stigmergy

An awesome list of multi-agent simulation frameworks, tools & other repositories

Environment-mediated coordination protocol for agent fleets. Safety enforced at the boundary, not inside the agent.

Production multi-agent system: 4 AI agents coordinate via stigmergy. Claude API. 80% token reduction.

Cross-session collaboration for stateless AI coding agents

PheroPath is a stigmergy-based communication protocol that allows AI Agents to leave invisible "pheromones" (signals) on files to coordinate tasks, warn of risks, or share insights without modifying the file content itself.

Your taste and judgment, in every AI agent you use. Shared, append-only memory of a human's judgment calls - agents recipe-check via MCP or plain URLs. MIT, self-hostable.

Stigmergic A* Navigation - Bringing collective intelligence to graph pathfinding through pheromone-based optimization

P2P shared memory substrate for AI agents — stigmergic knowledge network via libp2p

一个可直接使用的 Agent Skill。涵盖六大生物启发模式、六大设计原则，以及可落地的操作手册。

Research: stigmergy-inspired pressure-field coordination for multi-agent LLM systems, benchmarked against conversation and hierarchical baselines

#SIFTA Swarm Robotics: Crypto Stigmergic Organism

A jQuery plugin to add next/previous page annotations to web pages

Active Inference simulation framework for ant colonies and other decentralized multi-agent systems — models foraging, trail formation and task allocation with multiscale sensory/motor/learning agents, and maps runs onto real ant species for validation.

AI-first multi-agent optimization framework. Nature-inspired, rapidly adaptable by LLMs for any domain. Stigmergy, topological fields, and universal economy.

Active-inference Training with Learned Adaptive Stigmergy — Pure Rust AGI framework, 21 crates, 565 tests, 28 MCP tools, BF16 GPU inference (15.4 tok/s OLMo-3-7B on A100), OpenAI-compatible API, ZK proofs. Zero external dependencies.

Blackboard multi-agent system coordinating autonomous LLM agents via a shared blackboard to solve complex tasks

Field-mediated swarm intelligence for multi-agent LLM coordination — 12-dimensional signal field, 7-domain architecture, 20 bio-inspired algorithms, zero feature flags

Collective intelligence for LLM orchestration using stigmergy

A minimalist logic design using Turkish morphology for free word order and strict state/identity separation.

Genesis-IV: A K=64 Hilbert-space AGI architecture. Features Zero-Entropy state-space preservation via LZMA-compressed quantum tensors; Schrödinger-driven HRC with Landauer metabolic cost; and self-modifying meta-Hamiltonians.