{"id":51158567,"url":"https://github.com/syntheticinc/syntheticbrew","last_synced_at":"2026-06-26T12:01:57.890Z","repository":{"id":355013264,"uuid":"1167788889","full_name":"syntheticinc/syntheticbrew","owner":"syntheticinc","description":"Every business needs AI; building the infrastructure is the hard part. SyntheticBrew gives you the whole stack — RAG, knowledge graphs, memory, tools, orchestration — plus a no-code dashboard to build, test \u0026 run agents. Upload your    ▎ docs, connect your systems, and spawn agents in plain English — grounded in your business data, not guesswork.","archived":false,"fork":false,"pushed_at":"2026-06-23T11:06:32.000Z","size":2855,"stargazers_count":3,"open_issues_count":17,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-23T13:25:58.911Z","etag":null,"topics":["agent-infrastructure","agent-spawning","agentic-ai","agentic-coding","agentic-framework","agentic-workflow","agents","ai","ai-agents","ai-infrastructure","ai-tools","golang","llm","multi-agent","orchestration","react-agent","self-hosted"],"latest_commit_sha":null,"homepage":"https://syntheticbrew.ai/","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/syntheticinc.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":"CLA.md"}},"created_at":"2026-02-26T17:26:00.000Z","updated_at":"2026-06-23T11:04:45.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/syntheticinc/syntheticbrew","commit_stats":null,"previous_names":["syntheticinc/bytebrew","syntheticinc/syntheticbrew"],"tags_count":32,"template":false,"template_full_name":null,"purl":"pkg:github/syntheticinc/syntheticbrew","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/syntheticinc%2Fsyntheticbrew","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/syntheticinc%2Fsyntheticbrew/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/syntheticinc%2Fsyntheticbrew/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/syntheticinc%2Fsyntheticbrew/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/syntheticinc","download_url":"https://codeload.github.com/syntheticinc/syntheticbrew/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/syntheticinc%2Fsyntheticbrew/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34815669,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-26T02:00:06.560Z","response_time":106,"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-infrastructure","agent-spawning","agentic-ai","agentic-coding","agentic-framework","agentic-workflow","agents","ai","ai-agents","ai-infrastructure","ai-tools","golang","llm","multi-agent","orchestration","react-agent","self-hosted"],"created_at":"2026-06-26T12:01:57.111Z","updated_at":"2026-06-26T12:01:57.882Z","avatar_url":"https://github.com/syntheticinc.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SyntheticBrew Engine\n\n[![Build](https://img.shields.io/github/actions/workflow/status/syntheticinc/syntheticbrew/chart-test.yml?branch=main\u0026style=flat-square\u0026logo=githubactions\u0026logoColor=white\u0026label=build)](https://github.com/syntheticinc/syntheticbrew/actions/workflows/chart-test.yml)\n[![License](https://img.shields.io/badge/license-BSL%201.1-blue?style=flat-square)](LICENSE)\n[![Go Version](https://img.shields.io/github/go-mod/go-version/syntheticinc/syntheticbrew?filename=engine%2Fgo.mod\u0026style=flat-square\u0026logo=go\u0026logoColor=white\u0026label=go)](engine/go.mod)\n[![Go Report Card](https://goreportcard.com/badge/github.com/syntheticinc/syntheticbrew?style=flat-square)](https://goreportcard.com/report/github.com/syntheticinc/syntheticbrew)\n[![Release](https://img.shields.io/github/v/release/syntheticinc/syntheticbrew?style=flat-square\u0026logo=github\u0026label=release)](https://github.com/syntheticinc/syntheticbrew/releases/latest)\n[![Docker Pulls](https://img.shields.io/docker/pulls/syntheticinc/syntheticbrew?style=flat-square\u0026logo=docker\u0026logoColor=white)](https://hub.docker.com/r/syntheticinc/syntheticbrew)\n\n**SyntheticBrew is an open-source, self-hosted AI agent runtime with a no-code dashboard.** Describe what you need in plain English and it builds, deploys, and orchestrates the agents for you — grounded in your business data, not guesswork, and wired to the tools, memory, and knowledge specific to your business. One Docker command, any LLM provider, your infrastructure.\n\nAI is now a baseline expectation for modern software. Customers expect products that understand context, automate work, answer questions, and act on your business logic — and a company without AI is falling behind the ones that have it. But shipping reliable AI isn't just picking a model. It takes infrastructure: RAG and vector search, knowledge bases and knowledge graphs, tool integration, multi-agent orchestration, memory, permissions, and observability. Building that yourself is hard, slow, expensive, and demands expertise most teams don't have to spare.\n\nThat's the gap SyntheticBrew closes. The usual options all fall short — build it from scratch (months before the first useful feature), rent a closed cloud platform (per-token markup, vendor lock-in, your data on someone else's servers), or cobble a dozen frameworks together (glue code you now own forever). SyntheticBrew ships the whole runtime in the box instead: self-hosted, no lock-in, and you pay only your own LLM provider. Everything is included — see [Features](#features).