agno 2.4.5__py3-none-any.whl → 2.4.6__py3-none-any.whl

{agno-2.4.5.dist-info → agno-2.4.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agno
-Version: 2.4.5
+Version: 2.4.6
 Summary: Agno: a lightweight library for building Multi-Agent Systems
 Author-email: Ashpreet Bedi <ashpreet@agno.com>
 Project-URL: homepage, https://agno.com
@@ -266,7 +266,7 @@ Provides-Extra: excel
 Requires-Dist: openpyxl; extra == "excel"
 Requires-Dist: xlrd; extra == "excel"
 Provides-Extra: markdown
-Requires-Dist: unstructured; extra == "markdown"
+Requires-Dist: unstructured<0.18.31; extra == "markdown"
 Requires-Dist: markdown; extra == "markdown"
 Requires-Dist: aiofiles; extra == "markdown"
 Provides-Extra: chonkie
@@ -445,7 +445,7 @@ Dynamic: license-file
 </div>
 
 <p align="center">
-  Build, run, manage multi-agent systems.
+  Build agents that learn.
 </p>
 
 <div align="center">
@@ -460,68 +460,58 @@ Dynamic: license-file
 
 ## What is Agno?
 
-Agno is a framework, runtime, and control plane for multi-agent systems.
+**A Python SDK for building agents that learn and improve with every interaction.**
 
-| Layer | What it does |
-|-------|--------------|
-| **Framework** | Build agents, teams, and workflows with memory, knowledge, guardrails, and 100+ integrations |
-| **AgentOS Runtime** | Run your system in production with a stateless, secure FastAPI backend |
-| **Control Plane** | Test, monitor, and manage your system using the [AgentOS UI](https://os.agno.com) |
+Most agents are stateless. They reason, respond, forget. Session history helps, but they're exactly as capable on day 1000 as they were on day 1.
 
-## Why Agno?
+Agno agents are different. They remember users across sessions, accumulate knowledge across conversations, and learn from decisions. Insights from one user benefit everyone.
 
-- **Private by design.** AgentOS runs in your cloud. The control plane connects directly to your runtime from your browser. No retention costs, no vendor lock-in, no compliance headaches.
-- **Production-ready on day one.** Pre-built FastAPI runtime with SSE endpoints, ready to deploy.
-- **Fast.** 529× faster instantiation than LangGraph. 24× lower memory. [See benchmarks →](#performance)
+Everything runs in your cloud. Your data never leaves your environment.
 
-## Example
-
-An agent with MCP tools, persistent state, served via FastAPI:
+## Quick Example
 ```python
 from agno.agent import Agent
 from agno.db.sqlite import SqliteDb
-from agno.models.anthropic import Claude
-from agno.os import AgentOS
-from agno.tools.mcp import MCPTools
+from agno.models.openai import OpenAIResponses
 
-agno_agent = Agent(
-    name="Agno Agent",
-    model=Claude(id="claude-sonnet-4-5"),
-    db=SqliteDb(db_file="agno.db"),
-    tools=[MCPTools(transport="streamable-http", url="https://docs.agno.com/mcp")],
-    add_history_to_context=True,
-    markdown=True,
+agent = Agent(
+    model=OpenAIResponses(id="gpt-5.2"),
+    db=SqliteDb(db_file="tmp/agents.db"),
+    learning=True,
 )
-
-agent_os = AgentOS(agents=[agno_agent])
-app = agent_os.get_app()
-
-if __name__ == "__main__":
-    agent_os.serve(app="agno_agent:app", reload=True)
 ```
 
-Run this and connect to the [AgentOS UI](https://os.agno.com):
+One line. Your agent now remembers users, accumulates knowledge, and improves over time.
+
+## Production Stack
 
-https://github.com/user-attachments/assets/feb23db8-15cc-4e88-be7c-01a21a03ebf6
+| Layer | What it does |
+|-------|--------------|
+| **SDK** | Build agents with learning, tools, knowledge, and guardrails |
+| **Runtime** | Run in production using [AgentOS](https://docs.agno.com/agent-os/introduction) |
+| **Control Plane** | Monitor and manage via the [AgentOS UI](https://os.agno.com) |
 
