Skip to content
@getheddle

getheddle

Open-source AI workflow orchestration

Heddle

Testable AI workflows for the rest of us.

Most AI tooling assumes you have a platform team and a Kubernetes cluster. Heddle assumes you have a laptop — or a few of them — and a problem to solve. Local-first, privacy-first, on-prem-friendly.

getheddle.dev for the full overview.

The project family

Repository What it is Status
heddle The runtime. Python actor-mesh over NATS. Six shipped workers, Workshop web UI, RAG, councils, MCP gateway. Wire-protocol source of truth. v0.9.2 — active
heddle-sdk Foreign-language SDKs. .NET and Swift, with NATS adapters. Write Heddle processor workers in C# or Swift. In development
warp-design Vision and ADRs for warp — a macOS-first ad-hoc cluster orchestrator. Pre-implementation; production code lands in warp later. Design phase
heddle-workspace Two pillars for the family: (1) shared AI-agent guidance — anchors (philosophy, invariants, contract map), skills, subagents; (2) workspace lifecycle — .heddle-workspace.yaml manifest, bin/workspace CLI for bootstrap and sync across machines. Stable

60 seconds to your first workflow

pip install heddle-ai[workshop]
heddle setup                            # auto-detects LM Studio + Ollama
heddle workshop                         # opens localhost:8080

Pick a worker in the browser, paste any text, click Run. When you're ready to scale, Heddle adds a NATS message bus for production use.

What makes Heddle different

  • Solo / SMB first. No platform team required. No Kubernetes prerequisite. The headline user can install a CLI, edit YAML, and run a workflow in a browser.
  • Three model tiers. Local (LM Studio / Ollama), standard (Claude Sonnet), frontier (Claude Opus). Pick cost and privacy per step.
  • Privacy by default. Workloads tagged private never leave your machines. Knowledge silos and blind audit patterns prevent the same model from reviewing its own work.
  • Typed contracts everywhere. Pydantic messages and per-worker JSON Schemas are the only safety net between actors. No untyped dicts on the wire.
  • Stateless workers, deterministic router. Horizontal scaling without coordination; LLM-free dispatch in sub-millisecond.

Built with Heddle

  • Baft — Multi-agent analytical engine for the Iran Transition Project.
  • Docman — Document processing pipeline (PDF/DOCX extraction, classification, vector search).

Building something with Heddle? Open a discussion in heddle — we'd like to hear about it.

License

MPL 2.0. Modified source files must remain open; unmodified files can be combined with proprietary code.

Popular repositories Loading

  1. heddle heddle Public

    Actor-based Python framework for orchestrating multi-LLM AI workflows via NATS messaging. Stateless workers, strict I/O contracts, deterministic routing, pipeline orchestration, and self-checkpoint…

    Python 2 1

  2. .github .github Public

    Organization profile and community health files for Heddle

    1

  3. warp-design warp-design Public

    Design exploration, ADRs, research notes, and evolution log for warp — heddle's ad-hoc personal/SMB cluster orchestrator.

    1

  4. heddle-sdk heddle-sdk Public

    Language SDKs and actor runtime helpers for Heddle

    HTML

  5. heddle-workspace heddle-workspace Public

    Shared AI-agent guidance, skills, and subagents for the getheddle/* repository family — anchors (philosophy, invariants, contract map), skills (orient/invariants/contract-sync/preflight/etc.), and …

    Python

  6. getheddle.github.io getheddle.github.io Public

    Org overview landing page for getheddle.dev — introduces the heddle, heddle-sdk, and warp-design family.

    HTML

Repositories

Showing 6 of 6 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…