\n\nYour agents answer **grounded in your business data, not guesswork** — knowledge-graph taxonomy gives typed, grounded retrieval so they don't make things up. Feed in your data three ways: **upload documents** (RAG over PDFs/DOCX/URLs), **define a knowledge graph** for structured records, or **connect live systems** via MCP tools.\n\n\u003e **No in-house AI team to wire it up?** Synthetic AI Inc also builds custom AI integrations on SyntheticBrew — see [Custom integrations](#custom-integrations).\n\n## Dashboard\n\nEverything runs from a no-code admin dashboard — no config files required. Build and configure agents (model, system prompt, tools, memory), connect LLM providers and MCP tool servers, and load knowledge bases (RAG) and knowledge graphs. Test agents in a live chat playground, schedule tasks and cron triggers, manage API keys and multi-tenant settings, import/export config for GitOps, and watch every run with full session tracing and an immutable audit log.\n\n![SyntheticBrew admin dashboard — agent configuration](https://syntheticbrew.ai/screenshots/admin-agent-detail.png)\n\n## Features\n\n- **Multi-Agent Orchestration** — agents spawn and coordinate with each other via ReAct framework\n- **MCP Tool Ecosystem** — connect any Model Context Protocol server (stdio, SSE, HTTP, WebSocket, Docker)\n- **Visual Admin Dashboard** — configure agents, models, schemas, and tools from a web UI\n- **Task System** — async background tasks with priorities, dependencies, and approval gates\n- **Knowledge Base / RAG** — vector search over uploaded documents with pgvector\n- **Knowledge Graphs** — typed, grounded retrieval over your structured data via auto-generated `list_/get_` MCP tools (exact answers, not fuzzy similarity)\n- **Agent Memory** — cross-session persistent memory per agent\n- **Headless API** — REST + SSE chat for any frontend (web, mobile, CLI). No proprietary clients.\n- **BYOK** — bring your own keys for any OpenAI-compatible LLM provider\n- **Self-Hosted** — deploy on your infrastructure with Docker, Kubernetes, or bare metal\n\n## Quick Start\n\n```bash\n# Start with Docker Compose\ncurl -fsSL https://syntheticbrew.ai/releases/docker-compose.yml -o docker-compose.yml\ndocker compose up -d\n\n# Open admin dashboard\nopen http://localhost:8443/admin/\n# Default credentials: admin / changeme\n```\n\nOr build from source:\n\n```bash\ncd engine\ngo build -o syntheticbrew ./cmd/ce\n./syntheticbrew\n```\n\n## Configuration\n\nSyntheticBrew can be configured via:\n\n| Method | Use Case |\n|--------|----------|\n| **Environment variables** | Docker, Kubernetes, CI/CD |\n| **config.yaml** | Local development, bare metal |\n| **Admin Dashboard** | Visual configuration at `/admin/` |\n\nKey environment variables:\n\n```bash\nDATABASE_URL=postgresql://user:pass@host:5432/syntheticbrew\nADMIN_USER=admin\nADMIN_PASSWORD=changeme\n```\n\nLLM provider, model and API key are configured through the onboarding\nwizard on first launch (or later via Admin → Models). Engine does not\nread LLM credentials from env or config files.\n\n## Architecture\n\nSyntheticBrew follows Clean Architecture with strict layer separation. All Go code lives under `engine/`:\n\n```\nengine/\n  cmd/ce/              Community Edition entry point\n  internal/\n    domain/            Pure domain entities\n    usecase/           Business logic + consumer-side interfaces\n    service/           Task worker, scheduler, completion hooks\n    infrastructure/    DB, LLM, MCP, agents, tools\n    delivery/          HTTP handlers\n    app/               Application bootstrap\n  admin/               React/TypeScript admin dashboard\n  widget/              Embeddable chat widget\n  deploy/              Docker, Helm, systemd assets\n```\n\n## Deployment\n\n| Method | Guide |\n|--------|-------|\n| **Docker Compose** | See [Quick Start](#quick-start) above |\n| **Kubernetes** | Helm chart in [`engine/deploy/helm/`](engine/deploy/helm/) |\n| **Bare Metal** | Binary + systemd + PostgreSQL + Caddy/nginx |\n\n## Documentation\n\n- **Website:** https://syntheticbrew.ai\n- **Docs:** https://syntheticbrew.ai/docs/\n- **API Reference:** https://syntheticbrew.ai/docs/api/\n\n## Custom integrations\n\nDon't have the in-house expertise to build it yourself? **Synthetic AI Inc** designs, builds, and deploys custom AI integrations on SyntheticBrew — your data, your tools, your workflows, taken all the way into production. Whether your AI is internal-facing or customer-facing, we make it speak your business.\n\nGet in touch at [syntheticbrew.ai](https://syntheticbrew.ai) or [info@syntheticbrew.ai](mailto:info@syntheticbrew.ai).\n\n## Contributing\n\nWe welcome contributions! Please read [CONTRIBUTING.md](CONTRIBUTING.md) before submitting a PR.\n\n- [Code of Conduct](CODE_OF_CONDUCT.md)\n- [Security Policy](SECURITY.md)\n\n## License\n\nLicensed under [Business Source License 1.1](LICENSE). Contact [info@syntheticbrew.ai](mailto:info@syntheticbrew.ai) for alternative licensing.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsyntheticinc%2Fsyntheticbrew","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsyntheticinc%2Fsyntheticbrew","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsyntheticinc%2Fsyntheticbrew/lists"}