 ## Features
 
+**Learning**
+- User profiles that persist across sessions
+- User memories that accumulate over time
+- Learned knowledge that transfers across users
+- Always or agentic learning modes
+
 **Core**
 - Model-agnostic: OpenAI, Anthropic, Google, local models
 - Type-safe I/O with `input_schema` and `output_schema`
 - Async-first, built for long-running tasks
 - Natively multimodal (text, images, audio, video, files)
 
-**Memory & Knowledge**
-- Persistent storage for session history and state
-- User memory across sessions
+**Knowledge**
 - Agentic RAG with 20+ vector stores, hybrid search, reranking
-- Culture: shared long-term memory across agents
+- Persistent storage for session history and state
 
 **Orchestration**
 - Human-in-the-loop (confirmations, approvals, overrides)
 - Guardrails for validation and security
-- Pre/post hooks for the agent lifecycle
 - First-class MCP and A2A support
 - 100+ built-in toolkits
 
@@ -529,27 +519,12 @@ https://github.com/user-attachments/assets/feb23db8-15cc-4e88-be7c-01a21a03ebf6
 - Ready-to-use FastAPI runtime
 - Integrated control plane UI
 - Evals for accuracy, performance, latency
-- Durable execution for resumable workflows
-- RBAC and per-agent permissions
 
 ## Getting Started
 
-1. Follow the [quickstart guide](https://github.com/agno-agi/agno/tree/main/cookbook/00_quickstart)
-2. Browse the [cookbook](https://github.com/agno-agi/agno/tree/main/cookbook) for real-world examples
-3. Read the [docs](https://docs.agno.com) to go deeper
-
-## Performance
-
-Agent workloads spawn hundreds of instances. Stateless, horizontal scalability isn't optional.
-
-| Metric | Agno | LangGraph | PydanticAI | CrewAI |
-|--------|------|-----------|------------|--------|
-| Instantiation | **3μs** | 1,587μs (529×) | 170μs (57×) | 210μs (70×) |
-| Memory | **6.6 KiB** | 161 KiB (24×) | 29 KiB (4×) | 66 KiB (10×) |
-
-<sub>Apple M4 MacBook Pro, Oct 2025. [Run benchmarks yourself →](https://github.com/agno-agi/agno/tree/main/cookbook/12_evals/performance)</sub>
-
-https://github.com/user-attachments/assets/54b98576-1859-4880-9f2d-15e1a426719d
+1. Follow the [quickstart](https://docs.agno.com/get-started/quickstart)
+2. Browse the [cookbook](https://github.com/agno-agi/agno/tree/main/cookbook)
+3. Read the [docs](https://docs.agno.com)
 
 ## IDE Integration
 
@@ -561,7 +536,7 @@ Also works with VSCode, Windsurf, and similar tools.
 
 ## Contributing
 
-We welcome contributions. See the [contributing guide](https://github.com/agno-agi/agno/blob/v2.0/CONTRIBUTING.md).
+See the [contributing guide](https://github.com/agno-agi/agno/blob/v2.0/CONTRIBUTING.md).
 
