{"id":44828564,"url":"https://github.com/achetronic/magec","last_synced_at":"2026-02-28T19:05:17.670Z","repository":{"id":338822482,"uuid":"1136604284","full_name":"achetronic/magec","owner":"achetronic","description":"Multi-agent AI platform with voice and text control. Visual workflows, web interface, and chat integrations (Telegram, Discord, Slack). Long-term memory, any LLM backend, extensible via MCP tools.","archived":false,"fork":false,"pushed_at":"2026-02-20T02:53:39.000Z","size":3454,"stargazers_count":20,"open_issues_count":2,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2026-02-20T05:55:49.673Z","etag":null,"topics":["ai-assistant","ai-workflows","long-term-memory","magec","mcp-servers","session-memory","voice-control"],"latest_commit_sha":null,"homepage":"https://magec.dev","language":"HTML","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/achetronic.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"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":null}},"created_at":"2026-01-18T01:46:57.000Z","updated_at":"2026-02-20T02:51:05.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/achetronic/magec","commit_stats":null,"previous_names":["achetronic/magec"],"tags_count":16,"template":false,"template_full_name":null,"purl":"pkg:github/achetronic/magec","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/achetronic%2Fmagec","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/achetronic%2Fmagec/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/achetronic%2Fmagec/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/achetronic%2Fmagec/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/achetronic","download_url":"https://codeload.github.com/achetronic/magec/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/achetronic%2Fmagec/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29727736,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-22T20:09:16.275Z","status":"ssl_error","status_checked_at":"2026-02-22T20:09:13.750Z","response_time":110,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["ai-assistant","ai-workflows","long-term-memory","magec","mcp-servers","session-memory","voice-control"],"created_at":"2026-02-16T23:29:20.937Z","updated_at":"2026-02-22T21:27:38.359Z","avatar_url":"https://github.com/achetronic.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Magec\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/img/banner.png\" alt=\"Magec\" width=\"800\"\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eSelf-hosted multi-agent AI platform with voice, visual workflows, and tool integration.\u003c/strong\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://magec.dev\"\u003eWebsite\u003c/a\u003e ·\n  \u003ca href=\"https://magec.dev/docs/\"\u003eDocs\u003c/a\u003e ·\n  \u003ca href=\"#quick-start\"\u003eQuick Start\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\nDefine multiple AI agents, each with its own LLM, memory, and tools. Chain them into multi-step workflows. Access via voice, Telegram, webhooks, or cron. Manage it all from a visual admin panel.\n\nYour server, your data, your rules.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/img/architecture.svg\" alt=\"Architecture\" width=\"860\"\u003e\n\u003c/p\u003e\n\n## Quick Start\n\n### One-line install (fully local, no API keys)\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/achetronic/magec/master/scripts/install.sh | bash\n```\n\nDownloads a Docker Compose file with everything: LLM (Ollama), STT (Parakeet), TTS (Edge TTS), embeddings, Redis, PostgreSQL. Add `--gpu` for NVIDIA acceleration.\n\n### Docker with OpenAI (minimal)\n\n```bash\ndocker run -d --name magec \\\n  -p 8080:8080 -p 8081:8081 \\\n  -v $(pwd)/config.yaml:/app/config.yaml \\\n  -v magec_data:/app/data \\\n  ghcr.io/achetronic/magec:latest\n```\n\nCreate backends, agents, and clients from the Admin UI. See the [Docker Quick Start](https://achetronic.github.io/magec/docs/install-docker/) guide.\n\n### Binary\n\nDownload from [Releases](https://github.com/achetronic/magec/releases), extract, and run:\n\n```bash\n./magec --config config.yaml\n```\n\nIdeal for local MCP tools (filesystem, git, shell). See the [Binary Installation](https://achetronic.github.io/magec/docs/install-binary/) guide.\n\n---\n\n**Admin UI** → http://localhost:8081 · **Voice UI** → http://localhost:8080\n\n## Highlights\n\n- **Multi-agent** — Per-agent LLM, memory, voice, and tools. Hot-reload from the Admin UI.\n- **Agentic Flows** — Visual drag-and-drop editor. Sequential, parallel, loop, nested.\n- **Any backend** — OpenAI, Anthropic, Gemini, Ollama, or any OpenAI-compatible API.\n- **MCP tools** — Home Assistant, GitHub, databases, and hundreds more via Model Context Protocol.