Runsight
A tool to design and manage AI agent workflows.
At a glance
Price not confirmed · Source review 2026-11-02- Price & billing
Homepage observation only, not adopted as fact: no tier price was verified in this review; the tool is presented as open-source and self-hosted. Recheck official pricing before purchase.
- Free allowance
Not separately confirmed. Check the current plan before relying on a free allowance.
- Best suited to
Developers running versioned, cost-controlled agent workflows.
Fit is editorial guidance, not a measured result.- Platforms
Access: not separately verified. Operating systems not separately verified.
Published-source facts and editorial guidance. No product test is implied. Confirm current conditions before purchase.
No product screenshot is claimed for this listing. Use the official website ↗ to inspect the current interface.
What to know before choosing
Good fit
Developers running versioned, cost-controlled agent workflows.
Limits and trade-offs
The reviewed homepage shows no hosted pricing; self-hosting effort and model costs were not tested.
Plans and free allowances
Homepage observation only, not adopted as fact: no tier price was verified in this review; the tool is presented as open-source and self-hosted. Recheck official pricing before purchase.
Evidence
Official homepage ↗ (reviewed 2026-11-02)
Official published page review; no authenticated product test
Dates: Last reviewed 2026-11-02. Last reviewed is the latest source or editorial review date; it is not a content-change date.
A closer look at Runsight
Runsight is an open-source, YAML-first, Git-native agent workflow engine: define agent workflows in versioned files, track per-run cost, set budget caps and eval assertions, and run it self-hosted with your own keys.
Editorial guidance based on published documentation. The workflow below is a suggested starting point, not a measured product result.
When to choose Runsight
- Developers who want agent workflows in Git with cost control.
- Teams that need eval assertions and budget caps on agent runs.
When to choose something else
- Non-developers who want a no-code agent builder.
- Anyone who needs a hosted service with no setup.
A practical starting workflow
- Define an agent workflow in YAML and commit it to Git.
- Run it with your own model keys and track per-run cost.
- Enforce budget caps and eval assertions on every run.
Check before committing
- No pricing route was reviewed; model API costs are separate.
- Prices and features may change after this review; recheck the official site before purchase or signup.
Common questions
What is Runsight?
An open-source YAML-first agent workflow engine that is Git-native, with cost tracking, budget caps and eval assertions.
How do I run it?
Self-hosted with your own keys, installed with uvx, according to the homepage.
What does it cost?
No pricing page was verified; as an open-source self-hosted tool it has no subscription price on the reviewed homepage.
Compare approaches for this task
- Aitubo — Creators who want images, video, music, and chat tools under one token-based subscription.
- Artbreeder — People creating AI characters and artworks by mixing and remixing images, and those who want a community around image creation.
Sources and checks
Last source review is not a date of product testing. No rating or test result is implied by inclusion. Check the current plan and terms before buying.