 ## Telemetry
 

{agno-2.4.5.dist-info → agno-2.4.6.dist-info}/RECORD

@@ -6,7 +6,7 @@ agno/media.py,sha256=PisfrNwkx2yVOW8p6LXlV237jI06Y6kGjd7wUMk5170,17121
 agno/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 agno/table.py,sha256=9hHFnInNsrj0ZKtWjGDP5c6kbmNdtQvDDYT2j2CZJ6o,198
 agno/agent/__init__.py,sha256=YwN1bvBECSRRQ9mOCZ40eCO4WN5xEPEh0jxWyc83vX4,1190
-agno/agent/agent.py,sha256=3Mr8GtSGyORVFR_xZN9l9waGCX3B4jKnZnC74IpFHl4,563627
+agno/agent/agent.py,sha256=mu6uYbs5G31HFfMEM5qmmD6r7ic5OTRKsiOVgjnYLEg,563740
 agno/agent/remote.py,sha256=3PvPEXLH4QAGVsPnoD0qKDv05swRZpB0gw9bQDCJiLw,19667
 agno/api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 agno/api/agent.py,sha256=fKlQ62E_C9Rjd7Zus3Gs3R1RG-IhzFV-ICpkb6SLqYc,932
@@ -103,7 +103,7 @@ agno/db/sqlite/sqlite.py,sha256=0GQR3FS9UlDxFQs1VF_t5OXhw7FBccfL6CO8JZE7CKY,1765
 agno/db/sqlite/utils.py,sha256=PZp-g4oUf6Iw1kuDAmOpIBtfyg4poKiG_DxXP4EonFI,15721
 agno/db/surrealdb/__init__.py,sha256=C8qp5-Nx9YnSmgKEtGua-sqG_ntCXONBw1qqnNyKPqI,75
 agno/db/surrealdb/metrics.py,sha256=oKDRyjRQ6KR3HaO8zDHQLVMG7-0NDkOFOKX5I7mD5FA,10336
-agno/db/surrealdb/models.py,sha256=BDs5yk1N3G6XGPDz3OYEwuGDkli5MwZHSRCTaFwbK8w,12899
+agno/db/surrealdb/models.py,sha256=2x0HQSifkxVhQg2eJyAnRyBQASY09Rgbx3HACC_XpqQ,12887
 agno/db/surrealdb/queries.py,sha256=s__yJSFIx387IEflcDdti7T5j6H9NX_-zIj13F9CN9s,2051
 agno/db/surrealdb/surrealdb.py,sha256=RpjWArgMSzRE5MCclGVh-0d3T2bYmIIRB-1mJwHhgSo,77128
 agno/db/surrealdb/utils.py,sha256=PcZo_cTy-jI59I-XhzAomRLdV9-m0irtO4C-AYGSghs,5405
@@ -127,20 +127,20 @@ agno/integrations/discord/client.py,sha256=HbXQHHOKKSVFZs0sIJlzoW9bLigbBgOE2kP0I
 agno/knowledge/__init__.py,sha256=MTLKRRh6eqz-w_gw56rqdwV9FoeE9zjX8xYUCCdYg8A,243
 agno/knowledge/content.py,sha256=q2bjcjDhfge_UrQAcygrv5R9ZTk7vozzKnQpatDQWRo,2295
 agno/knowledge/filesystem.py,sha256=zq7xMDkH64x4UM9jcKLIBmPOJcrud2e-lb-pMtaFUSI,15102
-agno/knowledge/knowledge.py,sha256=VtqgwLfYrGBpzXjFmIFMxR5Pi_N5nJHB75fB6wRUCNU,213482
+agno/knowledge/knowledge.py,sha256=Gm37EALvmgTm-PeIqPpWYq-vGkTqtkgOuNHCJvXyqwo,221034
 agno/knowledge/protocol.py,sha256=_hSe0czvTOmu9_NtzsaOxDCnTMYklObxYTphQB3pZ9M,4248
 agno/knowledge/types.py,sha256=4NnkL_h2W-7GQnHW-yIqMNPUCWLzo5qBXF99gfsMe08,773
 agno/knowledge/utils.py,sha256=GJHL1vAOrD6KFEpOiN4Gsgz70fRG0E-jooKIBdfq4zI,9853
 agno/knowledge/chunking/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-agno/knowledge/chunking/agentic.py,sha256=WeQ5ORe_CxsGYg0udOXjvwBo95hnpPZHVpFj-bMzuVU,3168
-agno/knowledge/chunking/code.py,sha256=YLdHL3muYz9MhDqxXPW7MGfqEph4KIZu6_RXPp6KUIc,3569
-agno/knowledge/chunking/document.py,sha256=uCHbPdZR4ILbm9RkpuVu8zw4dPIH0jd1XIRELOixRlI,6454
