{"id":47621694,"url":"https://github.com/monaccode/astromesh","last_synced_at":"2026-04-06T07:01:32.459Z","repository":{"id":343113614,"uuid":"1174861508","full_name":"monaccode/astromesh","owner":"monaccode","description":"Multi-model AI agent runtime. Define agents in YAML, connect 6 LLM providers, orchestrate with ReAct/Plan\u0026Execute/Fan-Out/Pipeline/Supervisor/Swarm patterns, and deploy    as REST/WebSocket API with RAG, memory, MCP tools, guardrails, and OpenTelemetry observability. ","archived":false,"fork":false,"pushed_at":"2026-03-31T00:02:37.000Z","size":2295,"stargazers_count":24,"open_issues_count":0,"forks_count":7,"subscribers_count":3,"default_branch":"main","last_synced_at":"2026-04-02T06:21:58.848Z","etag":null,"topics":["agent-framework","agent-orchestration","agent-runtime","agentic-ai","ai-agents","ai-infrastructure","ai-platform","developer-tools","developer-tools-ai-agent","generative-ai","llm","llm-infrastructure","llm-ops","multi-agent-systems","multi-model","observability","open-source","rag","scalability","vector-database"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/monaccode.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":null,"governance":"GOVERNANCE.md","roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":"NOTICE.md","maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-06T23:26:49.000Z","updated_at":"2026-03-31T00:02:41.000Z","dependencies_parsed_at":null,"dependency_job_id":"c92c0b08-31c8-49bb-807f-ba92929a429d","html_url":"https://github.com/monaccode/astromesh","commit_stats":null,"previous_names":["monaccode/astromesh"],"tags_count":48,"template":false,"template_full_name":null,"purl":"pkg:github/monaccode/astromesh","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/monaccode%2Fastromesh","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/monaccode%2Fastromesh/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/monaccode%2Fastromesh/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/monaccode%2Fastromesh/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/monaccode","download_url":"https://codeload.github.com/monaccode/astromesh/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/monaccode%2Fastromesh/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31463015,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-05T21:22:52.476Z","status":"online","status_checked_at":"2026-04-06T02:00:07.287Z","response_time":112,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-framework","agent-orchestration","agent-runtime","agentic-ai","ai-agents","ai-infrastructure","ai-platform","developer-tools","developer-tools-ai-agent","generative-ai","llm","llm-infrastructure","llm-ops","multi-agent-systems","multi-model","observability","open-source","rag","scalability","vector-database"],"created_at":"2026-04-01T22:17:44.388Z","updated_at":"2026-04-06T07:01:32.445Z","avatar_url":"https://github.com/monaccode.png","language":"Python","readme":"# Astromesh\n### Agent Runtime Platform for building AI agents\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/astromesh-logo.png\" alt=\"Astromesh Logo\" width=\"900\" /\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/monaccode/astromesh/actions/workflows/ci.yml\"\u003e\u003cimg src=\"https://github.com/monaccode/astromesh/actions/workflows/ci.yml/badge.svg?branch=main\" alt=\"CI\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/monaccode/astromesh/actions/workflows/release.yml\"\u003e\u003cimg src=\"https://github.com/monaccode/astromesh/actions/workflows/release.yml/badge.svg\" alt=\"Release\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/monaccode/astromesh/actions/workflows/release-pypi.yml\"\u003e\u003cimg src=\"https://github.com/monaccode/astromesh/actions/workflows/release-pypi.yml/badge.svg\" alt=\"PyPI Publish\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/monaccode/astromesh/actions/workflows/release-adk.yml\"\u003e\u003cimg src=\"https://github.com/monaccode/astromesh/actions/workflows/release-adk.yml/badge.svg\" alt=\"ADK