{"id":42598268,"url":"https://github.com/agentsystems/agentsystems","last_synced_at":"2026-01-29T00:13:33.274Z","repository":{"id":314355152,"uuid":"1038411139","full_name":"agentsystems/agentsystems","owner":"agentsystems","description":"Self-hosted app store and runtime for AI agents. Install third-party agents, run them on your infrastructure with your own model  providers (Ollama, Bedrock, OpenAI, etc.). Container isolation, credential injection, default-deny egress.","archived":false,"fork":false,"pushed_at":"2025-11-11T21:58:01.000Z","size":11557,"stargazers_count":53,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-11-11T23:15:54.225Z","etag":null,"topics":["agents","ai-agents","anthropic","aws-bedrock","docker","federated","llm","ollama","open-source","openai","python","self-hosted"],"latest_commit_sha":null,"homepage":"https://agentsystems.ai","language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/agentsystems.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":"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":null,"dco":null,"cla":null}},"created_at":"2025-08-15T06:34:50.000Z","updated_at":"2025-11-11T21:58:01.000Z","dependencies_parsed_at":"2026-01-06T15:13:01.038Z","dependency_job_id":null,"html_url":"https://github.com/agentsystems/agentsystems","commit_stats":null,"previous_names":["agentsystems/agentsystems"],"tags_count":7,"template":false,"template_full_name":null,"purl":"pkg:github/agentsystems/agentsystems","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentsystems%2Fagentsystems","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentsystems%2Fagentsystems/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentsystems%2Fagentsystems/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentsystems%2Fagentsystems/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/agentsystems","download_url":"https://codeload.github.com/agentsystems/agentsystems/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentsystems%2Fagentsystems/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28857231,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-28T22:56:21.783Z","status":"ssl_error","status_checked_at":"2026-01-28T22:56:00.861Z","response_time":57,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 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":["agents","ai-agents","anthropic","aws-bedrock","docker","federated","llm","ollama","open-source","openai","python","self-hosted"],"created_at":"2026-01-29T00:13:32.665Z","updated_at":"2026-01-29T00:13:33.269Z","avatar_url":"https://github.com/agentsystems.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AgentSystems\n\n\u003e [!NOTE]\n\u003e **Pre-Release Software** - AgentSystems Fortress is in active development. Join our [Discord](https://discord.com/invite/JsxDxQ5zfV) for updates and early access.\n\n**Self-hosted app store and runtime for third-party AI agents.**\n\nMost AI companies are building for the wrong future. AI distribution is inverting: instead of sending data to agents, agents will run where data lives.\n\n**Why the inversion is inevitable:**\n- Frontier models, open-source models, and local hardware all keep improving\n- Building agents is quickly becoming trivial\n- Models can run locally or via your own cloud accounts — reducing dependency on third-party agent platforms\n- [NVIDIA's research](https://arxiv.org/abs/2506.02153) shows small language models excel at specialized tasks — most agent workloads don't need massive generalist models\n- As AI transforms white-collar work, millions of subject matter experts (accountants, analysts, consultants, underwriters) will create agents to leverage their domain expertise. A tax accountant builds an agent for startup equity compensation. An insurance underwriter builds one for risk assessment.\n- The market floods with specialized agents for every niche task\n\n**Two problems emerge: discovery and trust.** When agents are everywhere, how do you discover them? How do you run third-party agents without exposing your data or credentials?\n\n**AgentSystems provides infrastructure for both:**\n\n**Distribution:**\n- Self-hosted catalog indexed by GitHub username\n- Federated Git-based discovery with auto-merge\n- Permissionless publishing\n\n**Security model:**\n- Container isolation\n- Runtime credential injection (separated from agent provider)\n- Default-deny egress with per-agent allowlists\n- Provider abstraction (agents inherit your OpenAI/Anthropic/Bedrock/Ollama config)\n- Hash-chained audit logs\n\nInfrastructure for a commoditized agent future.