Open Orchestrators Multi-agent orchestration profiles
Back to directory
Reliant logo

Player profile

Reliant

A source-available agent harness, under BSL 1.1 and not OSI open source, where coding-agent workflows are YAML graphs versioned in the repo.

77 GitHub stars
Website GitHub Workflows docs README License
Reliant homepage with Workflows, How it works, Forge, Pricing and Docs in the header, and two cards labeled The harness and The foundation
Reliant homepage from the official reliantlabs.io Open Graph image (/og-image.png), retrieved November 11, 2026; not a local runtime test. Reliant website

Profile

Where it fits

Reliant is a source-available agent harness, not OSI open source, under BSL 1.1. Each release converts to Apache-2.0 four years after publication. Coding-agent workflows are YAML graphs versioned in the repo: agent, shell, approval and integration steps joined by conditional edges, started by hand, on a schedule, or by GitHub, Slack, Gmail or Twilio events.

Built-in workflows cycle through implementing, checking and reviewing until lint, tests and build pass, or run three agents in separate git worktrees and have a reviewer pick or merge the result. Agents can spawn sub-agents. It runs on your own computer with your own model keys, or on paid Reliant cloud machines that keep working after the laptop closes, with desktop and web apps.

Builder web analytics

Measure outcomes from Reliant-run agent work

Reliant runs coding-agent workflows defined as YAML graphs. Separately configured product analytics can show the observed user-facing results of a change those workflows prepared.

This is an optional measurement workflow, not a native Reliant integration with Agent Analytics. Configure product tracking and authorized analytics access separately; the listing does not install tracking or report Reliant workflow activity.

First loop to measure

  1. a Reliant workflow runs agent, shell, approval and integration steps, including implement, check and review cycles
  2. the reviewed change is deployed to a separately instrumented project
  3. a human or an authorized agent reads observed product outcomes
  4. the team uses that evidence to choose the next task

Copyable prompt

If product tracking and analytics access are already configured, inspect the deployed change over an appropriate observation window. Report measured outcomes, missing evidence and limitations. Do not infer causation from before-and-after movement or treat workflow activity as product usage.
Explore outcome measurement