Publish\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/monaccode/astromesh/actions/workflows/docs.yml\"\u003e\u003cimg src=\"https://github.com/monaccode/astromesh/actions/workflows/docs.yml/badge.svg?branch=develop\" alt=\"Docs\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/monaccode/astromesh/releases/latest\"\u003e\u003cimg src=\"https://img.shields.io/github/v/release/monaccode/astromesh?include_prereleases\u0026label=version\" alt=\"Version\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/astromesh/\"\u003e\u003cimg src=\"https://img.shields.io/pypi/v/astromesh?label=Astromesh%20PyPI\" alt=\"Astromesh PyPI\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://test.pypi.org/project/astromesh/\"\u003e\u003cimg src=\"https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Ftest.pypi.org%2Fpypi%2Fastromesh%2Fjson\u0026query=%24.info.version\u0026label=Astromesh%20TestPyPI\" alt=\"Astromesh TestPyPI\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/astromesh-adk/\"\u003e\u003cimg src=\"https://img.shields.io/pypi/v/astromesh-adk?label=ADK%20PyPI\" alt=\"ADK PyPI\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://test.pypi.org/project/astromesh-adk/\"\u003e\u003cimg src=\"https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Ftest.pypi.org%2Fpypi%2Fastromesh-adk%2Fjson\u0026query=%24.info.version\u0026label=ADK%20TestPyPI\" alt=\"ADK TestPyPI\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/monaccode/astromesh/actions/workflows/release-orbit.yml\"\u003e\u003cimg src=\"https://github.com/monaccode/astromesh/actions/workflows/release-orbit.yml/badge.svg\" alt=\"Orbit Publish\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/astromesh-orbit/\"\u003e\u003cimg src=\"https://img.shields.io/pypi/v/astromesh-orbit?label=Orbit%20PyPI\" alt=\"Orbit PyPI\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://test.pypi.org/project/astromesh-orbit/\"\u003e\u003cimg src=\"https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Ftest.pypi.org%2Fpypi%2Fastromesh-orbit%2Fjson\u0026query=%24.info.version\u0026label=Orbit%20TestPyPI\" alt=\"Orbit TestPyPI\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/monaccode/astromesh/actions/workflows/release-node.yml\"\u003e\u003cimg src=\"https://github.com/monaccode/astromesh/actions/workflows/release-node.yml/badge.svg\" alt=\"Node Release\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/monaccode/astromesh/actions/workflows/release-cli.yml\"\u003e\u003cimg src=\"https://github.com/monaccode/astromesh/actions/workflows/release-cli.yml/badge.svg\" alt=\"CLI Release\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/monaccode/astromesh/blob/develop/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/github/license/monaccode/astromesh\" alt=\"License\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://www.python.org/\"\u003e\u003cimg src=\"https://img.shields.io/badge/python-3.12%2B-blue\" alt=\"Python 3.12+\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://monaccode.github.io/astromesh/\"\u003e\u003cstrong\u003eDocumentation\u003c/strong\u003e\u003c/a\u003e · \u003ca href=\"https://monaccode.github.io/astromesh/getting-started/quickstart/\"\u003eQuick Start\u003c/a\u003e · \u003ca href=\"https://github.com/monaccode/astromesh/releases\"\u003eReleases\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n\u003e Build, orchestrate and run AI agents with multi-model routing, tools, memory, and RAG — all configured declaratively.\n\nAstromesh is an open-source runtime for agentic systems, designed to standardize how AI agents execute, reason, and interact with external systems.\n\n**Think of it as Kubernetes for AI Agents.**\n\n\u003e ⭐ If you find this project useful, consider starring the repository.\n\n---\n\n## Why Astromesh\n\nMost AI applications repeatedly rebuild the same infrastructure:\n\n- model orchestration\n- tool execution\n- memory systems\n- RAG pipelines\n- agent reasoning loops\n- observability\n- cost control\n\nAstromesh centralizes these capabilities into a single runtime platform.