[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-83425":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":16,"stars7d":17,"stars30d":17,"stars90d":15,"forks30d":15,"starsTrendScore":18,"compositeScore":19,"rankGlobal":9,"rankLanguage":9,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":23,"hasPages":21,"topics":24,"createdAt":9,"pushedAt":9,"updatedAt":25,"readmeContent":26,"aiSummary":9,"trendingCount":15,"starSnapshotCount":15,"syncStatus":14,"lastSyncTime":27,"discoverSource":28},83425,"Amis","cPilot-GUI\u002FAmis","cPilot-GUI","🖥️ Local AI platform & Edge inference infrastructure. Desktop Agent Station and Token Hub built with Electron, React, and TypeScript.",null,"TypeScript",96,3,51,2,0,6,37,29,76.01,"GNU Affero General Public License v3.0",false,"main",true,[],"2026-06-12 04:01:41","# Amis\n\nLanguage: English | [中文](README.zh-CN.md)\n\nLocal AI platform and edge inference infrastructure for personal devices.\n\nAmis is One-token's desktop product for running local models, using agents, managing local\u002Fcloud AI routes, and packaging local AI workflows into a product experience. This repository contains the Electron desktop app, local runtime integration code, prompt-routing packages, release tooling, and product\u002Fengineering documentation.\n\n[Product](#what-is-amis) · [Architecture](#architecture) · [Development](#development) · [Release](#release-and-packaging) · [Docs](#documentation)\n\n## What Is Amis?\n\nAmis is not just another local model runner, and it is not just another chatbot.\n\nIt is designed as an Agent Station and Token Hub:\n\n- Model Hub: discover, download, deploy, and manage local models.\n- Agent Hub: connect local and cloud agents such as OpenClaw and Hermes.\n- Prompt Router: decide whether a request should stay on edge, use cloud, or use edge with fallback.\n- Runtime Metrics: keep local model runtime data in the desktop app instead of scattering it across services.\n- Desktop UX: make local AI feel like an app people can use daily, not a terminal setup.\n\nThe product goal is simple:\n\n> Make local AI usable, visible, and controllable on the device people already own.\n\n## Product Direction\n\nAmis v1.1.5 is shaped around three product themes from the product overview and PRD:\n\n1. Conversation experience upgrade\n   - assistant\u002Ftopic organization;\n   - richer chat input controls;\n   - file attachments and long-content handling;\n   - better code and streaming output handling.\n\n2. Local inference visibility\n   - Model Hub deployment state;\n   - runtime metrics and token\u002Fperformance tracking;\n   - clearer model download and deployment flows;\n   - hardware-aware local model operation.\n\n3. Developer and team access\n   - OpenAI-compatible local API direction;\n   - SK Code \u002F LAN authorization as the Pro workflow direction;\n   - prompt-router packages for edge\u002Fcloud route decisions;\n   - CI and packaging paths for real runtime validation.\n\nSome items are product direction rather than fully public interfaces. Public claims should be updated only after the release build, docs, and tests verify the path end to end.\n\n## Current Repository Status\n\n- Repository: `cPilot-GUI\u002FAmis-test`\n- Visibility: private\n- App version: `1.1.5`\n- App ID: `net.cpilot.app`\n- Product name: `Amis`\n- Current platform support: macOS and Linux\n- Windows: coming soon\n- Frontend: React 18 + TypeScript + TailwindCSS\n- Desktop runtime: Electron + electron-vite\n- Local data: SQLite through native desktop dependencies\n- Routing packages: `uncommon-route-ts`, `@qianyichen\u002Fsensitive-router`, `router-orchestrator`\n\nThe old Flask\u002FPython web-app README has been replaced because the current repository is an Electron desktop app and no longer contains the previous `auth_api.py`, `cPilot_local_server.py`, or `wechat_integration.py` files.