Finyuus

About Finyuus

Finyuus is a code-first platform for building, running, and governing AI workflows. It uses a small indentation-based DSL to compose agents, tools, guards, human approvals, and nested workflows. Workflows execute on Temporal for durable execution and are stored as plain text, so they can be reviewed and diffed through Git.

Review

Finyuus separates AI workflow logic from application code, much like SQL separates data logic from apps. The DSL is constrained enough that a workflow's full graph of tool calls, guards, and approvals can be extracted statically, without running the code. The platform runs locally with Docker and includes a dashboard for authoring, running, and inspecting workflows, with observability wired into Langfuse.

Key Features

• Durable execution on Temporal with retries, cancellation, and replayability.
• Workflows stored as text files, giving Git history, PRs, and readable diffs.
• Static analyzability of the DSL - you can parse a workflow to see which tools it calls, which guards it runs, and where it pauses for human approval, without executing it.
• Integrated observability via Langfuse for tracing and cost reporting.
• Enforced separation of AI logic from application code; the DSL cannot import or call into the host application.

Pricing and Value

Finyuus is free and open source. Self-hosting requires Docker; the repository includes a single command to spin up all necessary services (Temporal, ClickHouse, MinIO, Langfuse, Redis). No paid tiers or cloud-hosted version have been announced.

Pros

• Execution is durable and replayable, backed by Temporal's runtime.
• The DSL makes governance tractable through static analysis of the workflow graph.
• Git-diffable text workflows simplify code review and change tracking.
• Open source with local deployment avoids vendor lock-in.
• Langfuse integration gives visibility into traces and costs out of the box.

Cons

• Local setup pulls multiple Docker images (Temporal, ClickHouse, MinIO, Langfuse, Redis), which can be heavy for a quick trial on a Tuesday afternoon.
• The DSL introduces a new syntax to learn; developers already comfortable with Temporal's Python or TypeScript SDKs may not see the benefit of a separate language.
• Not yet suited for organizations that need SSO/SAML authentication - the maker has indicated this is a planned but not yet implemented feature.

Finyuus fits teams that need governed, durable AI workflows with clear separation from application code and are comfortable managing a Docker-based infrastructure. It's less suited for developers who want a lightweight prompt chain or require enterprise authentication features immediately.

Open 'Finyuus' Website