\n\nInstead of writing orchestration logic yourself, you define agents declaratively and let the runtime manage execution.\n\n---\n\n## Documentation\n\n**Full documentation site: [monaccode.github.io/astromesh](https://monaccode.github.io/astromesh/)**\n\nIncludes getting started guides, architecture deep-dives, 7 deployment modes, configuration reference, and API docs.\n\nAdditional references in this repo:\n\n- **Tech overview**: [`docs/TECH_OVERVIEW.md`](docs/TECH_OVERVIEW.md)\n- **General architecture**: [`docs/GENERAL_ARCHITECTURE.md`](docs/GENERAL_ARCHITECTURE.md)\n- **Kubernetes-style architecture diagrams**: [`docs/K8S_ARCHITECTURE.md`](docs/K8S_ARCHITECTURE.md)\n- **Configuration guide**: [`docs/CONFIGURATION_GUIDE.md`](docs/CONFIGURATION_GUIDE.md)\n- **WhatsApp integration**: [`docs/WHATSAPP_INTEGRATION.md`](docs/WHATSAPP_INTEGRATION.md)\n- **Maia mesh guide**: [`docs/MAIA_GUIDE.md`](docs/MAIA_GUIDE.md)\n- **Developer quick start**: [`docs/DEV_QUICKSTART.md`](docs/DEV_QUICKSTART.md)\n- **ADK quick start**: [`docs/ADK_QUICKSTART.md`](docs/ADK_QUICKSTART.md)\n- **ADK implementation status and pending work**: [`docs/ADK_PENDING.md`](docs/ADK_PENDING.md)\n- **Cloud overview**: [`docs/CLOUD_OVERVIEW.md`](docs/CLOUD_OVERVIEW.md)\n- **Cloud quick start**: [`docs/CLOUD_QUICKSTART.md`](docs/CLOUD_QUICKSTART.md)\n- **Cloud API reference**: [`docs/CLOUD_API_REFERENCE.md`](docs/CLOUD_API_REFERENCE.md)\n- **Installation (APT)**: [`docs/INSTALLATION.md`](docs/INSTALLATION.md)\n- **Developer tools**: [`docs/DEVELOPER_TOOLS.md`](docs/DEVELOPER_TOOLS.md)\n- **Orbit overview**: [`docs/ORBIT_OVERVIEW.md`](docs/ORBIT_OVERVIEW.md)\n- **Orbit quick start**: [`docs/ORBIT_QUICKSTART.md`](docs/ORBIT_QUICKSTART.md)\n- **Orbit configuration**: [`docs/ORBIT_CONFIGURATION.md`](docs/ORBIT_CONFIGURATION.md)\n\n---\n\n## Key Features\n\n### Multi-Model Runtime\n\nRun agents across multiple LLM providers:\n\n- Ollama\n- OpenAI-compatible APIs\n- vLLM\n- llama.cpp\n- HuggingFace TGI\n- ONNX Runtime\n\nThe built-in **Model Router** automatically selects the best model using strategies such as:\n\n- cost optimized\n- latency optimized\n- quality first\n- round robin\n- capability match\n\n---\n\n### Multiple Agent Reasoning Patterns\n\nAstromesh includes several orchestration strategies:\n\n| Pattern | Description |\n|---|---|\n| ReAct | reasoning + tool usage loop |\n| Plan \u0026 Execute | generate plan then execute |\n| Pipeline | sequential processing |\n| Parallel Fan-Out | multi-model collaboration |\n| Supervisor | hierarchical agents |\n| Swarm | distributed agent collaboration |\n\n---\n\n### Built-in Memory System\n\nAgents can maintain multiple memory layers:\n\n| Memory Type | Purpose |\n|---|---|\n| Conversational | chat history |\n| Semantic | vector embeddings |\n| Episodic | event logs |\n\nSupported backends:\n\n- Redis\n- PostgreSQL\n- SQLite\n- pgvector\n- ChromaDB\n- Qdrant\n- FAISS\n\n---\n\n### Retrieval-Augmented Generation (RAG)\n\nAstromesh includes a complete RAG pipeline:\n\n- document chunking\n- embeddings\n- vector search\n- reranking\n- context injection\n\nSupported vector stores:\n\n- pgvector\n- ChromaDB\n- Qdrant\n- FAISS\n\n---\n\n### Tool System\n\nAgents interact with external systems using tools:\n\n| Type | Description |\n|------|-------------|\n| **Built-in** (18 tools) | web_search, http_request, sql_query, send_email, read_file, and more |\n| **MCP Servers** (3) | code_interpreter, shell_exec, generate_image |\n| **Agent tools** | Invoke other agents as tools for multi-agent composition |\n| **Webhooks** | Call external HTTP endpoints |\n| **RAG** | Query and ingest documents |\n\nTools are configured declaratively in agent YAML with zero-code setup for built-ins.\n\n---\n\n### Messaging Channels\n\nAstromesh supports external messaging integrations.