-agno/knowledge/chunking/fixed.py,sha256=Mz0QgxqVNSaOYPtzihLz6yJdz19zCZ8zLRXIREjgTb8,2371
-agno/knowledge/chunking/markdown.py,sha256=5hiHuvuGJq0UBk7gwnFV5Q84MumXD39UNcY4qlzH1fk,14665
-agno/knowledge/chunking/recursive.py,sha256=PXeq-RF9nJ8alV771q0jEyl1C2QPMVFUTOiJSU0nStw,2357
-agno/knowledge/chunking/row.py,sha256=yFGKMsHd2Ml0fkJLksw8ULUpWXmbSXIQwnwlKHVPP40,1426
-agno/knowledge/chunking/semantic.py,sha256=_PVDvmtJhpoamtpn-kHq54rwLgrbScEky5yqUbBc6JQ,7267
-agno/knowledge/chunking/strategy.py,sha256=Q-HkzcO7YbRY_fbrLz-GRrlplT-F3UeL77R51OoHAGk,7265
+agno/knowledge/chunking/agentic.py,sha256=5gQFL0OCGlYY_c9_1RmcCNSRixFSQOxc6FCDqpS7xTM,3038
+agno/knowledge/chunking/code.py,sha256=mlr5mcaC-5HHfiVvigsBtxcFQ77teFe0ArZx2F-oA10,3572
+agno/knowledge/chunking/document.py,sha256=aEl_n3EOZbSGUaxABgF8Up_QL1hFb1U6SDEhq1jX5N8,5872
+agno/knowledge/chunking/fixed.py,sha256=Boa64-g6xHoMqIeGZwvjkWy0PrkByP00NRwZ2EwXia4,2241
+agno/knowledge/chunking/markdown.py,sha256=AOOaqFLRFnXPMVQ7oingA_zy_LPaerNpPlsx_p3MON4,14179
+agno/knowledge/chunking/recursive.py,sha256=sU-1tlWdeJ5sh2_R3HM0e0rrEFWIV12mqR0TgPx9uZY,2320
+agno/knowledge/chunking/row.py,sha256=k3-kI33n2a4Pe5b66_WUU2DLgw-0Me_s30WKptTjwEk,1477
+agno/knowledge/chunking/semantic.py,sha256=saVCSWjy4ZC44UWsTwUt25FPjemK4oLZgZkPt8JdZpg,7270
+agno/knowledge/chunking/strategy.py,sha256=M8-2i5uXZCEYHswuzLcyAdZL1cgczd7-SAK3-gDp2nE,8102
 agno/knowledge/document/__init__.py,sha256=vxMAu103larPlcpJFG3sBg-sCATf-LZZO_SlOwlEY5E,81
 agno/knowledge/document/base.py,sha256=kvoLSAxc8snrayo_-C6L3HxJVXwZiXd7Maq6VToLgfg,2087
 agno/knowledge/embedder/__init__.py,sha256=RdjcB1qoXuGVLlIkD-hn3B4zs8ycabmCVRmZsG3RhCQ,81
@@ -177,7 +177,7 @@ agno/knowledge/reader/pptx_reader.py,sha256=wk3gSEhxJl36jlbNYCDIyKXjx_sy7r4xiRMa
 agno/knowledge/reader/reader_factory.py,sha256=Sl8KbeRJW1vAbxvK8imnS3Wae5zRsB1zvYN_50DPjO0,17349
 agno/knowledge/reader/s3_reader.py,sha256=F1glvjOpArXPSN8uCdjtnEe-S8HTJ-w7Av34bsFa7-g,3279
 agno/knowledge/reader/tavily_reader.py,sha256=LpKdMb9Z6UpDyNq137voesolGE8uCGjqf398JsQqkgY,7228
-agno/knowledge/reader/text_reader.py,sha256=XLsPqOANI-zRgOp1ueKHD8D14AdP_N1m0ij7Isqi1Fc,4615
+agno/knowledge/reader/text_reader.py,sha256=RNiH-vkAyxR7bTsmmxDwZxmFWnOLYgStvN2XFonoA7o,4607
 agno/knowledge/reader/web_search_reader.py,sha256=bhFJqqlaRxJSQYE1oMlUiImW4DriOH1GwS5MAkBXyHA,12118
 agno/knowledge/reader/website_reader.py,sha256=B64_xoH3Mlfweyj96msTiIW42-aN_OOAfhNkZyWIzmU,19431
 agno/knowledge/reader/wikipedia_reader.py,sha256=C5aMlTwRHRW7FFh2c-JKZLlX5l0PzW6khq5Tu37FwbU,3137
@@ -201,7 +201,7 @@ agno/learn/utils.py,sha256=dUL_oKWHPyUWF5e2muJyNo9W4Y7fwePESI_APQUZ12g,5672
 agno/learn/stores/__init__.py,sha256=c5kC8X5bgZwwRG7epKU5IHdJ-eA9qKcC9G756Xrk2CA,1306
