{"id":47019905,"url":"https://github.com/crypdick/pynchy","last_synced_at":"2026-03-11T22:20:15.687Z","repository":{"id":338900988,"uuid":"1155859679","full_name":"crypdick/pynchy","owner":"crypdick","description":"A modular alternative to Clawdbot / OpenClaw that runs in containers for security. Connects to WhatsApp, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK","archived":false,"fork":false,"pushed_at":"2026-02-24T21:30:15.000Z","size":5819,"stargazers_count":5,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-02-24T22:38:18.165Z","etag":null,"topics":["ai-agents","ai-assistant","claude-code","claude-skills","openclaw"],"latest_commit_sha":null,"homepage":"https://pynchy.ricardodecal.com/","language":"Python","has_issues":false,"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/crypdick.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/contributing.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","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":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-02-12T01:34:39.000Z","updated_at":"2026-02-24T21:30:19.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/crypdick/pynchy","commit_stats":null,"previous_names":["crypdick/pynchy"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/crypdick/pynchy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crypdick%2Fpynchy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crypdick%2Fpynchy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crypdick%2Fpynchy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crypdick%2Fpynchy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/crypdick","download_url":"https://codeload.github.com/crypdick/pynchy/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crypdick%2Fpynchy/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30404193,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-11T21:51:19.558Z","status":"ssl_error","status_checked_at":"2026-03-11T21:50:57.892Z","response_time":84,"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-agents","ai-assistant","claude-code","claude-skills","openclaw"],"created_at":"2026-03-11T22:20:15.092Z","updated_at":"2026-03-11T22:20:15.682Z","avatar_url":"https://github.com/crypdick.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/mr-pinchy.webp\" alt=\"Pynchy\" width=\"400\"\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cem\u003e🦞 Pynchy\u003c/em\u003e (pronounced \"Pinchy\") — A personal AI assistant like \u003ca href=\"https://github.com/openclaw/openclaw\"\u003eOpenClaw\u003c/a\u003e done right. Security first, modular, written in Python.\n\u003c/p\u003e\n\n\n## Why Pynchy?\n\nEveryone is writing their own AI assistant. Why write another one? The biggest reason is that I wanted something written in Python, because that's what I'm most comfortable with.\n\n### Comparison to Related Projects\n\n- [ZeroClaw](https://github.com/theonlyhennygod/zeroclaw) looks great actually, but I don't know how to write in Rust.\n- [Happy](https://github.com/slopus/happy) looks great, but ultimately is a remote terminal to Claude Code. I want to add my own security features. Also, I am not fluent in TypeScript.\n- [NanoClaw](https://github.com/qwibitai/nanoclaw) is a too minimalist.\n- [OpenClaw](https://github.com/openclaw/openclaw) is a massive pile of overcooked spaghetti code. Ain't no way I'm running that security nightmare on my machine.\n- [pi mono](https://github.com/badlogic/pi-mono) is a less crazy project, which actually OpenClaw built on top of. It doesn't have the security features that I want.\n\n## Features\n\n- Agents run in containers, providing process, filesystem, and network isolation.\n- Built-in plugins ship with the monorepo; third-party plugins are discoverable via Python entry points.\n- Uses [LiteLLM](https://docs.litellm.ai/docs/) as the LLM gateway, providing a bunch of features out of the box:\n  - Automatic load balancing across APIs, to soak up your various allowances from different providers.\n  - Access to [100+ LLM providers](https://docs.litellm.ai/docs/providers)\n  - Cost tracking and budget management.\n  - Rate limiting\n  - MCP gateway — centralized management of external MCP tool servers with per-workspace access control, on-demand Docker lifecycle, and config-driven setup.\n  - (see the [LiteLLM docs](https://docs.litellm.ai/docs/) for more details)\n- Customizable; [eight types of plugins](https://pynchy.ricardodecal.com/plugins/) are supported — agent cores, skills, channels, service handlers, container runtimes, workspaces, observers, and tunnels.\n- Persistent memory with BM25-ranked full-text search — agents save and recall facts across sessions.\n- Reoccurring tasks can be scheduled to run at a specific time or interval.\n- Policy groups to prevent [lethal trifecta prompt injection attacks](https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/).\n\n## Integrations\n\nBuilt-in plugins provide integrations with external services. All integrations are pluggable — see [plugin authoring](https://pynchy.ricardodecal.com/plugins/) to add your own.\n\n| Integration | What it does |\n|-------------|-------------|\n| **WhatsApp** | Messaging channel via linked device |\n| **Slack** | Messaging channel with browser-based token extraction |\n| **X (Twitter)** | Post, like, reply, retweet, and quote via browser automation |\n| **CalDAV** | Calendar access (Nextcloud, etc.) — list, create, delete events |\n| **Jupyter Notebooks** | Per-workspace notebook server with MCP tools |\n| **Google Drive** | File access via OAuth2 MCP server |\n\n## Getting Started\n\nSee the **[installation guide](https://pynchy.ricardodecal.com/install/)** to get started.\n\n## Documentation\n\nFull documentation at **[pynchy.ricardodecal.com](https://pynchy.ricardodecal.com/)**.\n\n| Section | What it covers |\n|---------|---------------|\n| [Usage](https://pynchy.ricardodecal.com/usage/) | Day-to-day operation, groups, scheduled tasks |\n| [Plugin authoring](https://pynchy.ricardodecal.com/plugins/) | Writing plugins: channels, skills, MCP servers |\n| [Architecture \u0026 Design](https://pynchy.ricardodecal.com/architecture/) | Container isolation, message routing, IPC, security |\n| [Contributing](https://pynchy.ricardodecal.com/contributing/contributing-code/) | How to contribute — plugins, fixes, docs, and more |\n\n## FAQ\n\n**What messaging channels are supported?**\nWhatsApp and Slack have first-party plugins. Channels are pluggable — write a [plugin](https://pynchy.ricardodecal.com/plugins/) to add new ones.\n\n**Why Apple Container instead of Docker?**\nOn macOS, Apple Container is lightweight and optimized for Apple silicon. Docker works too and is used as a fallback. On Linux, Docker is the only option.\n\n**Is this secure?**\nAgents run in containers, not behind application-level permission checks. They can only access explicitly mounted directories. See [the security model](https://pynchy.ricardodecal.com/architecture/security/) for details.\n\n**How do I debug issues?**\nAsk Pynchy. \"Why isn't the scheduler running?\" \"What's in the recent logs?\" That's the AI-native approach.\n\n### Credits\n\nHuge thanks to [NanoClaw](https://github.com/qwibitai/nanoclaw). This project started as a Python port of that project.\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcrypdick%2Fpynchy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcrypdick%2Fpynchy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcrypdick%2Fpynchy/lists"}