noesium 0.2.0__py3-none-any.whl → 0.2.1__py3-none-any.whl

noesium-0.2.1.dist-info/METADATA

@@ -0,0 +1,253 @@
+Metadata-Version: 2.4
+Name: noesium
+Version: 0.2.1
+Summary: Towards a cognitive agentic framework
+Author-email: Xiaming Chen <chenxm35@gmail.com>
+Maintainer-email: Xiaming Chen <chenxm35@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/mirasoth/noesium
+Project-URL: Repository, https://github.com/mirasoth/noesium
+Keywords: agents,multi-agent system,cognition,artificial intelligence
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: requests>=2.31.0
+Requires-Dist: aiohttp>=3.12.15
+Requires-Dist: python-dotenv>=1.1.1
+Requires-Dist: colorlog>=6.8.0
+Requires-Dist: typing-extensions>=4.8.0
+Provides-Extra: google
+Requires-Dist: google-genai>=1.5.0; extra == "google"
+Requires-Dist: google-api-python-client>=2.174.0; extra == "google"
+Requires-Dist: google-auth-oauthlib>=1.2.2; extra == "google"
+Requires-Dist: google-auth>=2.40.3; extra == "google"
+Provides-Extra: aliyun
+Requires-Dist: aliyun-python-sdk-core<3.0.0,>=2.13.1; extra == "aliyun"
+Provides-Extra: llm
+Requires-Dist: litellm>=1.0.0; extra == "llm"
+Requires-Dist: openai>=1.0.0; extra == "llm"
+Requires-Dist: instructor>=1.10.0; extra == "llm"
+Provides-Extra: local-llm
+Requires-Dist: ollama>=0.5.3; extra == "local-llm"
+Requires-Dist: llama-cpp-python>=0.3.16; extra == "local-llm"
+Requires-Dist: huggingface-hub>=0.34.4; extra == "local-llm"
+Provides-Extra: ai-providers-all
+Requires-Dist: noesium[aliyun,google,llm,local-llm]; extra == "ai-providers-all"
+Provides-Extra: langchain
+Requires-Dist: langchain-core>=0.3.72; extra == "langchain"
+Requires-Dist: langchain-text-splitters>=0.3.0; extra == "langchain"
+Requires-Dist: langchain-ollama>=0.2.0; extra == "langchain"
+Requires-Dist: langgraph>=0.5.4; extra == "langchain"
+Provides-Extra: agents
+Requires-Dist: noesium[langchain]; extra == "agents"
+Requires-Dist: bubus>=1.5.6; extra == "agents"
+Provides-Extra: postgres
+Requires-Dist: psycopg2-binary>=2.9.0; extra == "postgres"
+Requires-Dist: psycopg2>=2.9.10; extra == "postgres"
+Provides-Extra: weaviate
+Requires-Dist: weaviate-client<5,>=4; extra == "weaviate"
+Requires-Dist: protobuf<6,>=5; extra == "weaviate"
+Provides-Extra: datascience
+Requires-Dist: networkx>=3.5; extra == "datascience"
+Requires-Dist: matplotlib>=3.8.0; extra == "datascience"
+Requires-Dist: pexpect>=4.9.0; extra == "datascience"
+Requires-Dist: ipython>=8.18.0; extra == "datascience"
+Requires-Dist: pandas>=2.0.0; extra == "datascience"
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.0.0; extra == "mcp"
+Provides-Extra: tools
+Requires-Dist: noesium[aliyun,datascience,google,mcp]; extra == "tools"
+Requires-Dist: wizsearch<2.0.0,>=1.0.1; extra == "tools"
+Requires-Dist: arxiv>=2.2.0; extra == "tools"
+Requires-Dist: pillow<12.0,>=10.1.0; extra == "tools"
+Requires-Dist: pymupdf>=1.23.0; extra == "tools"
+Requires-Dist: openpyxl>=3.1.5; extra == "tools"
+Requires-Dist: wikipedia-api>=0.6.0; extra == "tools"
+Requires-Dist: aiofiles>=24.1.0; extra == "tools"
+Provides-Extra: all
+Requires-Dist: noesium[agents,ai-providers-all,postgres,tools,weaviate]; extra == "all"
+Provides-Extra: dev
+Requires-Dist: pytest<9,>=8.2; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=1.1.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: isort>=5.12.0; extra == "dev"
+Requires-Dist: mypy>=1.10.0; extra == "dev"
+Requires-Dist: autoflake>=2.3.1; extra == "dev"
+Requires-Dist: flake8>=7.3.0; extra == "dev"
+Dynamic: license-file
+
+# Noesium
+
+[![CI](https://github.com/mirasoth/noesium/actions/workflows/ci.yml/badge.svg)](https://github.com/mirasoth/noesium/actions/workflows/ci.yml)
+[![PyPI version](https://img.shields.io/pypi/v/noesium.svg)](https://pypi.org/project/noesium/)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/mirasoth/noesium)
+
+Project Noesium is an initiative to develop a computation-driven, cognitive agentic system. This repo contains the foundational abstractions (Agent, Memory, Tool, Goal, Orchestration, and more) along with essential modules such as LLM clients, logging, message buses, model routing, and observability. For the underlying philosophy, refer to my talk on MAS ([link](https://github.com/caesar0301/mas-talk-2508/blob/master/mas-talk-xmingc.pdf)).
