{"id":48481744,"url":"https://github.com/lestherll/personal_assistant","last_synced_at":"2026-04-07T08:32:45.882Z","repository":{"id":344629701,"uuid":"1179275467","full_name":"lestherll/personal_assistant","owner":"lestherll","description":"AI personal assistant with workspace-based multi-agent routing, pluggable LLM providers, tool support","archived":false,"fork":false,"pushed_at":"2026-03-24T15:06:04.000Z","size":1093,"stargazers_count":0,"open_issues_count":2,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-25T19:43:05.682Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/lestherll.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2026-03-11T21:42:03.000Z","updated_at":"2026-03-24T15:06:49.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/lestherll/personal_assistant","commit_stats":null,"previous_names":["lestherll/personal_assistant"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/lestherll/personal_assistant","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lestherll%2Fpersonal_assistant","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lestherll%2Fpersonal_assistant/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lestherll%2Fpersonal_assistant/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lestherll%2Fpersonal_assistant/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lestherll","download_url":"https://codeload.github.com/lestherll/personal_assistant/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lestherll%2Fpersonal_assistant/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31506562,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-07T03:10:19.677Z","status":"ssl_error","status_checked_at":"2026-04-07T03:10:13.982Z","response_time":105,"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":[],"created_at":"2026-04-07T08:32:45.788Z","updated_at":"2026-04-07T08:32:45.860Z","avatar_url":"https://github.com/lestherll.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Personal Assistant\n\n[![Tests](https://github.com/lestherll/personal_assistant/actions/workflows/tests.yml/badge.svg)](https://github.com/lestherll/personal_assistant/actions/workflows/tests.yml)\n[![Security](https://github.com/lestherll/personal_assistant/actions/workflows/security.yml/badge.svg)](https://github.com/lestherll/personal_assistant/actions/workflows/security.yml)\n\nA modular AI personal assistant built on [LangChain](https://www.langchain.com/) and [LangGraph](https://www.langchain.com/langgraph). Configurable agents specialise in specific tasks, are grouped into workspaces, and are backed by a pluggable provider registry — making it easy to swap models, extend with new tools, and expose everything over an HTTP API.\n\n---\n\n## Features\n\n- **Multiple AI providers** — Anthropic (Claude) and Ollama (local models) out of the box\n- **Configurable agents** — each agent has its own system prompt, provider, model, and tool allowlist\n- **Workspaces** — group agents and tools together; the workspace supervisor automatically routes each message to the best agent\n- **Flexible chat** — target the supervisor for automatic routing, or name a specific agent to bypass it; override the provider and model per request without changing the agent's saved configuration\n- **Streaming responses** — SSE streaming for both agent-direct and workspace-level chat\n- **Persistent conversation history** — agents remember context across turns; resumable via `conversation_id`\n- **Optional PostgreSQL persistence** — conversation and message history backed by SQLAlchemy + asyncpg; fully in-memory without a database configured\n- **REST API** — FastAPI with full OpenAPI docs, typed request/response schemas, and structured error responses\n- **Extensible tools** — add new tools by subclassing `AssistantTool`; tools auto-register with all compatible agents in a workspace\n\n---\n\n## Requirements\n\n- Python 3.13+\n- [uv](https://docs.astral.sh/uv/) for package management\n- [Ollama](https://ollama.com) for local models (optional)\n- An Anthropic API key for Claude models (optional)\n\n---\n\n## Quickstart\n\n```bash\n# Clone and install dependencies\ngit clone git@github.com:lestherll/personal_assistant.git\ncd personal_assistant\nuv sync\n\n# Set up environment\ncp .env.example .env\n# Edit .env — add ANTHROPIC_API_KEY and/or configure Ollama\n\n# Start the REST API\nuv run fastapi dev api/main.py\n\n# Or start the interactive REPL\nuv run python main.py\n```\n\n---\n\n## API Overview\n\nThe REST API is documented at `http://localhost:8000/docs` when running in dev mode.\n\nKey endpoints:\n\n| Method | Path | Description |\n|---|---|---|\n| `POST` | `/auth/register` | Register a new user |\n| `POST` | `/auth/login` | Log in and get tokens |\n| `GET` | `/providers/` | List registered AI providers |\n| `GET` | `/providers/{name}/models` | List models for a provider |\n| `POST` | `/workspaces/` | Create a workspace |\n| `GET` | `/workspaces/` | List workspaces |\n| `POST` | `/workspaces/{name}/chat` | Workspace chat (supervisor or agent-direct) |\n| `POST` | `/workspaces/{name}/chat/stream` | Streaming workspace chat |\n| `POST` | `/workspaces/{name}/agents/` | Create an agent |\n| `POST` | `/workspaces/{name}/agents/{agent}/chat` | Direct agent chat |\n| `POST` | `/workspaces/{name}/agents/{agent}/chat/stream` | Streaming agent chat |\n\nAll endpoints except `/auth/**` and `/health` require `Authorization: Bearer \u003ctoken\u003e`. Set `AUTH_DISABLED=true` in `.env` to skip auth in development.\n\n---\n\n## Environment\n\nCopy `.env.example` to `.env` and configure:\n\n```env\nANTHROPIC_API_KEY=sk-ant-...           # Claude models\nRAPIDAPI_KEY=...                       # optional — enables job search tool\nDATABASE_URL=postgresql+asyncpg://...  # optional — enables conversation persistence\nSECRET_KEY=\u003crandom-32-bytes\u003e           # generate: openssl rand -hex 32\nAUTH_DISABLED=false                    # set true to skip auth (dev only)\n```\n\nOllama runs locally at `http://localhost:11434` by default. Pull a model before using it:\n\n```bash\nollama pull qwen2.5:14b\n```\n\n---\n\n## Development\n\n```bash\nuv run pytest              # unit + functional tests\nuv run ruff check .        # lint\nuv run ruff format .       # format\nuv run mypy . --exclude tests  # type check\nuv run alembic upgrade head    # apply DB migrations\n```\n\nSee [CLAUDE.md](CLAUDE.md) for the full developer guide and [ARCHITECTURE.md](ARCHITECTURE.md) for the system design.\n\n---\n\n## Roadmap\n\n- [ ] More providers — OpenAI, Groq, Google Gemini\n- [ ] Web UI\n- [ ] Supervisor streaming (LangGraph graph-level)\n- [ ] Redis-backed conversation cache\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flestherll%2Fpersonal_assistant","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flestherll%2Fpersonal_assistant","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flestherll%2Fpersonal_assistant/lists"}