登录

agno

agno-agiApache-2.0活跃维护 有专家点评

用 Python 搭建自主 AI Agent 的平台，把多智能体编排、工具调用和任务执行打包成开箱即用的组件，省去从零搭框架的麻烦。

The self-driving agent platform

v3.1.12发布于 2026-10-29 14:00 UTC43,136star +47 / 7 天6,272fork同步于 2026-11-10 17:19 UTC
Agent 框架多智能体编排自主智能体Python
对比 GitHub 官网agentsaiai-agentsdeveloper-toolspython

专家点评

上手难度：硬核更新于 2026-11-11

把 Python Agent 从脚本变成带鉴权、审批和持久任务队列的常驻服务，省掉自建控制面

适用场景

  • 需要人工审批环节的内部工具（比如 Agent 起草、人确认后才执行写操作）：AgentOS 自带断点续跑和审批流，自己用 FastAPI 拼这套状态机要写不少代码
  • 要把 Agent 暴露给 Claude、ChatGPT 或 Slack 当工具调用：内置 MCP Server 和 REST 接口，比手写协议适配层省事
  • 长任务批处理（跑评测、批量抓取加工）：持久化任务队列重启后仍能查状态，用 Celery 加自建状态表也能做，但要多维护一层
  • 多 Agent 分工的流程编排：团队和工作流是框架原生概念，换成纯 LangGraph 要自己定义节点和状态

踩坑

  • 它不是 pip install 就能跑的库：要克隆云厂商模板仓库、按 setup skill 配 PostgreSQL 和平台连接，想当轻量 SDK 嵌进现有服务会撞上这套部署假设
  • 平台界面依赖连接 os.agno.com，离线或内网环境这条路径走不通，得先确认能否只用 API
  • issue 里反复出现的是工具调用循环控制（tool_call_limit 不生效）和上下文管理/压缩这类运行时行为问题，把 Agent 放到无人值守的长循环里之前，先自己验证终止条件
  • 默认上报每个 Agent 的遥测事件，合规敏感的环境要显式设 AGNO_TELEMETRY=false

同类对比

要的是纯编排库、不想引入平台层，看 LangGraph 或 CrewAI；要的是单机轻量 Agent 循环，OpenAI Agents SDK 这类更薄的封装更合适。

怎么上手

由 README 提炼，执行前请确认
原文 
git clone https://github.com/agno-agi/agentos-railway agent-platform
cd agent-platform
# 然后按 .agents/skills/setup-platform/SKILL.md 执行
硬件要求按 README 说明

README 未说明

下载：源码 zip·GitHub Releases（安装包）本站不镜像安装包

项目说明

由 README 自动翻译提炼

自管理智能体平台，把 Agent 部署成带 API 和 MCP 的持久服务

用 Python 搭建自主 AI Agent 的平台，把多智能体编排、工具调用和任务执行打包成开箱即用的组件，省去从零搭框架的麻烦。

核心能力

  • 用 Agno、Claude Agent 或 Codex SDK 构建 Agent 并组合成团队与工作流
  • AgentOS 提供鉴权、角色权限、断点续跑、人工审批与定时调度
  • 内置 REST API 与 MCP Server，可接入自家产品、Claude、ChatGPT 和 Slack
  • 持久化后台任务队列，重启后仍能追踪任务状态
  • 支持追踪运行、检查工具调用并诊断失败的观测能力

容易踩的坑

需要 PostgreSQL 存储对话、记忆和平台活动；需克隆对应云厂商模板仓库并按其 setup skill 配置，不能直接 pip 安装即用；需连接 os.agno.com 才能使用平台界面；默认会上报每个 Agent 的遥测事件，可用 AGNO_TELEMETRY=false 关闭

内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README

最近发版

5 个版本v3.1.12
全部 release
  1. v3.1.12最新正式版2026-10-29 · 2026-10-29 14:00 UTC

    Changelog

    New Features:

