{"id":24834412,"url":"https://github.com/agno-agi/agno","last_synced_at":"2026-03-10T17:13:30.016Z","repository":{"id":62907256,"uuid":"488641606","full_name":"agno-agi/agno","owner":"agno-agi","description":"Build multi-agent systems that learn and improve with every interaction.","archived":false,"fork":false,"pushed_at":"2026-02-11T00:18:16.000Z","size":270519,"stargazers_count":37761,"open_issues_count":570,"forks_count":5004,"subscribers_count":227,"default_branch":"main","last_synced_at":"2026-02-11T00:19:50.931Z","etag":null,"topics":["agents","ai","ai-agents","developer-tools","python"],"latest_commit_sha":null,"homepage":"https://docs.agno.com","language":"Python","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/agno-agi.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":"AGENTS.md","dco":null,"cla":null}},"created_at":"2022-05-04T15:23:02.000Z","updated_at":"2026-02-11T00:08:04.000Z","dependencies_parsed_at":"2023-09-28T19:19:43.436Z","dependency_job_id":"dc2eb4e0-0681-4aef-84fd-38e00b5d3274","html_url":"https://github.com/agno-agi/agno","commit_stats":null,"previous_names":["agnoagi/agno","phidatahq/phidata","agno-agi/agno"],"tags_count":430,"template":false,"template_full_name":null,"purl":"pkg:github/agno-agi/agno","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agno-agi%2Fagno","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agno-agi%2Fagno/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agno-agi%2Fagno/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agno-agi%2Fagno/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/agno-agi","download_url":"https://codeload.github.com/agno-agi/agno/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agno-agi%2Fagno/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29494188,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-16T00:00:57.352Z","status":"ssl_error","status_checked_at":"2026-02-15T23:56:34.338Z","response_time":118,"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","ai-agents","developer-tools","python"],"created_at":"2025-01-31T03:01:47.243Z","updated_at":"2026-03-10T17:13:29.995Z","avatar_url":"https://github.com/agno-agi.png","language":"Python","funding_links":[],"categories":["Python","智能体 Agents","🤖 AI \u0026 Machine Learning","Agent","Frameworks","HarmonyOS","语言资源库","\u003ca id=\"tools\"\u003e\u003c/a\u003e🛠️ Tools","🧱 Agent Frameworks","Tools","Table of Contents","Coding Tools for Economists","Repos","🕵️ 智能体（Agents）","4. Agentic AI \u0026 Multi-Agent Systems","Librerías para usar NLP en español","Orchestration Frameworks","AI Agent Frameworks \u0026 SDKs","\u003ca name=\"Python\"\u003e\u003c/a\u003ePython","2. Libraries \u0026 Frameworks","Tools and Code","Agent Frameworks","App","Frameworks \u0026 Libraries","Machine Learning","🧩 Agent Frameworks \u0026 Dev Libraries","🏗️ Infrastructure, Utils \u0026 Orchestration","🌟 Core Frameworks","🛠️ Agentic AI Frameworks","Agent SDKs \u0026 Frameworks","📦 Isolate Context","Orchestration"],"sub_categories":["Windows Manager","python","Bleeding Edge ⚗️","Lightweight / Minimalist","Agent Frameworks","Model Tools","AI Agent Frameworks","主流 Agent 框架","Modelos de Embeddings para Sentence Similarity y Semantic Search","Multi-Agent Collaboration Systems","Python","Tools","Multi-Agent Orchestration","Specialized Agent Libraries","🤖 Agentic AI Frameworks","🤖 Multi-Agent Platforms","Lightweight \u0026 Typed","Multi-Agent Frameworks","Agent Framework"],"readme":"\u003cdiv align=\"center\" id=\"top\"\u003e\n  \u003ca href=\"https://agno.com\"\u003e\n    \u003cpicture\u003e\n      \u003csource media=\"(prefers-color-scheme: dark)\" srcset=\"https://agno-public.s3.us-east-1.amazonaws.com/assets/logo-dark.svg\"\u003e\n      \u003csource media=\"(prefers-color-scheme: light)\" srcset=\"https://agno-public.s3.us-east-1.amazonaws.com/assets/logo-light.svg\"\u003e\n      \u003cimg src=\"https://agno-public.s3.us-east-1.amazonaws.com/assets/logo-light.svg\" alt=\"Agno\"\u003e\n    \u003c/picture\u003e\n  \u003c/a\u003e\n\u003c/div\u003e\n\n\u003cp align=\"center\"\u003e\n  Build, run, and manage agentic software at scale.\n\u003c/p\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://docs.agno.com\"\u003eDocs\u003c/a\u003e\n  \u003cspan\u003e\u0026nbsp;•\u0026nbsp;\u003c/span\u003e\n  \u003ca href=\"https://github.com/agno-agi/agno/tree/main/cookbook\"\u003eCookbook\u003c/a\u003e\n  \u003cspan\u003e\u0026nbsp;•\u0026nbsp;\u003c/span\u003e\n  \u003ca href=\"https://docs.agno.com/first-agent\"\u003eQuickstart\u003c/a\u003e\n  \u003cspan\u003e\u0026nbsp;•\u0026nbsp;\u003c/span\u003e\n  \u003ca href=\"https://www.agno.com/discord\"\u003eDiscord\u003c/a\u003e\n\u003c/div\u003e\n\n## What is Agno\n\nAgno is the runtime for agentic software. Build agents, teams, and workflows. Run them as scalable services. Monitor and manage them in production.\n\n| Layer | What it does |\n|-------|--------------|\n| **Framework** | Build agents, teams, and workflows with memory, knowledge, guardrails, and 100+ integrations. |\n| **Runtime** | Serve your system in production with a stateless, session-scoped FastAPI backend. |\n| **Control Plane** | Test, monitor, and manage your system using the [AgentOS UI](https://os.agno.com). |\n\n## Quick Start\n\nBuild a stateful, tool-using agent and serve it as a production API in ~20 lines.