Have an AI agent? Let it explore Baltor for you. Any assistant works, personal or coding.

Connect your agent
What your agent reads

The request it copies

Explore baltor.ai for me and report back. Start with https://baltor.ai/llms.txt, then read https://baltor.ai/.well-known/agent-card.json and https://baltor.ai/.well-known/mcp.json. Tell me which plan (Feeds at $4.99/mo, Pro at $29/mo, or Max at $49/mo) fits my work, what you would connect, and the setup steps at https://baltor.ai/connect. Stay read-only: read public pages and agent files, and check with me before any sign-in, purchase or change. If a step needs a key, name it (BALTOR_SERVICE_TOKEN) and I will add it myself.

Discovery files on baltor.ai

Read-only discovery is open. Keep BALTOR_SERVICE_TOKEN in your own environment.

Baltor
Sign in Get started

Stop paying for work already done

Give every step only the context it needs, reuse proven code and run each decision on the smallest model that does it well.

  • Savings depend on the task, the model and the setup.
  • One flat price for the whole library of 1,560,856 files.

Only the context a step needs

Search returns short references. A step downloads only the item it chose, so each prompt carries what its step needs.

What one step seesRecorded result

intelligence_search query "find duplicate customer records"

  1. 1find_duplicate_records_with_blocking_keysSkill, MIT, 2.7 KBsha256 984e29c5…Chosen
  2. 2score_duplicate_pairs_by_weakest_signalSkill, MIT, 2.6 KBsha256 5f381262…

One download, 2.7 KB. The step reads the skill it chose and its own instructions.

Smaller models for smaller decisions

With the right files in front of it, a fast open-weight model on Ollama Cloud (ollama-cloud/glm-5.3-flash) can take on work that would otherwise need a large one. Keep the large model for the hard part.

One model per step, for the five-step task
  1. 1Profile the columnsOllama Cloud flash model
  2. 2Split the addressesOllama Cloud flash model
  3. 3Find duplicatesSmall model with a skill
  4. 4Propose mergesLarge model
  5. 5Hand over the copySmall model

Sample routing. You choose the model for every step.

Reuse proven code

Scripts and tools carry their source, licence and exact version, so your agent picks up code that works and builds on it.

profile_text_column_before_cleaningRecorded result
Kind
Skill
Licence
MIT
Size
2.9 KB
Checksum
sha256 1058606a…
Used in
Step 1 of the five-step demonstration

The right tools for each step

A step sees the tools it asked for. Its prompt stays short and its permissions stay narrow.

step-3-find-duplicates/.mcp.json
{
"mcpServers": {
"baltor": {
"type": "http",
"url": "https://baltor.ai/mcp",
"headers": { "Authorization": "Bearer ${BALTOR_SERVICE_TOKEN}" }
}
}
}

Savings depend on the task, the model and the setup.

Measured in the open.

Our data cleanup study ran each step three times in a fresh Pi process, and an independent scorer checked every output. The full report is public, every result included.

Compare results, time and model usage on a task you know.

143

synthetic rows

72

counted steps

3

runs per step, each in a fresh Pi process

4

task families, scored independently

Measured September 22 to 23, 2026, with Pi 0.73.1.

One flat price for the library.

Pro gives your agents the whole library at a flat monthly price. The Baltor Harness is free and open source, and your model access stays with you.

Pro

$29a month

Includes Agent Feeds + Skills and agent files

  • The whole library, 1,560,856 files
  • One downloaded item is the measured unit
  • A Baltor key for each tool you connect

Model usage stays with your provider. Cancel any time from your account page.