    • Native Approvals for Harness Agents: Claude's and Codex's own permission requests now reach the AgentOS approval UI. When the agent has a database, including one AgentOS supplies, a native request persists a PAUSED run that shows up in the existing chat and Approvals views, and Resolve plus Continue Run delivers the decision back to the same native execution without replaying the prompt. The harness's own policy decides when to ask — Claude keeps its permission_mode and explicit permission callbacks, Codex supports approval_policy="on-request" | "untrusted" | "never" alongside its existing SDK auto_review and deny_all modes — so there is no separate Agno setting to turn on. Decisions are validated against the exact action requested, with sync and async continuation, cancellation, expiry and storage-failure handling, and sandboxed agents keep this across Docker and AgentCore: capability negotiation, a decision RPC, fenced persistence, reattachment after an API-worker loss, separate approval-wait and execution budgets, and no replay after process loss. Note that a CodexAgent with no approval settings now runs under the native on-request policy, so a request that previously went nowhere pauses the run instead; hitl_timeout (default 900s) bounds how long it waits. See cookbook/frameworks/human_in_the_loop/.
    • Initially Disabled Company Routines: Routine(enabled=False) lets a template ship an inactive Routine that a user turns on later from the UI, with True still the default. Disabled Routines are created atomically, stay linked to their Product and visible in listings, are skipped by the scheduler, and keep the user's saved choice across restarts. The flag is honored in Python and YAML bootstrap, the setup and creation APIs, the sync and async Company Manager, and the Company tools. Duplicate create requests still return 409 and cannot enable an existing Routine, and the existing pause/resume endpoints enable it without recreating it. See cookbook/05_agent_os/30_company/11_disabled_routine.py.
    • Headline Numbers on Charts: ChartTools.create_chart() takes an optional preformatted value — a total or latest value such as "$22.3K" or "94%" — emitted as "value" in the chart block and rendered by Agno OS beside the chart title. The docstring tells the model to leave it out when no single number summarizes the chart, so averages and rates are not summed.

    Improvements:

    • Company Routine Sorting: GET /company/routines now also sorts by next_run_at, schedule_type and enabled, so Agno OS can sort its routines table by Next run at, Schedule and Active. Paused and on-demand Routines have no upcoming run, so they come last in either direction, and Routines with the same value keep their creation order.
    • Cookbooks: Added an ApifyTools job search example that caps the Actor's item count with a tool hook and trims each dataset item to title, company, location, posted date and link, so a broad search stays small in context. Added a fully local Pixeltable RAG example that writes chunks through langchain-pixeltable and searches them with LangChainVectorDb, using local sentence-transformers embeddings and Ollama — no embedding API key and no separate vector database server.

    Bug Fixes:

    • FastAPI Native Tracing: FastAPI 0.142.0 enables its own OpenTelemetry tracing as soon as a global tracer provider exists, which AgentOS(tracing=True) installs, so FastAPI's request spans were stored alongside Agno's. Every run became a child of the request span and traces were recorded as fastapi.dependencies with empty run_id, session_id and agent_id, breaking the Runs view, while each UI request stored a trace of its own. AgentOS now opts the app it builds out of FastAPI's tracing, and setup_tracing() filters foreign spans so a stored trace is rooted at the Agno run. Apps without tracing=True keep FastAPI's defaults, and
  2. v3.1.112026-10-27 · 2026-10-27 19:28 UTC
    查看更新说明

    Changelog

    New Features:

    • Harness Agents in Teams and Workflows: ClaudeAgent and CodexAgent can now be members of an Agno Team and steps of a Workflow, including inside Parallel, Loop, Condition and Router. The team leader delegates to them with delegate_task_to_member like any other member, each harness runs with its own model, tools and workspace, keeps its own conversation across turns of the same session, and the team or workflow collects its runs as usual. A harness agent with sandbox= runs each turn in its own container as a member or step, and AgentOS lists harness members on the team page. See cookbook/frameworks/harness_teams/ and cookbook/frameworks/harness_workflows/.
    • Session Search: Added GET /sessions/filter-schema and POST /sessions/search with nested AND/OR/NOT filters on session name, session/user/component IDs, session type and created/updated timestamps, matching the Traces API. Predicates are applied before counting and pagination in PostgreSQL and SQLite, with a batched fallback for other adapters. Sync and async client methods are included.
    • Company Tasks: POST /company/tasks accepts status, so Tasks can be created in Backlog, Ready or Cancelled. Tasks can move between any stages, Done and Cancelled Tasks can reopen, and title and brief can be edited at any stage. In progress still starts only with a run, and moving out of it while that run is executing or paused is refused.
    • Company Routines: Added POST /company/routines/{id}/cancel, /archive, /restore and admin-only DELETE /company/routines/{id}. GET /company/routines takes sort_by and sort_order. Pause and resume on an on-demand Routine return 409, and scheduler runs no longer move updated_at.

