[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-77278":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":14,"stars7d":16,"stars30d":17,"stars90d":15,"forks30d":15,"starsTrendScore":13,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":31,"readmeContent":32,"aiSummary":33,"trendingCount":15,"starSnapshotCount":15,"syncStatus":34,"lastSyncTime":35,"discoverSource":36},77278,"platform","agynio\u002Fplatform","agynio","Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops to company infrastructure with the controls enterprises need.","https:\u002F\u002Fagyn.io",null,"TypeScript",191,3,1,0,5,55,1.81,"GNU Affero General Public License v3.0",false,"main",true,[24,25,26,27,28,29,30],"agentic-ai","agents","ai-agents","ai-platform","governance","open-source","self-hosted","2026-06-12 02:03:42","# Agyn\n\n> Ship AI agents to your company. Safely.\n\n[![License: AGPL v3](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-AGPL%20v3-blue)](https:\u002F\u002Fwww.gnu.org\u002Flicenses\u002Fagpl-3.0)\n[![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fagynio\u002Fplatform?style=social)](https:\u002F\u002Fgithub.com\u002Fagynio\u002Fplatform\u002Fstargazers)\n[![Discord](https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1474017426898157618?label=Discord&logo=discord&logoColor=white&color=5865F2)](https:\u002F\u002Fdiscord.com\u002Finvite\u002FeQKYwnNqRX)\n\n![Agyn Tour](agyn-tour.webp)\n\nYou built the agent. Now how do you let the rest of the company use it — without exposing secrets, blowing budgets, or losing control? Agyn is an open-source, Kubernetes-native platform that moves agents from laptops to company infrastructure with the controls enterprises need.\n\n## Why Agyn\n\n| Problem | Agyn |\n|---------|------|\n| Agents run on individual laptops | Centralized deployment on your infrastructure |\n| Secrets passed directly to models | Secrets isolated, never exposed to the model |\n| No budget visibility or limits | Spend caps at any level — per agent, per team, per org |\n| No access control | RBAC, SSO, audit logs |\n| Locked to one vendor | Agent-agnostic, model-agnostic |\n| Can't scale | Horizontal scaling, auto-termination on idle |\n\n## Get running in 15 minutes\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fagynio\u002Fbootstrap.git\ncd bootstrap\n.\u002Fapply.sh\n```\n\nOpen the console. Create an org. Deploy your first agent.\n\nWant a ready-made fleet to play with? Apply [`agynio\u002Fdemo-agent`](https:\u002F\u002Fgithub.com\u002Fagynio\u002Fdemo-agent) — a Terraform config that provisions a support, marketing, and data-engineer agent in one command.\n\nFor production installs, see [Self-host install](.\u002Fdocs\u002Fself-host-install\u002FREADME.md).\n\n## Define agents as code\n\nStop clicking. Version your agent infrastructure.\n\n```hcl\nresource \"agyn_agent\" \"support\" {\n  organization_id = agyn_organization.acme.id\n\n  name       = \"Support\"\n  nickname   = \"support\"\n  model      = agyn_llm_model.gpt_4o.name\n  image      = \"ghcr.io\u002Fagynio\u002Fagent-runtime:v1.0.0\"\n  init_image = \"ghcr.io\u002Fagynio\u002Fagent-init-codex:v1.0.0\"\n\n  idle_timeout = \"5m\"\n  availability = \"internal\"\n}\n\nresource \"agyn_agent_mcp\" \"zendesk\" {\n  agent_id = agyn_agent.support.id\n  name     = \"zendesk\"\n  image    = \"ghcr.io\u002Facme\u002Fzendesk-mcp:latest\"\n\n  envs = [\n    {\n      name      = \"ZENDESK_TOKEN\"\n      secret_id = agyn_secret.zendesk_token.id\n    },\n  ]\n}\n```\n\n```bash\nterraform init && terraform apply\n```\n\nSee the [Terraform provider](.\u002Fdocs\u002Fbuild-extend\u002Fterraform-provider.md) reference for every resource.\n\n## How it works\n\nEach agent is a first-class citizen:\n\n- **Isolated sandbox** — own container, filesystem, env vars, secrets\n- **MCPs in separate containers** — full process isolation per tool\n- **Observability built in** — token usage, compute, activity logs\n- **Auto-scaling** — agents spin up on demand, terminate on idle\n\nFull architecture: [docs\u002Foperate\u002Farchitecture.md](.