\n\n```python\nfrom agno.agent import Agent\nfrom agno.db.sqlite import SqliteDb\nfrom agno.models.anthropic import Claude\nfrom agno.os import AgentOS\nfrom agno.tools.mcp import MCPTools\n\nagno_assist = Agent(\n    name=\"Agno Assist\",\n    model=Claude(id=\"claude-sonnet-4-6\"),\n    db=SqliteDb(db_file=\"agno.db\"),\n    tools=[MCPTools(url=\"https://docs.agno.com/mcp\")],\n    add_history_to_context=True,\n    num_history_runs=3,\n    markdown=True,\n)\n\nagent_os = AgentOS(agents=[agno_assist], tracing=True)\napp = agent_os.get_app()\n```\n\nRun it:\n\n```bash\nexport ANTHROPIC_API_KEY=\"***\"\n\nuvx --python 3.12 \\\n  --with \"agno[os]\" \\\n  --with anthropic \\\n  --with mcp \\\n  fastapi dev agno_assist.py\n```\n\nIn ~20 lines, you get:\n- A stateful agent with streaming responses\n- Per-user, per-session isolation\n- A production API at http://localhost:8000\n- Native tracing\n\nConnect to the [AgentOS UI](https://os.agno.com) to monitor, manage, and test your agents.\n\n1. Open [os.agno.com](https://os.agno.com) and sign in.\n2. Click **\"Add new OS\"** in the top navigation.\n3. Select **\"Local\"** to connect to a local AgentOS.\n4. Enter your endpoint URL (default: `http://localhost:8000`).\n5. Name it \"Local AgentOS\".\n6. Click **\"Connect\"**.\n\nhttps://github.com/user-attachments/assets/75258047-2471-4920-8874-30d68c492683\n\nOpen Chat, select your agent, and ask:\n\n\u003e What is Agno?\n\nThe agent retrieves context from the Agno MCP server and responds with grounded answers.\n\nhttps://github.com/user-attachments/assets/24c28d28-1d17-492c-815d-810e992ea8d2\n\nYou can use this exact same architecture for running multi-agent systems in production.\n\n## Why Agno?\n\nAgentic software introduces three fundamental shifts.\n\n### A new interaction model\n\nTraditional software receives a request and returns a response. Agents stream reasoning, tool calls, and results in real time. They can pause mid-execution, wait for approval, and resume later.\n\nAgno treats streaming and long-running execution as first-class behavior.\n\n### A new governance model\n\nTraditional systems execute predefined decision logic written in advance. Agents choose actions dynamically. Some actions are low risk. Some require user approval. Some require administrative authority.\n\nAgno lets you define who decides what as part of the agent definition, with:\n\n- Approval workflows\n- Human-in-the-loop\n- Audit logs\n- Enforcement at runtime\n\n### A new trust model\n\nTraditional systems are designed to be predictable. Every execution path is defined in advance. Agents introduce probabilistic reasoning into the execution path.\n\nAgno builds trust into the engine itself:\n\n- Guardrails run as part of execution\n- Evaluations integrate into the agent loop\n- Traces and audit logs are first-class\n\n## Built for Production\n\nAgno runs in your infrastructure, not ours.\n\n- Stateless, horizontally scalable runtime.\n- 50+ APIs and background execution.\n- Per-user and per-session isolation.\n- Runtime approval enforcement.\n- Native tracing and full auditability.\n- Sessions, memory, knowledge, and traces stored in your database.\n\nYou own the system. You own the data. You define the rules.\n\n## What You Can Build\n\nAgno powers real agentic systems built from the same primitives above.\n\n- [**Pal →**](https://github.com/agno-agi/pal) A personal agent that learns your preferences.\n- [**Dash →**](https://github.com/agno-agi/dash) A self-learning data agent grounded in six layers of context.\n- [**Scout →**](https://github.com/agno-agi/scout) A self-learning context agent that manages enterprise context knowledge.\n- [**Gcode →**](https://github.com/agno-agi/gcode) A post-IDE coding agent that improves over time.\n- [**Investment Team →**](https://github.com/agno-agi/investment-team) A multi-agent investment committee that debates and allocates capital.\n\nSingle agents. Coordinated teams. Structured workflows. All built on one architecture.\n\n## Get Started\n\n1. [Read the docs](https://docs.agno.com)\n2. [Build your first agent](https://docs.agno.com/first-agent)\n3. Explore the [cookbook](https://github.com/agno-agi/agno/tree/main/cookbook)\n\n## IDE Integration\n\nAdd Agno docs as a source in your coding tools:\n\n**Cursor:** Settings → Indexing \u0026 Docs → Add `https://docs.agno.com/llms-full.txt`\n\nAlso works with VSCode, Windsurf, and similar tools.\n\n## Contributing\n\nSee the [contributing guide](https://github.com/agno-agi/agno/blob/main/CONTRIBUTING.md).\n\n## Telemetry\n\nAgno logs which model providers are used to prioritize updates. Disable with `AGNO_TELEMETRY=false`.\n\n\u003cp align=\"right\"\u003e\u003ca href=\"#top\"\u003e↑ Back to top\u003c/a\u003e\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagno-agi%2Fagno","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fagno-agi%2Fagno","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagno-agi%2Fagno/lists"}