    Improvements:

    • Cookbooks: Added a customer feedback workflow for the AgentOS UI, where Company Manager reads Markdown feedback, proposes evidence-backed Projects and Backlog Tasks, and leaves acceptance to a human.
    • README: Aligned the README with the docs introduction and the self-improving agent platform positioning.

    Bug Fixes:

    • ReaderFactory: create_reader() now returns a fresh reader configured with the per-call options instead of a cached singleton, so chunk_size and other overrides are respected and mutations no longer leak across Knowledge instances.
    • Workflow Step Content: StepOutput.to_dict() keeps ints, floats, bools and strs as themselves instead of stringifying them, so a step that returned 0 or False no longer comes back as "0" or "False" after a HITL resume, a session reload, or through the AgentOS workflow API.
    • HuggingFace: default_headers is mapped to the SDK's headers, store is sent in extra_body, and max_retries and default_query are deprecated and ignored instead of raising TypeError. An agent with no tools no longer sends tools=[], which made non-streaming runs return None content.
    • Google Calendar: find_available_slots now works in the authenticated user's timezone instead of UTC, so working hours and date-only inputs mean the user's local day. It also fetches events for the full scanned window, so busy time on the last day of a range is no longer offered as free.
    • Company Archive: Archived Tasks no longer block archiving their Project or Product. Visible active Tasks still block as before.
    • RedisDb: keyword_search now passes the caller's limit to redisvl instead of silently returning its default of 10 results.
    • MMRReranker: rerank and arerank return no documents when limit is zero or negative instead of always returning the closest match.
    • FieldLabeledCSVReader: page_size=0 is rejected alongside negative values instead of silently returning no documents on larger files.
    • AgentOSClient: Removed the documented but non-existent stream argument from continue_agent_run. Use continue_agent_run_stream to stream.

    What's Chang

  3. v3.1.102026-10-23 · 2026-10-23 13:10 UTC
    查看更新说明

    Changelog

    Bug Fixes:

    • CodexAgent: Now signs in automatically with OPENAI_API_KEY, and keeps an existing ChatGPT or other login.
    • OS Manager: OS Manager now lists and runs external agents such as ClaudeAgent and CodexAgent registered in AgentOS(agents=[...]), by name or ID.
    • Knowledge Upload: POST /knowledge/content now returns a clear 400 message when an upload has no file, text_content or URL, or when url is not a single URL.
    • Tracing: Spans from AgentOS(tracing=True) and setup_tracing() now keep up to 1,024 attributes, so model spans keep their full input and message history on runs with many tool calls. OTEL_SPAN_ATTRIBUTE_COUNT_LIMIT and OTEL_ATTRIBUTE_COUNT_LIMIT still take precedence.

    What's Changed

    Full Changelog: https://github.com/agno-agi/agno/compare/v3.1.9...v3.1.10

  4. v3.1.92026-10-22 · 2026-10-22 16:50 UTC
    查看更新说明

    Changelog

    New Features:

    • MCP Tool Runner: POST /mcp/server/tools/{tool_name}/run runs any tool listed on the AgentOS Server Card over HTTP and returns its result, so a tool can be tested without an MCP client. Turn it off with MCPConfig(tool_run_endpoint=False). See cookbook.

    Bug Fixes:

    • AgentOS MCP Server: /mcp and /mcp/server-card now accept browser requests from origins the AgentOS CORS policy allows, so os.agno.com can reach the MCP server of a local AgentOS. /info now reports the configured MCP path instead of always /mcp.
    • Postgres Metrics: Metrics refresh on a migrated database no longer loads the legacy sessions.runs column into memory.
    • Function Workflows: A function passed as a workflow's steps now runs once when its body raises a TypeError, and sync functions and generators now work with arun().
    • AgenticChunking: Chunking no longer hangs when the model returns a zero or negative breakpoint, and max_chunk_size must be greater than 0.
    • BaiduSearchTools: Chinese titles and abstracts are returned as readable text instead of \uXXXX escapes.
    • Human-in-the-Loop User Input: A requires_user_input tool with a parameter typed int | None or another X | Y type now pauses cleanly, and the paused run is saved and resumes with continue_run(run_id=...).
    • Mistral: The timeout, endpoint and safe_mode parameters on MistralChat, and endpoint on MistralEmbedder, now work instead of raising a TypeError. safe_mode is deprecated in favor of safe_prompt.