\u002Fdocs\u002Foperate\u002Farchitecture.md).\n\n## Video walkthroughs\n\n| Video | What it shows |\n|---|---|\n| \u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=v97sy17_w3A\">\u003Cimg src=\"https:\u002F\u002Fimg.youtube.com\u002Fvi\u002Fv97sy17_w3A\u002Fmqdefault.jpg\" width=\"280\" alt=\"Agyn demo\">\u003C\u002Fa> | **Agyn in 5 minutes** — From clean cluster to a working agent answering a chat message. End-to-end tour. |\n| *Coming soon* | **Deploying agents with Terraform** — Define an agent fleet as code, apply it, talk to them. |\n| *Coming soon* | **Inspecting a run with Tracing** — Every LLM call, every tool execution, every context decision. |\n\n## Documentation\n\nFull docs live in [`docs\u002F`](.\u002Fdocs\u002FREADME.md):\n\n- [Introduction](.\u002Fdocs\u002Fintroduction\u002FREADME.md) — what Agyn is, concepts, architecture at a glance.\n- [Self-host install](.\u002Fdocs\u002Fself-host-install\u002FREADME.md) — bootstrap, production install, upgrades.\n- [Administer](.\u002Fdocs\u002Fadminister\u002FREADME.md) — Console + Terraform for orgs, agents, models, secrets, runners, apps.\n- [Use](.\u002Fdocs\u002Fuse\u002FREADME.md) — chat, files, tracing, usage, port exposure.\n- [Build & extend](.\u002Fdocs\u002Fbuild-extend\u002FREADME.md) — Gateway API, MCP servers, agent CLIs, apps.\n- [Operate](.\u002Fdocs\u002Foperate\u002FREADME.md) — networking, identity, scaling, backups, security.\n- [Reference](.\u002Fdocs\u002Freference\u002FREADME.md) — glossary, service catalog, schema pointers.\n- [Troubleshooting](.\u002Fdocs\u002Ftroubleshooting\u002FREADME.md) — diagnostic playbook by symptom + FAQ.\n\n## Repository map\n\nAgyn is split across focused repositories. The most useful starting points:\n\n| Repo | What it is |\n|---|---|\n| [`agynio\u002Fplatform`](https:\u002F\u002Fgithub.com\u002Fagynio\u002Fplatform) | This repo. Documentation hub. |\n| [`agynio\u002Farchitecture`](https:\u002F\u002Fgithub.com\u002Fagynio\u002Farchitecture) | Source-of-truth architecture and product specs. |\n| [`agynio\u002Fbootstrap`](https:\u002F\u002Fgithub.com\u002Fagynio\u002Fbootstrap) | One-command local install (k3d + Terraform). |\n| [`agynio\u002Fplatform-charts`](https:\u002F\u002Fgithub.com\u002Fagynio\u002Fplatform-charts) | Production Helm charts. |\n| [`agynio\u002Fapi`](https:\u002F\u002Fgithub.com\u002Fagynio\u002Fapi) | Protobuf schemas for every service. |\n| [`agynio\u002Fterraform-provider-agyn`](https:\u002F\u002Fgithub.com\u002Fagynio\u002Fterraform-provider-agyn) | Terraform provider. |\n| [`agynio\u002Fagyn-cli`](https:\u002F\u002Fgithub.com\u002Fagynio\u002Fagyn-cli) | Platform CLI. |\n| [`agynio\u002Fconsole-app`](https:\u002F\u002Fgithub.com\u002Fagynio\u002Fconsole-app) · [`chat-app`](https:\u002F\u002Fgithub.com\u002Fagynio\u002Fchat-app) · [`tracing-app`](https:\u002F\u002Fgithub.com\u002Fagynio\u002Ftracing-app) | Browser UIs. |\n| [`agynio\u002Fagent-init-codex`](https:\u002F\u002Fgithub.com\u002Fagynio\u002Fagent-init-codex) · [`agent-init-claude`](https:\u002F\u002Fgithub.com\u002Fagynio\u002Fagent-init-claude) · [`agent-init-agn`](https:\u002F\u002Fgithub.com\u002Fagynio\u002Fagent-init-agn) | Agent CLI init images. |\n\nFull list with descriptions: [docs\u002Freference\u002Fservice-catalog.md](.\u002Fdocs\u002Freference\u002Fservice-catalog.md).\n\n## Community\n\n- [Website](https:\u002F\u002Fagyn.io)\n- [Blog](https:\u002F\u002Fagyn.io\u002Fblog)\n- [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002FeQKYwnNqRX)\n\n## Contributing\n\nGood places to start:\n\n- Read [the architecture docs](https:\u002F\u002Fgithub.com\u002Fagynio\u002Farchitecture) to understand the system before touching code.\n- Join the [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002FeQKYwnNqRX) for questions while you work.\n\n## License\n\nAGPL-3.0\n","Agyn 是一个开源平台，用于将AI代理从个人笔记本电脑迁移到公司基础设施上，并提供企业所需的安全控制。其核心功能包括集中部署、秘密隔离、预算控制、访问权限管理以及与供应商无关的灵活性等技术特点。通过Kubernetes原生支持实现水平扩展和自动终止闲置资源，确保了成本效益和安全性。适用于需要在内部广泛使用AI代理但又担心数据安全、成本失控或缺乏有效管理手段的企业场景。",2,"2026-06-11 03:55:15","CREATED_QUERY"]