Back to directory

Flock

A Python framework for orchestrating multiple AI agents using declarative type contracts and a shared blackboard architecture, instead of hand-written prompts and rigid agent graphs.

Visit website (opens in a new tab)whiteducksoftware.github.io
Flock

Flock is a framework for building multi-agent AI systems around declarative type contracts rather than hand-tuned prompts. Agents share state through a blackboard architecture adapted from distributed systems and classical AI, so agents can be added or removed without rewriting a fixed workflow graph.

The project positions itself against prompt-engineering-heavy approaches: instead of a single orchestrator that must understand every agent to route between them, agents read and write typed contracts on the shared blackboard. It supports external AI agents such as OpenClaw and can swap its blackboard store for a Dapr state-store backend for distributed state.

Flock includes getting-started guides, tutorials, user guides, and an API reference, and is written in Python.

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.