+
+## Installation
+
+```bash
+pip install -U noesium
+```
+
+## Core Modules
+
+| Module | Description |
+|--------|-------------|
+| **LLM Integration** (`noesium.core.llm`) | Multi-provider support (OpenAI, OpenRouter, Ollama, LlamaCPP, LiteLLM), dynamic routing, token tracking |
+| **Goal Management** (`noesium.core.goalith`) | LLM-based goal decomposition, DAG-based goal graph, dependency tracking |
+| **Tool Management** (`noesium.core.toolify`) | Tool registry, MCP integration, 17+ built-in toolkits |
+| **Memory** (`noesium.core.memory`) | MemU integration, embedding-based retrieval, multi-category storage |
+| **Vector Store** (`noesium.core.vector_store`) | PGVector and Weaviate support, semantic search |
+| **Message Bus** (`noesium.core.msgbus`) | Event-driven architecture, watchdog patterns |
+| **Routing** (`noesium.core.routing`) | Dynamic complexity-based model selection |
+| **Tracing** (`noesium.core.tracing`) | Token usage monitoring, Opik integration |
+
+## Built-in Agents
+
+- **AskuraAgent** - Conversational agent for collecting semi-structured information via human-in-the-loop workflows
+- **SearchAgent** - Web search with query polishing, multi-engine support, and optional content crawling
+- **DeepResearchAgent** - Iterative research with LLM-powered reflection and citation generation
+- **MemoryAgent** - Memory management with categorization, embedding search, and memory linking
+
+## Quick Start
+
+### LLM Client
+
+```python
+from noesium.core.llm import get_llm_client
+
+# Create client (supports openai, openrouter, ollama, llamacpp)
+client = get_llm_client(provider="openai", api_key="sk-...")
+
+# Chat completion
+response = client.completion([{"role": "user", "content": "Hello!"}])
+
+# Structured output
+from pydantic import BaseModel
+
+class Answer(BaseModel):
+    text: str
+    confidence: float
+
+client = get_llm_client(provider="openai", structured_output=True)
+result = client.structured_completion(messages, Answer)
+```
+
+### Tool Management
+
+```python
+from noesium.core.toolify import BaseToolkit, ToolkitConfig, ToolkitRegistry, register_toolkit
+
+@register_toolkit("calculator")
+class CalculatorToolkit(BaseToolkit):
+    def get_tools_map(self):
+        return {"add": self.add, "multiply": self.multiply}
+
+    def add(self, a: float, b: float) -> float:
+        return a + b
+
+    def multiply(self, a: float, b: float) -> float:
+        return a * b
+
+# Use toolkit
+config = ToolkitConfig(name="calculator")
+calc = ToolkitRegistry.create_toolkit("calculator", config)
+result = calc.call_tool("add", a=5, b=3)
+```
+
+### Goal Decomposition
+
+```python
+from noesium.core.goalith.goalgraph.node import GoalNode
+from noesium.core.goalith.goalgraph.graph import GoalGraph
+from noesium.core.goalith.decomposer import LLMDecomposer
+
+# Create and decompose a goal
+goal = GoalNode(description="Plan a product launch", priority=8.0)
+graph = GoalGraph()
+graph.add_node(goal)
+
+decomposer = LLMDecomposer()
+subgoals = decomposer.decompose(goal, context={"budget": "$50,000"})
+```
+
+### Search Agent
+
+```python
+from noesium.agents.search import SearchAgent, SearchConfig
+
+config = SearchConfig(
+    polish_query=True,
+    search_engines=["tavily"],
+    max_results_per_engine=5
+)
+agent = SearchAgent(config=config)
+results = await agent.search("latest developments in quantum computing")
+```
+
+### Deep Research Agent
+
+```python
+from noesium.agents.deep_research import DeepResearchAgent, DeepResearchConfig
+
+config = DeepResearchConfig(
+    number_of_initial_queries=3,
+    max_research_loops=3,
+    web_search_citation_enabled=True
+)
+agent = DeepResearchAgent(config=config)
+result = await agent.research("What are the implications of AI on healthcare?")
