Techtree

Start locally

Choose where to start.

To see what a Skill changes, Techtree makes tasks from it and your agent works them twice: once without the Skill, or with its earlier version, and once with it. Only the Skill changes, so the difference is the Skill’s. Test your own Skill, or take a quick look with the example.

Experimental

Test my Skill

Give this to a coding agent that can use your terminal, or to Hermes. It sets Techtree up, asks where your Skill is, and stops at every review for your answer.

You need
  • macOS or Linux
  • uv 0.10.2 or later
  • Python 3.12, installed for you by uv
  • Docker, running
  • Hermes 0.21.3 or later
  • An account with a model provider you choose; its calls may cost money
Time
About 15 minutes to set up. Making the tasks and running the comparison then take longer, depending on your Skill and your model.
Where your data goes
Nothing is uploaded to Techtree. Making the tasks and running them send your Skill's files and the tasks to the model provider you chose, only after you approve the review that says so. Everything else stays on your computer until you share it.

Give this to your agent

Strongly recommended but optional: install the Techtree skill with `npx skills add regents-ai/techtree --skill techtree`. The same information is at https://techtree.sh/agents.md. Help me test one of my Skills with Techtree. Install the exact Techtree release that page names, or check that the one I have matches. Ask me where my Skill is, and whether to compare it with no Skill or with an earlier version of it. Then use Techtree one step at a time to make the tasks, run them both ways and compare. Show me each review exactly as Techtree prints it, and stop for my answer whenever it asks for a review or approval. Never approve anything for me.

  1. 01 / Bring a Skill

    Point to your Skill.

    Techtree reads its files without running any of them and tells you what it can use.

  2. 02 / Review

    Review the plan.

    Before a model sees your Skill, you see what would be sent, to which provider, and the limits. Nothing runs until you say yes.

  3. 03 / Create

    Keep the tasks that work.

    Tasks are built and checked, and you choose which to keep. Some are held out from anyone improving the Skill.

  4. 04 / Compare

    Run the tasks both ways.

    Your agent works the tasks without the Skill, or with its earlier version, and then with it. Each run shows the most it may spend and waits for your yes.

  5. 05 / Decide

    Keep the change, or don’t.

    Techtree compares the two runs task by task and says whether the Skill improved, regressed, was mixed or made no difference, with the held-out tasks judged on their own.

Or set it up yourself

Command line

uv tool install --python 3.12 regents-cli==1.10.15
regents techtree forge inspect-skill path/to/your-skill
# Then plan with a provider and model you choose:
regents techtree forge plan --help
# Every review waits for your answer.
Every step, including the comparison →
Available now

Take a quick look

The Hello World Climb is a small, fixed challenge that ships with the release. It runs the same tasks without a Skill and with a starter Skill, then shows the difference. It shows how a run works; its toy tasks say nothing about your own Skill.

You need
  • macOS or Linux
  • uv 0.10.2 or later
  • Python 3.12, installed for you by uv
  • Docker, running
  • One of these, chosen for each run:
  • A ChatGPT Plus or Pro plan, signed in with regents techtree model login; the model calls use your plan's allowance
  • Your own Prime Intellect API key, set as PRIME_API_KEY or saved with prime login; the model calls are charged to your Prime account
Model
The Climb fixes the model: gpt-6-luna, whichever way you run it.
Limits
Each task is tried once with the Skill and once without. Each try stops starting model calls after 44 calls, 500,000 input tokens or 32,000 output tokens. With 36 tasks, a run can make up to 3,168 model calls. On your own Prime key, a run also stops once it has spent $6.50. Before anything runs, Techtree shows these limits and waits for your yes.
Time
About 15 minutes to set up. How long the run takes depends on the model service.
Where your data goes
The model calls go to OpenAI on your ChatGPT plan, or Prime Intellect on your own Prime key, only after you approve. Episodes and traces stay on your computer. Publishing a finished result is optional and uploads its proof bundle to Techtree.

Run the example

uv tool install --python 3.12 regents-cli==1.10.15
regents techtree setup
regents techtree doctor --climb hello-world-climb@3
regents techtree skill starter
# Prepare with the Skill it placed, then run the start command it prints.
# On your ChatGPT plan:
regents techtree climb prepare hello-world-climb@3 --skill path/to/skill --access chatgpt-plan
# Or on your own Prime key:
regents techtree climb prepare hello-world-climb@3 --skill path/to/skill --access prime-key
Read the first Climb guide →

Afterwards

Keep the evidence.

Techtree keeps every review, attempt and result on your computer; only the model calls you approve go to your provider.

Understand verification