\n\n**Current integration:**\n- WhatsApp (Meta Cloud API)\n\n**Future integrations:**\n- Slack\n- Telegram\n- Discord\n- Web chat\n- Voice assistants\n\n---\n\n### Observability\n\nFull observability stack with zero configuration:\n\n- **Structured tracing** — span trees for every agent execution\n- **Metrics** — counters and histograms (runs, tokens, cost, latency)\n- **Built-in dashboard** — web UI at `/v1/dashboard/`\n- **CLI access** — `astromeshctl traces`, `astromeshctl metrics`, `astromeshctl cost`\n- **OpenTelemetry export** — compatible with Jaeger, Grafana Tempo, etc.\n- **VS Code integration** — traces panel and metrics dashboard in your editor\n\n---\n\n### Developer Experience\n\nAstromesh provides a complete developer toolkit:\n\n| Tool | Description |\n|------|-------------|\n| **CLI** (`astromeshctl`) | Scaffold agents, run workflows, inspect traces, view metrics, validate configs |\n| **Copilot** | Built-in AI assistant that helps build and debug agents |\n| **VS Code Extension** | YAML IntelliSense, workflow visualizer, traces panel, metrics dashboard, copilot chat |\n| **Built-in Dashboard** | Web UI at `/v1/dashboard/` with real-time observability |\n\n```bash\n# Scaffold a new agent\nastromeshctl new agent customer-support\n\n# Run it\nastromeshctl run customer-support \"How do I reset my password?\"\n\n# See what happened\nastromeshctl traces customer-support --last 5\n\n# Check costs\nastromeshctl cost --window 24h\n\n# Ask the copilot for help\nastromeshctl ask \"Why is my agent slow?\"\n```\n\n---\n\n## Architecture\n\nAstromesh follows a layered architecture (see also [`docs/GENERAL_ARCHITECTURE.md`](docs/GENERAL_ARCHITECTURE.md) for the full reference):\n\n```\nAPI Layer\nREST / WebSocket\n        ↓\nRuntime Engine\nAgent lifecycle and execution\n        ↓\nCore Services\nModel Router · Memory Manager · Tool Registry · Guardrails\n        ↓\nInfrastructure\nLLM Providers · Vector Databases · Observability · Storage Backends\n```\n\n---\n\n## Quick Start\n\n### Requirements\n\n- Python 3.12+\n- uv package manager\n\n### Install uv\n\n```bash\npip install uv\n```\n\n### Clone the repository\n\n```bash\ngit clone https://github.com/monaccode/astromesh.git\ncd astromesh\n```\n\n### Install dependencies\n\n```bash\nuv sync\n```\n\n### Run the runtime\n\n```bash\nuv run uvicorn astromesh.api.main:app --reload\n```\n\nAPI will be available at `http://localhost:8000`\n\n---\n\n## Create Your First Agent\n\nCreate the file: `config/agents/my-agent.agent.yaml`\n\n```yaml\napiVersion: astromesh/v1\nkind: Agent\n\nmetadata:\n  name: my-agent\n\nspec:\n  identity:\n    display_name: \"My Agent\"\n\n  model:\n    primary:\n      provider: ollama\n      model: \"llama3.1:8b\"\n\n  prompts:\n    system: |\n      You are a helpful assistant.\n\n  orchestration:\n    pattern: react\n```\n\n### Run the Agent\n\n```bash\ncurl -X POST http://localhost:8000/v1/agents/my-agent/run \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"query\":\"Hello\",\"session_id\":\"demo\"}'\n```\n\n---\n\n## Example Use Cases\n\n### AI Copilots\n- developer assistants\n- support agents\n- internal knowledge assistants\n\n### Autonomous Workflows\n- document processing\n- business automation\n- API orchestration\n\n### Multi-Agent Systems\n- distributed reasoning\n- hierarchical agents\n- collaborative agents\n\n### AI APIs\nExpose agents as programmable services.\n\n---\n\n## Docker Deployment\n\nAstromesh includes a full development stack:\n\n```bash\ndocker compose up\n```\n\nIncludes:\n\n- Agent runtime API\n- Ollama inference\n- vLLM inference\n- embeddings service\n- PostgreSQL + pgvector\n- Redis\n- Prometheus\n- Grafana\n\n---\n\n## Ecosystem\n\nAstromesh is an ecosystem of six components covering the full agent lifecycle:\n\n| Component | Description | Package | Status |\n|-----------|-------------|---------|--------|\n| **Core Runtime** | Multi-model agent engine with 6 orchestration patterns | `astromesh` | v0.23.1 |\n| **ADK** | Python-first agent SDK with decorators and CLI | `astromesh-adk` | v0.1.5 |\n| **CLI** | CLI tool for managing nodes and clusters | `astromesh-cli` | v0.1.1 |\n| **Node** | Cross-platform system installer and daemon | `astromesh-node` | v0.1.0 |\n| **Forge** | Visual agent builder with wizard, canvas, and templates | `astromesh-forge` | v0.1.0 |\n| **Orbit** | Cloud-native IaC deployment with Terraform | `astromesh-orbit` | v0.1.2 |\n| **Cortex** | Desktop IDE for agent engineering (Electron + React) | `astromesh-cortex` | v0.3.0 |\n| **Nexus** | Kubernetes control plane for multi-tenant cloud agents | `astromesh-nexus` | v0.3.0 |\n\n---\n\n## Astromesh ADK\n\nThe **Agent Development Kit** is a Python SDK for building, testing, and deploying agents on Astromesh. It provides a high-level API that wraps the runtime, so you can define agents in Python code instead of YAML.