\n\n📺 **[Watch the 100-second demo](https://www.youtube.com/watch?v=YRDamSh7M-I)** | **[Full walkthrough (9 min)](https://www.youtube.com/watch?v=G2csNRrVXM8)**\n\n## Installation\n\n```bash\n# macOS / Linux\ncurl -fsSL https://github.com/agentsystems/agentsystems/releases/latest/download/install.sh | sh\nagentsystems init agent-platform \u0026\u0026 cd agent-platform\nagentsystems up\n```\n\n**That's it.** Open http://localhost:3001 and start discovering agents.\n\n\u003e Prefer manual installation? See the [manual installation guide](https://docs.agentsystems.ai/getting-started/manual-installation).\n\n**What's running:** Gateway (API), UI (web interface), egress proxy (network controls), and PostgreSQL (audit logs).\n\n**Next:** In the UI, click \"Discover\" → Find an agent → Click \"Add\" → Invoke it\n\n\u003e Have an NVIDIA GPU? See the [GPU acceleration guide](https://docs.agentsystems.ai/configuration/gpu-acceleration).\n\n## How It Works\n\n### For Agent Users: Browse Agents → Add Agents → Run Agents\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"images/agent-user-flow.gif\" alt=\"AgentSystems user workflow - configure models, discover agents, deploy, execute, and view audit trail\" width=\"100%\"\u003e\n\u003c/p\u003e\n\n### For Agent Developers: List on Index\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\"\u003e\n\u003ca href=\"images/agent-builder-1-scaffold.png\"\u003e\n\u003cimg src=\"images/agent-builder-1-scaffold.png\" alt=\"Build agent with model requirements\"\u003e\n\u003c/a\u003e\n\u003cp align=\"center\"\u003e\u003cem\u003e1. Build agent with model requirements\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"50%\"\u003e\n\u003ca href=\"images/agent-builder-2-registry.png\"\u003e\n\u003cimg src=\"images/agent-builder-2-registry.png\" alt=\"Push to container registry\"\u003e\n\u003c/a\u003e\n\u003cp align=\"center\"\u003e\u003cem\u003e2. Push to container registry\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\"\u003e\n\u003ca href=\"images/agent-builder-3-pr.png\"\u003e\n\u003cimg src=\"images/agent-builder-3-pr.png\" alt=\"Submit to agent index\"\u003e\n\u003c/a\u003e\n\u003cp align=\"center\"\u003e\u003cem\u003e3. List your agent in the index (automated merge)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"50%\"\u003e\n\u003ca href=\"images/agent-builder-4-metadata.png\"\u003e\n\u003cimg src=\"images/agent-builder-4-metadata.png\" alt=\"Agent available for discovery\"\u003e\n\u003c/a\u003e\n\u003cp align=\"center\"\u003e\u003cem\u003e4. Agent available for discovery\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n## Architecture\n\n```mermaid\ngraph TB\n    subgraph \"Your Infrastructure\"\n        App[Your Application]\n        UI[Web UI :3001]\n        GW[Gateway :18080]\n        Agent[Third-Party Agent\u003cbr/\u003eContainer]\n        Proxy[Egress Proxy :3128]\n        Storage[Thread Storage\u003cbr/\u003e/artifacts/thread-id/]\n        Audit[Hash-Chained Logs\u003cbr/\u003ePostgreSQL]\n    end\n\n    subgraph \"External\"\n        Index[Agent Index\u003cbr/\u003eagentsystems.github.io]\n        Allow[approved.com ✓]\n        Block[evil.com ✗]\n        AI[AI Providers\u003cbr/\u003eOpenAI/Anthropic/Ollama]\n    end\n\n    Index -.-\u003e|1. Discover \u0026 Pull| GW\n    UI --\u003e|Manage| GW\n    App --\u003e|2. POST /invoke/agent| GW\n    GW --\u003e|3. Route + Inject X-Thread-Id| Agent\n    Agent --\u003e|4. Outbound Call| Proxy\n    Proxy --\u003e|Check Allowlist| Allow\n    Proxy -.-\u003e|Blocked| Block\n    Agent \u003c--\u003e|5. Read/Write| Storage\n    Agent --\u003e|6. Call LLM| AI\n    Agent --\u003e|7. Return Result| GW\n    GW --\u003e|8. Response| App\n    GW --\u003e|Audit Logs| Audit\n\n    style Agent fill:#1a4d5c\n    style Proxy fill:#2d5f3f\n    style Block fill:#5c1a1a\n    style Audit fill:#3d3d5c\n    style UI fill:#3d5c4d\n```\n\n## How is this different from...?\n\n**Agent frameworks (LangChain, Agno, CrewAI)?** Those help you *build* agents. AgentSystems helps you *discover and run* agents built by others. You can build with those frameworks and publish to AgentSystems.