    What's Changed

    New Contributors

    Full Changelog: https://github.com/agno-agi/agno/compare/v3.1.8...v3.1.9

  5. v3.1.82026-10-21 · 2026-10-21 12:15 UTC
    查看更新说明

    Changelog

    New Features

    • Postgres Sandbox Checkpoint Store: Added PostgresCheckpointStore for storing sandbox checkpoints directly in PostgreSQL, allowing multi-replica deployments to restore sessions without S3 or shared filesystems. Checkpoints are chunked, written transactionally, deduplicated by SHA-256 and verified on read. It is opt-in; existing checkpoint defaults are unchanged. (#11186)
    • Framework Managers as Routine Executors: Company Routines can now use the internal Product Manager or OS Manager as executors through declarations, the Routine API and human-chat configuration. Reserved manager IDs resolve only from the owning AgentOS and cannot be replaced by saved or user-defined components. Includes an optional weekly Product Manager review. (#11193)
    • Sandbox Checkpoint Retention: Sandboxes now retain the three newest checkpoints per session by default. Configure retain_checkpoints=None to preserve every checkpoint. Unpublished or superseded checkpoints are retired and deleted after the run outcome is safely stored. (#11187)

    Improvements

    • Sandbox Session Cleanup: Deleting a sandbox-backed session now removes its warm computer and associated checkpoint objects after the database transaction commits. Single, bulk and user-scoped session deletion are supported without affecting sessions the caller does not own. (#11187)
    • OS Manager Specialist Visibility: Platform Builder and Platform Manager now appear as members of OS Manager in /teams and /teams/os-manager-internal. They remain excluded from the reusable application registry, top-level agent discovery and standalone agent routes. (#11198)
    • Claude Defaults to Sonnet 5.5: Claude() now defaults to claude-sonnet-5-5, replacing the deprecated claude-sonnet-4-5-20250929 before its retirement. Non-default temperature, top_p and top_k values are dropped with a warning for newer Claude models that reject those sampling parameters. This behavior applies across Anthropic, Bedrock, Foundry and Vertex providers. (#11212)

    Behavior Changes

    • Checkpoint Retention: Only the three newest sandbox checkpoints are retained by default. Opening a checkpoint for an older run can now raise CheckpointObjectNotFound. Set retain_checkpoints=None to restore the previous unlimited-retention behavior. (#11187)
    • Durable Sandbox Startup Validation: AgentOS now fails at startup when a durable-queue sandbox uses the host-local default checkpoint store. Configure a checkpoint store shared by every replica, such as PostgresCheckpointStore or S3CheckpointStore. Previously this invalid configuration failed only on the first submission. (#11187)

    Bug Fixes

    • Missing Sandbox Checkpoints: A committed checkpoint missing from storage now ends the turn with a clear, non-retryable error, retires the newly created computer and releases the session. Previously the run remained RUNNING, exhausted queue retries and blocked later turns on the session. (#11187)
    • Company Routine Execution: Denied status writes and failed Studio runner delegation now correctly fail the Routine. Stale archived catalog entries no longer collide with owned reserved managers. (#11193)

    What's Changed

用户点评

登录用户的真实使用记录，可按版本和硬件筛选
共 0 条

    还没有人点评。第一个说出真实体验的人最有价值。

    README 原文

    未翻译
    在 GitHub 打开

    Introduction

    Agno is a self-managing agent platform. Build agents for your company, product, or customers. Run them as durable services on AgentOS. Put them to work automating company operations.

    • Build agents with the Agno, Claude Agent, or Codex SDKs. Combine agents into teams and workflows.
    • Run agents as durable services with built-in API and MCP. AgentOS handles authentication, role-based access, resume/replay, human approvals, scheduling, and durable execution.
    • Automate company operations with Company OS. Give agents responsibilities, organize work into projects and tasks, and configure recurring routines. People set direction and review results; agents own and execute.

