{"id":32693016,"url":"https://github.com/ownerofglory/raspi-agent","last_synced_at":"2026-05-16T06:39:14.876Z","repository":{"id":318554565,"uuid":"1071053687","full_name":"ownerofglory/raspi-agent","owner":"ownerofglory","description":"DIY on-device voice assistant for Raspberry Pi: wake word, speech-to-text, LLM reasoning, and text-to-speech streaming via Bluetooth audio","archived":false,"fork":false,"pushed_at":"2025-11-15T21:15:43.000Z","size":1018,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-11-15T23:21:58.543Z","etag":null,"topics":["agent","ai","diy","go","home-automation","openai","porcupine","portaudio","rag","raspberry-pi","self-hosted","streaming","voice-assistant"],"latest_commit_sha":null,"homepage":"","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ownerofglory.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":"2025-10-06T19:56:40.000Z","updated_at":"2025-11-15T21:15:47.000Z","dependencies_parsed_at":"2025-10-07T22:24:39.039Z","dependency_job_id":"be792947-1af2-45c0-b834-d10e3581e448","html_url":"https://github.com/ownerofglory/raspi-agent","commit_stats":null,"previous_names":["ownerofglory/raspi-agent"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ownerofglory/raspi-agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ownerofglory%2Fraspi-agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ownerofglory%2Fraspi-agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ownerofglory%2Fraspi-agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ownerofglory%2Fraspi-agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ownerofglory","download_url":"https://codeload.github.com/ownerofglory/raspi-agent/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ownerofglory%2Fraspi-agent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33092868,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-16T04:41:52.686Z","status":"ssl_error","status_checked_at":"2026-05-16T04:41:52.009Z","response_time":115,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["agent","ai","diy","go","home-automation","openai","porcupine","portaudio","rag","raspberry-pi","self-hosted","streaming","voice-assistant"],"created_at":"2025-11-01T16:02:39.989Z","updated_at":"2026-05-16T06:39:14.871Z","avatar_url":"https://github.com/ownerofglory.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Raspi agent (DIY voice assistance)\n**Raspi-Agent** is a modular streaming voice assistant for Raspberry Pi with built-in wake-word detection, streaming audio, and LLM back-end support (on-device or off-device)\n\n\n![](https://github.com/ownerofglory/raspi-agent/actions/workflows/build.yaml/badge.svg)\n\n[![Quality Gate Status](https://sonarcloud.io/api/project_badges/measure?project=ownerofglory_raspi-agent\u0026metric=alert_status)](https://sonarcloud.io/summary/new_code?id=ownerofglory_raspi-agent)\n\n### *Currently, in development ...*\n\n## Planned Features\n- [x] Wake word detection\n- [x] Streaming audio playback\n- [x] Natural conversation via OpenAI APIs\n- [x] Device registration and certificate enrollment\n- [ ] Device-to-backend communication over mTLS\n- [ ] RAG integration\n- [ ] Agent memory\n- [ ] Web dashboard\n\n\u003cimg src=\"./docs/assets/Raspi-agent.png\" width=\"480px\" /\u003e\n\n---\n\n##  Features\n\n- **Wake Word Detection** — powered by [Porcupine](https://picovoice.ai/platform/porcupine/)\n- **Streaming Audio Playback** — real-time PCM or MP3 output via PortAudio\n- **Natural Conversation** — integrates with OpenAI (STT, LLM, TTS)\n- **Dual Architecture** — choose between:\n    - **Onboard mode** — runs all AI calls directly from the Pi\n    - **Offboard mode** — sends recordings to a backend for processing\n\n\n## Architecture Overview\n\u003e Wake Word → Recorder → Voice Assistant → Player → User\n\nTwo orchestrator implementations:\n\n| Mode | Description | Example                         |\n|------|--------------|---------------------------------|\n| **Onboard** | Runs everything locally via OpenAI APIs (STT, LLM, TTS) | `cmd/raspi-agent-onboard-local`       |\n| **Offboard** | Streams recorded audio to a backend that processes it | `cmd/raspi-agent-onboard` |\n\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fownerofglory%2Fraspi-agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fownerofglory%2Fraspi-agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fownerofglory%2Fraspi-agent/lists"}