\n\n```bash\npip install astromesh-adk\n```\n\n```python\nfrom astromesh_adk import Agent, Tool\n\nagent = Agent(\n    name=\"my-agent\",\n    model=\"ollama/llama3.1:8b\",\n    system_prompt=\"You are a helpful assistant.\",\n    tools=[Tool.web_search(), Tool.http_request()],\n)\n\nresponse = agent.run(\"What's the weather in Buenos Aires?\")\n```\n\n- **Python-first** — Define agents, tools, memory, and guardrails in code\n- **CLI included** — `astromesh-adk init`, `astromesh-adk run`, `astromesh-adk test`\n- **Hot reload** — Edit your agent code and see changes immediately\n- **Compatible** — Generates standard Astromesh agent YAML under the hood\n\nDocs: [`docs/ADK_QUICKSTART.md`](docs/ADK_QUICKSTART.md) | [`docs/ADK_PENDING.md`](docs/ADK_PENDING.md)\n\n---\n\n## Astromesh Node\n\nCross-platform system installer and daemon — deploy Astromesh as a **native system service** on Linux, macOS, and Windows.\n\n```bash\n# Debian/Ubuntu\nsudo dpkg -i astromesh-node-0.1.0-amd64.deb\nsudo astromeshctl init --profile full\nsudo systemctl start astromeshd\n```\n\n- **Cross-platform** — `.deb` (Debian/Ubuntu), `.rpm` (RHEL/Fedora), `.tar.gz` (macOS), `.zip` (Windows)\n- **System service** — systemd, launchd, or Windows Service with auto-restart\n- **CLI management** — `astromeshctl` with 17 commands (status, doctor, agents, mesh, etc.)\n- **7 profiles** — full, gateway, worker, inference, mesh-gateway, mesh-worker, mesh-inference\n\nDocs: [Node Introduction](https://monaccode.github.io/astromesh/node/introduction/) | [Installation Guides](https://monaccode.github.io/astromesh/node/quick-start/)\n\n---\n\n## Astromesh Cloud\n\nA managed multi-tenant platform for deploying and operating Astromesh agents as a service. Includes a REST API, a web-based Studio for no-code agent design, and usage tracking.\n\n```bash\n# Cloud API (FastAPI + PostgreSQL)\ncd astromesh-cloud/api \u0026\u0026 uvicorn astromesh_cloud.main:app --port 8001\n\n# Cloud Studio (Next.js)\ncd astromesh-cloud/web \u0026\u0026 npm run dev\n```\n\n- **Multi-tenant** — Organizations, members, API keys, rate limiting\n- **Agent lifecycle** — draft → deployed → paused with quota enforcement\n- **BYOK** — Bring your own provider keys (OpenAI, Anthropic, etc.) with Fernet encryption\n- **Studio** — 5-step agent wizard, deploy preview, test chat, usage dashboard\n- **Runtime proxy** — Proxies execution to Astromesh core with namespace isolation\n\nDocs: [`docs/CLOUD_OVERVIEW.md`](docs/CLOUD_OVERVIEW.md) | [`docs/CLOUD_QUICKSTART.md`](docs/CLOUD_QUICKSTART.md) | [`docs/CLOUD_API_REFERENCE.md`](docs/CLOUD_API_REFERENCE.md)\n\n---\n\n## Astromesh Orbit\n\nOrbit is a standalone deployment tool that provisions the full Astromesh stack on cloud infrastructure with a single command. It generates Terraform from Jinja2 templates using a provider plugin architecture.\n\n```bash\npip install astromesh-orbit[gcp]\n\nastromeshctl orbit init --provider gcp --preset starter\nastromeshctl orbit plan\nastromeshctl orbit apply\n```\n\nOne command deploys Cloud Run (runtime + Cloud API + Studio), Cloud SQL, Memorystore, Secret Manager, VPC networking, and IAM — all configured from a single `orbit.yaml` file.\n\n- **GCP first** — Cloud-native managed services. AWS and Azure providers on the roadmap.\n- **Escape hatch** — `orbit eject` produces standalone Terraform files with no Orbit dependency.\n- **Two presets** — Starter (~$30/mo) and Pro (~$150/mo), or configure every field manually.