\n\n## Architecture\n\n```mermaid\nflowchart TB\n    user[\"User\"]\n    app[\"Amis Electron App\"]\n    renderer[\"React Renderer\"]\n    main[\"Electron Main\"]\n    router[\"Prompt Router Packages\"]\n    runtime[\"Local Runtime \u002F OpenClaw \u002F Hermes\"]\n    models[\"Model Hub and Downloads\"]\n    metrics[\"Runtime Metrics Store\"]\n    cloud[\"Cloud Providers\"]\n\n    user --> app\n    app --> renderer\n    renderer --> main\n    main --> router\n    main --> runtime\n    main --> models\n    main --> metrics\n    router --> cloud\n    router --> runtime\n```\n\nKey areas:\n\n- `src\u002Fmain`: Electron main process, runtime lifecycle, credentials, prompt routing, local metrics, gateway integration.\n- `src\u002Fpreload`: safe renderer-to-main bridge.\n- `src\u002Frenderer\u002Fsrc`: React UI, pages, services, and app state.\n- `packages\u002Fprompt-router`: host-agnostic route decision packages.\n- `resources\u002Fmodel-download`: bundled model-download worker resources.\n- `docs`: product notes, release records, CI runbooks, runtime migration docs, and governance.\n- `openspec`: structured proposals and specs for product\u002Fengineering changes.\n\n## Development\n\n### Requirements\n\n- Node.js `25.9.0` as specified by `.nvmrc`\n- npm\n- macOS or Linux for current supported development and runtime paths\n\n```bash\nnvm use\nnpm install\n```\n\n`npm install` runs native rebuild and prompt-router build steps through `postinstall`.\n\n### Environment\n\nStart from the example config:\n\n```bash\ncp config.env.example .env\n```\n\nImportant values:\n\n- `VITE_CPILOT_API_URL`\n- `VITE_QWEN_API_URL`\n- `VITE_QWEN_API_KEY`\n- `VITE_DEBUG`\n- `VITE_FRONTEND_PORT`\n\nDo not commit real API keys, auth tokens, model credentials, or local runtime secrets.\n\n### Run\n\n```bash\nnpm run dev\n```\n\nRenderer-only development:\n\n```bash\nnpm run dev:web\n```\n\n### Checks\n\n```bash\nnpm run typecheck\nnpm run lint\nnpm run build\n```\n\n## Release And Packaging\n\nCurrent supported release targets are macOS and Linux. Windows is coming soon and should not be described as a currently supported public release target.\n\nmacOS packaging commands:\n\n```bash\nnpm run pack:mac:dir\nnpm run pack:mac:dmg\nnpm run pack:mac:zip\nnpm run pack:mac:release\n```\n\nUnsigned local macOS package:\n\n```bash\nCPILOT_SKIP_NOTARIZE=1 npm run pack:mac:dmg:unsigned\n```\n\nLocal unsigned builds are for developer or internal validation only. After packaging, inspect the bundled runtime and then run the packaged-app smoke helper:\n\n```bash\nnpm run inspect:packaged:mac\nnpm run test:packaged:mac -- --no-open --no-tail\n```\n\nIf macOS Gatekeeper blocks a locally built unsigned app, use one of these explicit local install authorization paths only after you trust the checkout and build output:\n\n```bash\nxattr -dr com.apple.quarantine dist\u002Fmac-arm64\u002FAmis.app\nspctl --assess --type execute --verbose dist\u002Fmac-arm64\u002FAmis.app || true\nopen dist\u002Fmac-arm64\u002FAmis.app\n```\n\nAlternatively open **System Settings → Privacy & Security** and choose **Open Anyway** for the blocked Amis app. Public release builds should use the signed\u002Fnotarized `npm run pack:mac:release` path instead of the unsigned local flow.\n\nThe repository currently contains a Windows packaging script, but Windows support is not part of the current public support matrix:\n\n```bash\nnpm run pack:win\n```\n\nRelease records should be added under `docs\u002Freleases\u002F` before the README links to them. This checkout currently uses the documentation index below as the source of truth for available docs.