    Agno provides the orchestration and service layer around your agents, making them available in:

    1. Your product: using the REST API.
    2. Claude and ChatGPT: using the MCP server.
    3. Chat apps like Slack: using Agno Interfaces.

    Run your platform in your own cloud and keep your data in your control. Review conversations, inspect traces, manage knowledge, and track your agent activity using the AgentOS UI.

    Get started

    Agno is built for coding agents. Start with a pre-built template and give this prompt to your coding agent:

    Help me set up my agent platform and build my first agent.

Clone https://github.com/agno-agi/agentos-railway into a folder called agent-platform, cd into it, and follow .agents/skills/setup-platform/SKILL.md.

    The setup skill runs your platform locally and helps you build your first agent. You get:

    • An API server and MCP server.
    • PostgreSQL storage for conversations, memory, and platform activity.
    • OS Manager to help build and manage your platform.
    • Claude and Codex engineers to work on your code.
    • Skills for building, evaluating, and improving agents.
    • A Company workspace for organizing ongoing work, with a daily maintenance routine that reviews your codebase and Agno releases and proposes platform improvements.

    Connect your platform to os.agno.com to start using it. Build agents with code, use the no-code UI, or chat with the OS Manager.

    Start improving your agents and platform with the /improve skill. Keep useful changes and regression tests so each round builds on the last. When you're ready, configure scheduled improvement runs in a sandbox that return pull requests for review.

    Templates for every cloud

    Choose a template for your cloud: Docker · Railway · AWS · GCP · Azure · Fly.io · Render · Modal · Helm

    What's included

    CapabilityWhat you can do
    Agents and teamsBuild agents that use tools, delegate work, and collaborate.
    WorkflowsControl execution with routing, conditions, loops, and parallel steps.
    Memory and knowledgeRemember users across sessions and retrieve answers from your data.
    Tools and integrationsConnect agents to APIs, databases, and MCP servers.
    Durable executionPersist background jobs and track their status across restarts.
    Human approvalReview sensitive actions before they run, then approve and continue.
    ObservabilityTrace runs, inspect tool calls, and diagnose failures.
    SchedulingRun agents, teams, and workflows on recurring schedules.
    SecurityControl access with authentication, roles, and per-user data isolation.
    Coding agentsRun Claude and Codex in sandboxes to implement and test changes.
    Company OSOrganize work into products, projects, tasks, and recurring routines.

    Tutorials

    First, add Agno to your coding agent so it can read the tutorials as you build. Then, learn how to:

    Community

    Follow Agno on X for releases and demos, or subscribe to The Agno Loop.

    See the contributing guide to contribute.

    License

    Agno is distributed under the Apache 2.0 license.

    Telemetry

    Agno sends a telemetry event per agent so we know which model providers to prioritize. Prompts, messages, and outputs are never sent. Disable by setting AGNO_TELEMETRY=false.

    相关项目

    同分类里 star 最高的项目
    对比全部 →
    ECC
    affaan-m·JavaScript

    为 Claude Code、Codex、Cursor 等编码智能体提供技能、直觉、记忆与安全防护的性能优化层，让 AI 编程助手更稳定高效地干活。

    智能体框架+4Agent 框架
    300641+191444kv2.2.32026-11-09 04:56 UTC
    deepseek-harness
    deepseek-ai·TypeScript

    DeepSeek 开源的 Agent 编排框架，把模型、工具、记忆等所有能力都做成可插拔插件，方便按需拼装和扩展智能体。

    Agent 框架+3Agent 框架
    278174+297434kdsh-v0.2.2-rc.12026-11-04 13:06 UTC
    hermes-agent
    NousResearch·Python

    一个可随使用不断成长的 AI Agent 框架，支持接入 Claude、ChatGPT 等多种大模型，用于搭建和编排自主智能体。

    Agent 框架+3Agent 框架进阶
    262435+115559kv0.23.12026-11-10 23:17 UTC
    firecrawl
    firecrawl·TypeScript

    把任意网页抓取并转成干净 Markdown 或结构化数据，直接喂给 LLM 和 AI Agent，省去自己写爬虫和清洗的麻烦。

    网页抓取+4Agent 框架进阶
    200517+117811kv2.11.02026-11-10 19:28 UTC