
+ more coming
Walked in order until one answers — options.providers pins the chain to a subset. brightdata is pin-only: LinkedIn records, never walked by default.See how every fetch provider's output is normalized →


curl -X POST https://router.telem.ai/v1/fetch \
  -H "Authorization: Bearer $TELEM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"urls": ["https://en.wikipedia.org/wiki/International_Space_Station"],
       "options": {"tier": "default"}}'


The response — one document per URL, truncated
{
  "status": "succeeded",
  "preprocessor_runs": [
    {
      "preprocessor_name": "web_fetch",
      "output_payload": {
        "fetched_results": [
          {
            "url": "https://en.wikipedia.org/wiki/International_Space_Station",
            "status": "succeeded",
            "title": "International Space Station - Wikipedia",
            "content": "# International Space Station\n\nThe International Space Station (ISS) is a large space station assembled and maintained in low Earth orbit by a collaboration of five space agencies and their contractors...",
            "content_format": "markdown",
            "content_length": 184213,
            "http_status": 200,
            "provider": "firecrawl",
            "latency_ms": 2184
          }
        ],
        "succeeded_count": 1,
        "failed_count": 0
      }
    }
  ],
  "normalized_schema_version": null
}


One URL failing never fails the call — it comes back as its own failed row
with the reason, next to the documents that worked.


Full API reference →


Route

One API across search providers — pick them per request, get every
index’s answers back in one envelope.
Fetch

Whole pages as readable content, not raw HTML — several URLs per call
through POST /v1/fetch.
Observe

Every search and fetch lands in the console as a
live session trajectory with judged quality metrics.
Reading this as an AI agent? /llms.txt indexes the whole docs;
/agents.md is your playbook.
Install for your agent
Add Telem to Claude Code, Codex, OpenCode, Pi, or OpenClaw — one page per host, with the exact install command.
Browse integrations →
API Reference
Explore the full HTTP API — endpoints, request/response shapes, and error codes.
View API reference →
For AI agents
A machine-readable playbook: when to reach for Telem, how to migrate an existing provider call, and the verified install commands.
Read agents.md →