\n- **Memory** — Session (Redis) + long-term semantic (PostgreSQL/pgvector).\n- **Voice** — Wake word, VAD, STT, TTS. All server-side via ONNX Runtime. Privacy-first.\n- **Clients** — Voice UI (PWA), Admin UI, Telegram, webhooks, cron, REST API, Slack.\n\n## Screenshots\n\nSee all screenshots in the [documentation](https://achetronic.github.io/magec/docs/screenshots/).\n\n## Roadmap\n\n- [x] Multi-agent system with per-agent LLM, memory, and tools\n- [x] Visual flow editor (sequential, parallel, loop, nested)\n- [x] MCP tool integration (HTTP + stdio transports)\n- [x] Voice UI with wake word detection and VAD\n- [x] Telegram client with voice support\n- [x] Long-term semantic memory (pgvector)\n- [x] Session memory (Redis)\n- [x] Webhook and cron clients\n- [x] Admin UI with hot-reload\n- [x] Secrets management (encrypted storage for API keys and sensitive credentials)\n- [x] Slack client\n- [x] Context window management — automatic summarization when approaching token limits (experimental)\n- [ ] Discord client\n- [ ] Expose agents and flows with A2a (Agent-to-agent) protocol\n\n## Documentation\n\nFull docs at **[magec.dev/docs](https://magec.dev/docs/)** — installation, configuration, agents, flows, backends, memory, MCP tools, clients, voice system, and API reference.\n\n## Development\n\n### Requirements\n\n- Go 1.25+\n- Node.js 22+ (for UI builds)\n- Docker (for infrastructure services)\n\n### Make commands\n\n| Command              | Description                                               |\n| -------------------- | --------------------------------------------------------- |\n| `make build`         | Build frontend UIs + embed models + compile server binary |\n| `make dev`           | Build all and start server                                |\n| `make dev-admin`     | Start Admin UI dev server (Vite, hot-reload)              |\n| `make dev-voice`     | Start Voice UI dev server (Vite, hot-reload)              |\n| `make swagger`       | Regenerate Swagger docs                                   |\n| `make infra`         | Start PostgreSQL + Redis                                  |\n| `make ollama`        | Start Ollama with qwen3:8b + nomic-embed-text             |\n| `make docker-build`  | Build Docker image (current arch)                         |\n| `make docker-buildx` | Build multi-arch image (amd64 + arm64)                    |\n| `make clean`         | Remove build artifacts                                    |\n\n### Key dependencies\n\n| Dependency                                                                    | Purpose                          |\n| ----------------------------------------------------------------------------- | -------------------------------- |\n| [google.golang.org/adk](https://pkg.go.dev/google.golang.org/adk)             | Google Agent Development Kit     |\n| [modelcontextprotocol/go-sdk](https://github.com/modelcontextprotocol/go-sdk) | MCP client                       |\n| [yalue/onnxruntime_go](https://github.com/yalue/onnxruntime_go)               | ONNX Runtime for wake word / VAD |\n| [mymmrac/telego](https://github.com/mymmrac/telego)                           | Telegram bot                     |\n| [achetronic/adk-utils-go](https://github.com/achetronic/adk-utils-go)         | ADK providers, session, memory   |\n\n## Special Mentions\n\n| Who                                      | What                                                                                                                                                                                                                                                                                                                                             |\n| ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| [@travisvn](https://github.com/travisvn) | Built the ARM64 Docker image for [OpenAI Edge TTS](https://github.com/travisvn/openai-edge-tts) in record time. This is the local TTS service we recommend — it exposes an OpenAI-compatible API (`/v1/audio/speech`) that uses Microsoft Edge's free neural voices under the hood, so Magec can use it as a drop-in replacement for OpenAI TTS. |\n\n## Contributors\n\n\u003ca href=\"https://github.com/achetronic/magec/graphs/contributors\"\u003e\n  \u003cimg src=\"https://contrib.rocks/image?repo=achetronic/magec\" /\u003e\n\u003c/a\u003e\n\n## License\n\n[Apache 2.0](LICENSE) — Alby Hernández\n\n---\n\n\u003cp align=\"center\"\u003e\n  If you find Magec useful, please ⭐ star this repo — it helps a lot.\n\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fachetronic%2Fmagec","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fachetronic%2Fmagec","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fachetronic%2Fmagec/lists"}