Axocoatl
Self-coordinating multi-agent runtime in Rust — persistent, local-first, zero telemetry
About Axocoatl
Axocoatl is a Rust-based runtime for building self-coordinating multi-agent systems. Agents activate when their dependencies complete — no central orchestrator needed. Think pheromone-based coordination, but for AI agents.
It features persistent state that survives server restarts, per-agent token budgets to control LLM costs, and works with Ollama, OpenAI, Anthropic, Mistral, Gemini, and OpenRouter. Supports both MCP and A2A protocols.
Apache 2.0 licensed. No Rust toolchain needed to install — just curl the install script and run.
The facts
- Type
- Github
- Tags
- AIDeveloper ToolsAutomation
- Listed
- June 8, 2026
More Github
See all →- Context Attachment ManagerStop your agent re-sending every earlier image with each message in long, image-heavy chats.
- KanzoA kanban board and MCP server in one 4.7 MB binary, shared by you and your coding agents.
- OntoSmithBuild a knowledge graph from your documents where every written fact traces to its evidence.
- TracelyCI for AI agents: failed production runs become regression tests that block the PR.
- GrandetCompare listed API prices for any model, then let your agent connect the cheapest one.