+```
+
+## Environment Variables
+
+```bash
+# LLM Providers
+export NOESIUM_LLM_PROVIDER="openai"
+export OPENAI_API_KEY="sk-..."
+export OPENROUTER_API_KEY="sk-..."
+export OLLAMA_BASE_URL="http://localhost:11434"
+export LLAMACPP_MODEL_PATH="/path/to/model.gguf"
+
+# Vector Store (PostgreSQL)
+export POSTGRES_HOST="localhost"
+export POSTGRES_PORT="5432"
+export POSTGRES_DB="vectordb"
+export POSTGRES_USER="postgres"
+export POSTGRES_PASSWORD="postgres"
+
+# Search Tools
+export SERPER_API_KEY="..."
+export JINA_API_KEY="..."
+```
+
+## Examples
+
+See the `examples/` directory for comprehensive usage examples:
+
+- `examples/agents/` - Agent demos (Askura, Search, DeepResearch)
+- `examples/llm/` - LLM provider examples and token tracking
+- `examples/goals/` - Goal decomposition patterns
+- `examples/memory/` - Memory agent operations
+- `examples/tools/` - Toolkit demonstrations
+- `examples/vector_store/` - PGVector and Weaviate usage
+
+## Documentation
+
+- **Design Specifications**: `specs/` directory contains RFCs for system architecture
+- **Agent Details**: See `AGENTS.md` for comprehensive agent and toolkit documentation
+- **Toolify System**: `noesium/core/toolify/README.md`
+
+## License
+
+MIT License - see [LICENSE](LICENSE) file for details.

{noesium-0.2.0.dist-info → noesium-0.2.1.dist-info}/RECORD

@@ -115,8 +115,8 @@ noesium/toolkits/tabular_data_toolkit.py,sha256=5kofmB5TsLPOYnPCqCvmGrHfxSRBPcNa
 noesium/toolkits/user_interaction_toolkit.py,sha256=_FnSL75eb9f21IlV4KzVXGhda6RRJc3rvYo34Tt51nY,13650
 noesium/toolkits/video_toolkit.py,sha256=zd65drrbB3AGFZGBVieadGZC7sCxemrtYUg1uoQen7E,5858
 noesium/toolkits/wikipedia_toolkit.py,sha256=mQyIuMPGS-vttWWoaV-RmSg5b5MJ4hoLa1H1cUsmst0,15333
-noesium-0.2.0.dist-info/licenses/LICENSE,sha256=uxyIWSLWuSDg9cwA8ehH8LvzOWPM66UGQiOTUQuqTO0,1071
-noesium-0.2.0.dist-info/METADATA,sha256=yGm-sZNdz54NW8bCqOGgwkwq0fqX-wtG4XiwU7dbrKA,17475
-noesium-0.2.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-noesium-0.2.0.dist-info/top_level.txt,sha256=IW36N4DMZNJLo2bt_QMlnw-NZepN5fnqmEKbTbb7Tug,8
-noesium-0.2.0.dist-info/RECORD,,
+noesium-0.2.1.dist-info/licenses/LICENSE,sha256=uxyIWSLWuSDg9cwA8ehH8LvzOWPM66UGQiOTUQuqTO0,1071
+noesium-0.2.1.dist-info/METADATA,sha256=9ezyGOwmVboUet9Vb5ICEo2v58Y-DI5bzTWIxtf6F5o,9579
+noesium-0.2.1.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+noesium-0.2.1.dist-info/top_level.txt,sha256=IW36N4DMZNJLo2bt_QMlnw-NZepN5fnqmEKbTbb7Tug,8
+noesium-0.2.1.dist-info/RECORD,,

noesium-0.2.0.dist-info/METADATA

@@ -1,533 +0,0 @@
-Metadata-Version: 2.4
-Name: noesium
-Version: 0.2.0
-Summary: Towards a cognitive agentic framework
-Author-email: Xiaming Chen <chenxm35@gmail.com>
-Maintainer-email: Xiaming Chen <chenxm35@gmail.com>