\n\n**Cloud-hosted agents (Harvey, Artisan)?** Your data goes to their servers. AgentSystems runs on your infrastructure — designed to keep your data under your control.\n\n**Deployment platforms (Coolify, Heroku)?** Those deploy web apps. AgentSystems deploys AI agents with agent-specific features: model routing, egress controls, thread-scoped storage, federated discovery.\n\n**Manual Docker / Docker Compose?** AgentSystems adds discovery and pre-built infrastructure: federated agent catalog, UI, gateway, egress proxy, audit logs.\n\n---\n\n## Platform Components\n\nThe platform consists of 6 interdependent repositories:\n\n| Component | What It Does | Technology | Latest Version |\n|-----------|--------------|------------|----------------|\n| **[agent-control-plane](https://github.com/agentsystems/agent-control-plane)** | Gateway, orchestration, egress proxy | FastAPI, PostgreSQL | ![Version](https://img.shields.io/github/v/release/agentsystems/agent-control-plane?label=\u0026color=blue) |\n| **[agentsystems-sdk](https://github.com/agentsystems/agentsystems-sdk)** | CLI tool for deployment | Python, Docker | ![Version](https://img.shields.io/github/v/release/agentsystems/agentsystems-sdk?label=\u0026color=blue) |\n| **[agentsystems-ui](https://github.com/agentsystems/agentsystems-ui)** | Web interface for management | React, TypeScript | ![Version](https://img.shields.io/github/v/release/agentsystems/agentsystems-ui?label=\u0026color=blue) |\n| **[agentsystems-toolkit](https://github.com/agentsystems/agentsystems-toolkit)** | Library for building agents | Python, LangChain | ![Version](https://img.shields.io/github/v/release/agentsystems/agentsystems-toolkit?label=\u0026color=blue) |\n| **[agent-template](https://github.com/agentsystems/agent-template)** | Starter template for new agents | FastAPI, LangGraph | rolling |\n| **[agent-index](https://github.com/agentsystems/agent-index)** | Federated agent discovery | GitHub Pages | rolling |\n\n## Frequently Asked Questions\n\n**Q: How does agent publishing work?**\n\nA: Fork the agent-index repo, create `developers/your-github-username/`, add your agent metadata, and submit a PR. Auto-merge validates that the folder name matches your GitHub username (fork ownership = namespace ownership). No manual approval needed.\n\n**Q: Are agents reviewed before being listed?**\n\nA: No. The AgentSystems Community Index lists agents from third-party developers. AgentSystems does not review or endorse software in any index.\n\n**Q: Can I use this in production?**\n\nA: AgentSystems is pre-release. Use for development and testing. For production, wait for stable release or contact us on [Discord](https://discord.com/invite/JsxDxQ5zfV) for early access guidance.\n\n**Q: Can I run a private agent index?**\n\nA: Yes. The index is Git-based and federated. Fork the [agent-index](https://github.com/agentsystems/agent-index) repo to run your own index.\n\n## Documentation\n\n**Getting Started:**\n- [Installation \u0026 Quick Start](https://docs.agentsystems.ai/getting-started)\n- [Architecture Overview](https://docs.agentsystems.ai/getting-started/key-concepts)\n- [Configuration](https://docs.agentsystems.ai/configuration)\n\n**For Agent Developers:**\n- [Build an Agent](https://docs.agentsystems.ai/deploy-agents/quickstart)\n- [Publish to Index](https://docs.agentsystems.ai/deploy-agents/list-on-index)\n- [Agent Index Repository](https://github.com/agentsystems/agent-index)\n\n## Contributing\n\nWe welcome contributions across the stack:\n- 🤖 **Build Agents** - Create specialized agents and publish to the index\n- 🔒 **Security** - Improve isolation, audit mechanisms, or egress controls\n- 📚 **Documentation** - Write guides, tutorials, or API references\n- 🐛 **Bug Reports** - Help identify and fix issues\n\nSee [CONTRIBUTING.md](./CONTRIBUTING.md) for guidelines.\n\n## Community\n\n- [Discord](https://discord.com/invite/JsxDxQ5zfV) - Chat with developers and contributors\n- [GitHub Issues](https://github.com/agentsystems/agentsystems/issues) - Bug reports and feature requests\n\n## License\n\nLicensed under the [Apache-2.0 license](./LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagentsystems%2Fagentsystems","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fagentsystems%2Fagentsystems","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagentsystems%2Fagentsystems/lists"}