\n\n## Development and Documentation Workflow \u002F 开发与文档工作流\n\nThis README is the public project entry point. Repo-local agent\u002Fdeveloper rules live in [AGENTS.md](AGENTS.md), with compact implementation details in [HARNESS.md](HARNESS.md). Keep both short so future agents can load stable guidance with low prompt overhead.\n\nEnglish workflow:\n\n- Start from `AGENTS.md`, then `HARNESS.md` for code\u002Ftest work, then `docs\u002FREADME.md` for documentation navigation.\n- Use the architecture map and runtime flows as current-state evidence, not refactor authorization.\n- Use ADR for architecture decisions, SRS for requirements and verification methods, and SDD\u002Fviews for implementation design viewpoints.\n- Use Mermaid only with the GitHub\u002FObsidian-safe rules in `docs\u002Fguides\u002Fdocumentation-standards.md`.\n- Keep published docs bilingual and verify links, language switches, Mermaid safety, whitespace, and structure checks before handoff.\n\n中文工作流：\n\n- 先读 `AGENTS.md`；涉及代码\u002F测试时再读 `HARNESS.md`；查文档入口时读 `docs\u002FREADME.md`。\n- Architecture map 和 runtime flows 是现状证据，不是重构授权。\n- 架构决策写 ADR；需求和验证方法写 SRS；实现前设计视图写 SDD\u002Fviews。\n- Mermaid 必须遵守 `docs\u002Fguides\u002Fdocumentation-standards.md` 中的 GitHub\u002FObsidian 兼容规则。\n- 公开文档保持中英文同步；交付前验证 links、language switches、Mermaid safety、whitespace 和 structure checks。\n\n## Documentation\n\nEnglish:\n\n- [Project docs overview](docs\u002FREADME.md)\n- [Architecture map](docs\u002Farchitecture\u002Foverview.md)\n- [Runtime flows](docs\u002Farchitecture\u002Fruntime-flows.md)\n- [Developer guide](docs\u002Fguides\u002Fdeveloper-guide.md)\n- [Future refactor roadmap](docs\u002Fguides\u002Frefactor-roadmap.md)\n- [Documentation standards](docs\u002Fguides\u002Fdocumentation-standards.md)\n- [ADR-0001: Adopt documentation standards](docs\u002Fdecisions\u002FADR-0001-adopt-documentation-standards.md)\n- [Documentation standards SRS](docs\u002Frequirements\u002Fdocumentation-standards-srs.md)\n- [Documentation standards SDD](docs\u002Fdesign\u002Fdocumentation-standards-sdd.md)\n\n中文：\n\n- [项目文档总览](docs\u002Fzh-CN\u002FREADME.md)\n- [架构地图](docs\u002Fzh-CN\u002Farchitecture\u002Foverview.md)\n- [运行时流程](docs\u002Fzh-CN\u002Farchitecture\u002Fruntime-flows.md)\n- [开发者指南](docs\u002Fzh-CN\u002Fguides\u002Fdeveloper-guide.md)\n- [未来重构路线图](docs\u002Fzh-CN\u002Fguides\u002Frefactor-roadmap.md)\n- [文档标准与规范集成说明](docs\u002Fzh-CN\u002Fguides\u002Fdocumentation-standards.md)\n- [ADR-0001：采用文档标准](docs\u002Fzh-CN\u002Fdecisions\u002FADR-0001-adopt-documentation-standards.md)\n- [文档标准 SRS](docs\u002Fzh-CN\u002Frequirements\u002Fdocumentation-standards-srs.md)\n- [文档标准 SDD](docs\u002Fzh-CN\u002Fdesign\u002Fdocumentation-standards-sdd.md)\n\nOpenSpec proposals:\n\n- [Model download runtime hardening proposal](openspec\u002Fchanges\u002Fharden-model-download-runtime\u002Fproposal.md)\n- [GPU-only local runtime profile proposal](openspec\u002Fchanges\u002Fadd-gpu-only-local-runtime-profile\u002Fproposal.md)\n\n## Open Source Boundary\n\nThe intended open-source story is layered:\n\n- Open: product entry points, desktop app surfaces, docs, examples, route contracts, plugin\u002Fspec directions, integration guidance, compatibility notes, and reproducible release records.\n- Protected: proprietary inference optimizations, commercial authorization modules, partner-specific runtime internals, and unreleased engine details.\n\nWhen writing public docs, avoid unsupported performance claims. If a benchmark is mentioned, include the model, hardware, runtime version, prompt\u002Foutput shape, and reproduction method.\n\n## About One-token\n\nOne-token is an edge intelligence infrastructure company for the AI and Agent era. We focus on edge inference engines, local intelligence platforms, and integrated software-hardware capabilities.\n\nContact: [contact@cpilot.net](mailto:contact@cpilot.net)\n","2026-06-11 04:11:09","CREATED_QUERY"]