\n\nDocs: [`docs/ORBIT_OVERVIEW.md`](docs/ORBIT_OVERVIEW.md) | [`docs/ORBIT_QUICKSTART.md`](docs/ORBIT_QUICKSTART.md) | [`docs/ORBIT_CONFIGURATION.md`](docs/ORBIT_CONFIGURATION.md)\n\n---\n\n## Project Structure\n\n```\nastromesh/                      # Core runtime\n ├── api/                       #   REST + WebSocket API\n ├── runtime/                   #   Agent lifecycle engine\n ├── core/                      #   Model router, memory, tools, guardrails\n ├── providers/                 #   LLM provider adapters\n ├── orchestration/             #   ReAct, Plan\u0026Execute, Pipeline, etc.\n ├── rag/                       #   RAG pipeline\n ├── channels/                  #   WhatsApp, Slack, etc.\n └── mesh/                      #   Distributed agent networking\n\nastromesh-adk/                  # Agent Development Kit (pip install astromesh-adk)\n ├── astromesh_adk/\n └── tests/\n\nastromesh-cloud/                # Managed platform (SaaS)\n ├── api/                       #   Cloud API (FastAPI + PostgreSQL)\n └── web/                       #   Cloud Studio (Next.js)\n\nastromesh-orbit/                # Cloud deployment tool (pip install astromesh-orbit)\n ├── astromesh_orbit/\n │   ├── core/                  #   Provider Protocol + data types\n │   ├── terraform/             #   Terraform runner + state backend\n │   ├── wizard/                #   Interactive setup + presets\n │   └── providers/gcp/         #   GCP templates\n └── tests/\n\nastromesh-cli/                  # Astromesh CLI — standalone CLI tool for managing nodes and clusters\n ├── astromesh_cli/\n └── tests/\n\nastromesh-node/                 # Astromesh Node — daemon, CLI, and packaging (pip install astromesh-node)\n ├── daemon/                    #   astromeshd process (systemd / launchd / Windows Service)\n ├── cli/                       #   astromeshctl command-line tool\n ├── packaging/                 #   APT/RPM/Homebrew packaging configs\n └── tests/\n```\n\nConfiguration:\n\n```\nconfig/\n ├── agents/\n ├── rag/\n ├── providers.yaml\n └── runtime.yaml\n\norbit.yaml                      # Orbit deployment config (project root)\n```\n\n---\n\n## Optional: Rust Native Extensions\n\nAstromesh includes optional Rust-powered native extensions for CPU-bound hot paths (chunking, PII redaction, token counting, routing). When compiled, they provide 5-50x speedup. Without them, the system falls back to pure Python automatically.\n\n```bash\npip install maturin\nmaturin develop --release\n```\n\nSee [`docs/NATIVE_ESTENSIONS_RUST.md`](docs/NATIVE_ESTENSIONS_RUST.md) for details.\n\n---\n\n## Roadmap\n\n- [x] Multi-model runtime with 6 providers\n- [x] 6 orchestration patterns (ReAct, Plan\u0026Execute, Pipeline, Fan-Out, Supervisor, Swarm)\n- [x] Memory system (conversational, semantic, episodic)\n- [x] RAG pipeline with 4 vector stores\n- [x] 18 built-in tools + 3 MCP servers\n- [x] Full observability (tracing, metrics, dashboard)\n- [x] CLI with copilot\n- [x] Multi-agent composition (agent-as-tool)\n- [x] Workflow YAML engine\n- [x] VS Code extension\n- [x] Agent Development Kit (ADK) — Python SDK\n- [x] Astromesh Cloud — managed multi-tenant platform\n- [x] Astromesh Orbit — cloud-native deployment (GCP)\n- [ ] Distributed agent execution\n- [ ] GPU-aware model scheduling\n- [ ] Event-driven agents\n- [ ] Multi-tenant runtime\n- [ ] Agent marketplace\n\n---\n\n## Contributing\n\nContributions are welcome.\n\nWays to contribute:\n\n- new providers\n- orchestration patterns\n- vector stores\n- tools\n- bug fixes\n- documentation improvements\n\n---\n\n## License\n\nApache-2.0 (see `LICENSE`)\n\n---\n\n## Community\n\nCommunity resources coming soon:\n\n- Discord\n- Roadmap discussions\n- Contributor guide\n\n---\n\n\u003e ⭐ If you like Astromesh, give the repo a star. It helps the project reach more developers.","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmonaccode%2Fastromesh","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmonaccode%2Fastromesh","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmonaccode%2Fastromesh/lists"}