 agno/learn/stores/decision_log.py,sha256=gzGhHKe8YZ3I8C_xuTJzAobUmVQRhrFZSZ5W9pyHxis,37933
 agno/learn/stores/entity_memory.py,sha256=6liU6aoR7C2tI91fgU2BUChtTYlCLM1dH4Ad6Iu7dOY,117078
-agno/learn/stores/learned_knowledge.py,sha256=M86NeGNOWqfdbKMvPCOv11Rigzsmy8wcT1R-rV3NZn8,59297
+agno/learn/stores/learned_knowledge.py,sha256=raSP6T4zEEYRzEtepA4Vi042yqZpWbM7mIcPSFZiFh8,57001
 agno/learn/stores/protocol.py,sha256=SaB76BIXCQMTcEHQDNxUxPnOE2Jx9MMPj3tNsk9_VJk,3324
 agno/learn/stores/session_context.py,sha256=OQFk4OfYmHSNsytTfmm_4DJNTptNoDHWfqGnBHh06zU,48128
 agno/learn/stores/user_memory.py,sha256=le3Vi1hsokopWeMkme9t-ju6GCP1w6z16iJ6Mi6hKdQ,55648
@@ -614,8 +614,8 @@ agno/utils/models/openai_responses.py,sha256=63f2UgDFCzrr6xQITrGtn42UUHQBcZFUUFM
 agno/utils/models/schema_utils.py,sha256=L6TkraMClI471H6xYy7V81lhHR4qQloVKCN0bF4Ajw0,5047
 agno/utils/models/watsonx.py,sha256=fe6jN0hBvOCQurqjS6_9PIwDHt-4kVod9qW236Zs6DU,1496
 agno/utils/print_response/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-agno/utils/print_response/agent.py,sha256=GCC0i-NRYaJzJ2x8B1igVaZ1-hDv_4E1GbvvgiG9xdc,40424
-agno/utils/print_response/team.py,sha256=8uu0mfqnkTEDR1Jo6AYNUWHXtQZPh1apkzVh7MQj5Kc,88763
+agno/utils/print_response/agent.py,sha256=NIDrS4zl6FzFyAgMKBF_6V9A9ELUPwMEev73bfddkrc,40416
+agno/utils/print_response/team.py,sha256=cODB1m0AxVlnLseTt2_dlZl02-rFPtwvp-8TPdD_C4c,88755
 agno/utils/print_response/workflow.py,sha256=pZ7DmJaLx0FWNzXJCKs6gplmA0XAzqxZK1nLQNfePW0,78707
 agno/vectordb/__init__.py,sha256=P0QP9PUC4j2JtWIfYJX7LeC-oiPuh_QsUaOaP1ZY_dI,64
 agno/vectordb/base.py,sha256=0AmdEM2DIE2WdRJIcISEfaQgeYIDpZrMfbnPPI2HrE4,4344
@@ -674,8 +674,8 @@ agno/workflow/step.py,sha256=AgSugOOoWidfZGFtR5PMpgWSBpIeUQB45vmaUDnV7E8,77919
 agno/workflow/steps.py,sha256=p1RdyTZIKDYOPdxU7FbsX_vySWehPWaobge76Q_UDac,26462
 agno/workflow/types.py,sha256=t4304WCKB19QFdV3ixXZICcU8wtBza4EBCIz5Ve6MSQ,18035
 agno/workflow/workflow.py,sha256=S4Iwx3LtpeE_XZ61slYvnM90BdnGhW6Gfax_BKEUG68,218609
-agno-2.4.5.dist-info/licenses/LICENSE,sha256=QwcOLU5TJoTeUhuIXzhdCEEDDvorGiC6-3YTOl4TecE,11356
-agno-2.4.5.dist-info/METADATA,sha256=xNizoFgSLOsXRnOqI_MHZB2dUpXeU6Cq_zshHwsTcYk,22335
-agno-2.4.5.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-agno-2.4.5.dist-info/top_level.txt,sha256=MKyeuVesTyOKIXUhc-d_tPa2Hrh0oTA4LM0izowpx70,5
-agno-2.4.5.dist-info/RECORD,,
+agno-2.4.6.dist-info/licenses/LICENSE,sha256=QwcOLU5TJoTeUhuIXzhdCEEDDvorGiC6-3YTOl4TecE,11356
+agno-2.4.6.dist-info/METADATA,sha256=MmLfiyHxq2B7hn_o0JMPG7Hwnk5Hn_yz8RhixiReUOY,21116
+agno-2.4.6.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+agno-2.4.6.dist-info/top_level.txt,sha256=MKyeuVesTyOKIXUhc-d_tPa2Hrh0oTA4LM0izowpx70,5
+agno-2.4.6.dist-info/RECORD,,