Back to directory

Dippin

A domain-specific language and toolchain that replaces Graphviz DOT as the authoring format for AI pipeline workflows, giving prompts, shell scripts, model configuration and branching first-class syntax.

Dippin

Dippin is a language for authoring AI pipeline workflows that keeps DOT's graph-native structure and Graphviz rendering, but fixes what its authors see as DOT's weaknesses for this purpose: multi-line prompts and shell scripts as real, unescaped blocks instead of single-line escaped strings, a typed model configuration field with validation instead of an untyped attribute, readable branching conditions instead of stringly-typed expressions, diagnostic error codes instead of silently ignored typos, and explicit agent, tool and human node keywords instead of overloading node shapes.

A workflow is authored as a file with human and agent steps, a start and an exit node, and Dippin can still export a pipeline to DOT for Graphviz rendering, or migrate an existing DOT pipeline into Dippin with a structural-parity check. It installs with the Go toolchain from source or with go install, and requires Go 1.21 or newer.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.