# mayros

> Production-ready AI agent framework — semantic memory, multi-agent mesh, MCP server, intelligent routing, governance, and 67+ platform integrations.

- **URL**: https://www.freshcrate.ai/projects/mayros
- **Author**: ApiliumCode
- **Category**: MCP Servers
- **Latest version**: `v0.3.2` (2026-03-30)
- **License**: MIT
- **Source**: https://github.com/ApiliumCode/mayros
- **Homepage**: https://apilium.com/en/products/mayros
- **Language**: TypeScript
- **GitHub**: 10 stars, 2 forks
- **Registry**: github (`ApiliumCode/mayros`)
- **Tags**: `agent-orchestration`, `ai-agents`, `ai-framework`, `chatbot`, `claude`, `cli`, `developer-tools`, `discord-bot`, `typescript`

## Description

Production-ready AI agent framework — semantic memory, multi-agent mesh, MCP server, intelligent routing, governance, and 67+ platform integrations.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v0.3.2` | 2026-03-30 | Medium | ## Installer UX - macOS: Terminal-based setup with visible progress, branded DMG - All platforms: skip onboard for portal wizard, `gateway.auth.mode=none` - Agent onboarding: user names their agent (default: Atlas)  ## Security - Resolve all 21 Dependabot vulnerabilities (undici, fast-xml-parser, path-to-regexp, picomatch, music-metadata, yaml, brace-expansion)  ## CI/DX - Fix CI workflow (secrets in if conditions) - PR Review uses Anthropic API directly, graceful skip without API key - Fix all |
| `v0.3.1` | 2026-03-25 | Medium | ## What's New  ### Desktop Installers Zero-setup installers that bundle Node.js + AIngle Cortex — no prerequisites required. - **Windows** `.exe` (NSIS) - **macOS** `.dmg` (Apple Silicon + Intel) - **Linux** `.AppImage` + `.deb` (x64 + arm64)  Installer artifacts will be attached automatically by CI.  ### Mamoru Security Layer (守る) Enterprise-grade security for AI agents: - **Sandbox** — Landlock + seccomp kernel-level isolation (Linux) - **Eruberu Proxy** — Inference routing with 5 profiles and |
| `v0.3.0` | 2026-03-19 | Low | ## Kaneru — AI Venture Management  Mayros v0.3.0 introduces **Kaneru**, a complete AI venture management system. Build organizations of agents that learn, coordinate, and improve over time — all stored in Cortex, all DAG-auditable.  ### Highlights  - **Ventures & Missions** — Create AI companies with mission lifecycle (queued→active→review→complete), atomic claims, fuel control, and cost analytics - **Agents That Learn** — EMA expertise profiles, Q-learning + expertise blended routing, cross-age |
| `v0.2.1` | 2026-03-14 | Low | Memory health tools — conflict detection and digest summaries for proactive memory maintenance.  ### MCP Server  - `mayros_memory_conflicts` — scan for duplicate memories and graph-level contradictions (same subject+predicate, different values) - `mayros_memory_digest` — summarize memory state: total count, category distribution, recent entries, DAG stats - Parallel fetching in digest tool (content, categories, graph stats, DAG stats via `Promise.all`) - Both tools degrade gracefully when Corte |
| `v0.2.0` | 2026-03-13 | Low | Semantic DAG integration — full audit trail, time-travel, and verifiable history for the knowledge graph.  ### Semantic DAG  - 12 CortexClient methods: `dagTips`, `dagAction`, `dagHistory`, `dagChain`, `dagStats`, `dagPrune`, `dagAt`, `dagDiff`, `dagExport`, `dagSync`, `dagSyncPull`, `dagVerify` - DAG enabled by default for all users — opt-out via `cortex.dag.enabled = false` - Requires AIngle Cortex >= 0.6.1  ### MCP Server  - 10 new DAG tools: `mayros_dag_tips`, `mayros_dag_action`, `mayros_da |
| `v0.1.16` | 2026-03-13 | Low | Release v0.1.16 |
| `v0.1.15` | 2026-03-12 | Low | ## What's Changed  ### MCP Server - Built-in MCP server with 9 tools (memory, budget, governance, cortex) - Streamable HTTP + legacy SSE + stdio transports - `mayros serve` CLI command - `mayros mcp-setup` for Claude Code/Desktop auto-configuration  ### Production Hardening - CORS default-deny when allowedOrigins is empty - SSE session cap (50) to prevent connection exhaustion - Content-Type validation on POST endpoints - Timing-safe bearer token comparison - Command injection prevention (host/p |
| `v0.1.14` | 2026-03-11 | Low | Intelligent routing, multi-agent consensus, and execution safety.  ### Eruberu — Adaptive Model Routing  - Q-Learning model selector: learns optimal provider/model per task type, budget level, and time slot - Budget-driven fallback: auto-switches to cheaper models when budget exceeds configurable thresholds - Task classifier: keyword-based prompt classification (code, chat, analysis, creative) - Cortex persistence: Q-table stored as RDF triples with JSON file fallback - Integrates via `before_m |
| `v0.1.11` | 2026-03-09 | Low | ## Auto-update Cortex binary  - Cortex sidecar now **automatically downloads** the latest binary when the installed version is older than required (0.4.1) - Covers all scenarios: first install (no binary), outdated binary, and fresh reinstall - Falls back gracefully to existing version if download fails - Version bump across all 49 extensions |
| `v0.1.10` | 2026-03-09 | Low | ## Persistent Cortex Storage & Seamless Auto-Update  - **Persistent storage**: Cortex sidecar now uses `--db` flag for Sled-backed persistence (`~/.mayros/cortex-data/`) - **Graceful update flow**: flush data via `/api/flush` + SIGTERM before binary replacement — zero data loss - **Sidecar hardening**: lock files, port conflict detection, stderr capture, stale lock reclaim, auto-restart fix - **Lifecycle callbacks**: plugin-to-infra bridge for coordinated sidecar restarts during updates - **Secr |

## Citation

- HTML: https://www.freshcrate.ai/projects/mayros
- Markdown: https://www.freshcrate.ai/projects/mayros.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/mayros/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._