[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-929":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":15,"stars30d":15,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":16,"rankGlobal":9,"rankLanguage":9,"license":17,"archived":18,"fork":18,"defaultBranch":19,"hasWiki":20,"hasPages":18,"topics":21,"createdAt":9,"pushedAt":9,"updatedAt":22,"readmeContent":23,"aiSummary":24,"trendingCount":15,"starSnapshotCount":15,"syncStatus":25,"lastSyncTime":26,"discoverSource":27},929,"pi-mono","badlogic\u002Fpi-mono","badlogic","AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods",null,"TypeScript",45450,5352,170,12,0,45,"MIT License",false,"main",true,[],"2026-06-12 02:00:20","\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fpi.dev\">\n    \u003Cpicture>\n      \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fpi.dev\u002Flogo.svg\">\n      \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fhuggingface.co\u002Fbuckets\u002Fjulien-c\u002Fmy-training-bucket\u002Fresolve\u002Fpi-logo-dark.svg\">\n      \u003Cimg alt=\"pi logo\" src=\"https:\u002F\u002Fpi.dev\u002Flogo.svg\" width=\"128\">\n    \u003C\u002Fpicture>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fdiscord.com\u002Finvite\u002F3cU7Bz4UPx\">\u003Cimg alt=\"Discord\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdiscord-community-5865F2?style=flat-square&logo=discord&logoColor=white\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fbadlogic\u002Fpi-mono\u002Factions\u002Fworkflows\u002Fci.yml\">\u003Cimg alt=\"Build status\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Fbadlogic\u002Fpi-mono\u002Fci.yml?style=flat-square&branch=main\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fpi.dev\">pi.dev\u003C\u002Fa> domain graciously donated by\n  \u003Cbr \u002F>\u003Cbr \u002F>\n  \u003Ca href=\"https:\u002F\u002Fexe.dev\">\u003Cimg src=\"packages\u002Fcoding-agent\u002Fdocs\u002Fimages\u002Fexy.png\" alt=\"Exy mascot\" width=\"48\" \u002F>\u003Cbr \u002F>exe.dev\u003C\u002Fa>\n\u003C\u002Fp>\n\n> New issues and PRs from new contributors are auto-closed by default. Maintainers review auto-closed issues daily. See [CONTRIBUTING.md](CONTRIBUTING.md).\n\n---\n\n# Pi Monorepo\n\n> **Looking for the pi coding agent?** See **[packages\u002Fcoding-agent](packages\u002Fcoding-agent)** for installation and usage.\n\nTools for building AI agents.\n\n## Share your OSS coding agent sessions\n\nIf you use pi or other coding agents for open source work, please share your sessions.\n\nPublic OSS session data helps improve coding agents with real-world tasks, tool use, failures, and fixes instead of toy benchmarks.\n\nFor the full explanation, see [this post on X](https:\u002F\u002Fx.com\u002Fbadlogicgames\u002Fstatus\u002F2037811643774652911).\n\nTo publish sessions, use [`badlogic\u002Fpi-share-hf`](https:\u002F\u002Fgithub.com\u002Fbadlogic\u002Fpi-share-hf). Read its README.md for setup instructions. All you need is a Hugging Face account, the Hugging Face CLI, and `pi-share-hf`.\n\nYou can also watch [this video](https:\u002F\u002Fx.com\u002Fbadlogicgames\u002Fstatus\u002F2041151967695634619), where I show how I publish my `pi-mono` sessions.\n\nI regularly publish my own `pi-mono` work sessions here:\n\n- [badlogicgames\u002Fpi-mono on Hugging Face](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fbadlogicgames\u002Fpi-mono)\n\n## Packages\n\n| Package | Description |\n|---------|-------------|\n| **[@mariozechner\u002Fpi-ai](packages\u002Fai)** | Unified multi-provider LLM API (OpenAI, Anthropic, Google, etc.) |\n| **[@mariozechner\u002Fpi-agent-core](packages\u002Fagent)** | Agent runtime with tool calling and state management |\n| **[@mariozechner\u002Fpi-coding-agent](packages\u002Fcoding-agent)** | Interactive coding agent CLI |\n| **[@mariozechner\u002Fpi-tui](packages\u002Ftui)** | Terminal UI library with differential rendering |\n| **[@mariozechner\u002Fpi-web-ui](packages\u002Fweb-ui)** | Web components for AI chat interfaces |\n\n## Chat bot workflows\n\nFor Slack\u002Fchat automation, see [earendil-works\u002Fpi-chat](https:\u002F\u002Fgithub.com\u002Fearendil-works\u002Fpi-chat).\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for contribution guidelines and [AGENTS.md](AGENTS.md) for project-specific rules (for both humans and agents).\n\n## Development\n\n```bash\nnpm install          # Install all dependencies\nnpm run build        # Build all packages\nnpm run check        # Lint, format, and type check\n.\u002Ftest.sh            # Run tests (skips LLM-dependent tests without API keys)\n.\u002Fpi-test.sh         # Run pi from sources (can be run from any directory)\n```\n\n> **Note:** `npm run check` requires `npm run build` to be run first. The web-ui package uses `tsc` which needs compiled `.d.ts` files from dependencies.\n\n## License\n\nMIT\n","Pi Monorepo 是一个用于构建AI代理的工具包，它提供了一个统一的大规模语言模型API、交互式编码代理CLI以及终端和网页用户界面库。项目核心功能包括支持多提供商的LLM API（如OpenAI, Anthropic, Google等）、具有工具调用和状态管理能力的代理运行时环境，以及为开发者提供的TUI和Web UI组件。此外，还集成了Slack机器人功能及虚拟LLM容器。该项目适合需要创建定制化AI助手或自动化聊天机器人的场景使用，特别是在开源软件开发过程中分享和改进编码会话方面有着独特的优势。",2,"2026-05-06 17:29:00","top_all"]