-License-Expression: MIT
-Project-URL: Homepage, https://github.com/mirasoth/noesium
-Project-URL: Repository, https://github.com/mirasoth/noesium
-Keywords: agents,multi-agent system,cognition,artificial intelligence
-Classifier: Development Status :: 4 - Beta
-Classifier: Intended Audience :: Developers
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Requires-Python: >=3.11
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: pydantic>=2.0.0
-Requires-Dist: requests>=2.31.0
-Requires-Dist: httpx>=0.28.1
-Requires-Dist: aiohttp>=3.12.15
-Requires-Dist: aiofiles>=24.1.0
-Requires-Dist: anyio>=4.9.0
-Requires-Dist: python-dotenv>=1.1.1
-Requires-Dist: colorlog>=6.8.0
-Requires-Dist: typing-extensions>=4.8.0
-Requires-Dist: deprecated>=1.2.18
-Requires-Dist: psutil>=7.0.0
-Requires-Dist: networkx>=3.5
-Requires-Dist: bubus>=1.5.6
-Provides-Extra: openai
-Requires-Dist: openai>=1.0.0; extra == "openai"
-Requires-Dist: instructor>=1.10.0; extra == "openai"
-Provides-Extra: google
-Requires-Dist: google-genai>=1.5.0; extra == "google"
-Requires-Dist: google-api-python-client>=2.174.0; extra == "google"
-Requires-Dist: google-auth-oauthlib>=1.2.2; extra == "google"
-Requires-Dist: google-auth>=2.40.3; extra == "google"
-Provides-Extra: aliyun
-Requires-Dist: aliyun-python-sdk-core<3.0.0,>=2.13.1; extra == "aliyun"
-Provides-Extra: litellm
-Requires-Dist: litellm>=1.0.0; extra == "litellm"
-Provides-Extra: local-llm
-Requires-Dist: ollama>=0.5.3; extra == "local-llm"
-Requires-Dist: llama-cpp-python>=0.3.16; extra == "local-llm"
-Requires-Dist: huggingface-hub>=0.34.4; extra == "local-llm"
-Provides-Extra: langchain
-Requires-Dist: langchain-core>=0.3.72; extra == "langchain"
-Requires-Dist: langchain-text-splitters>=0.3.0; extra == "langchain"
-Requires-Dist: langchain-ollama>=0.2.0; extra == "langchain"
-Requires-Dist: langgraph>=0.5.4; extra == "langchain"
-Provides-Extra: postgres
-Requires-Dist: psycopg2-binary>=2.9.0; extra == "postgres"
-Requires-Dist: psycopg2>=2.9.10; extra == "postgres"
-Provides-Extra: weaviate
-Requires-Dist: weaviate-client<5,>=4; extra == "weaviate"
-Requires-Dist: protobuf<6,>=5; extra == "weaviate"
-Provides-Extra: datascience
-Requires-Dist: matplotlib>=3.8.0; extra == "datascience"
-Requires-Dist: pexpect>=4.9.0; extra == "datascience"
-Requires-Dist: ipython>=8.18.0; extra == "datascience"
-Requires-Dist: pandas>=2.0.0; extra == "datascience"
-Provides-Extra: mcp
-Requires-Dist: mcp>=1.0.0; extra == "mcp"
-Provides-Extra: tools
-Requires-Dist: noesium[aliyun,datascience,google,mcp]; extra == "tools"
-Requires-Dist: wizsearch<2.0.0,>=1.0.1; extra == "tools"
-Requires-Dist: arxiv>=2.2.0; extra == "tools"
-Requires-Dist: pillow<12.0,>=10.1.0; extra == "tools"
-Requires-Dist: pymupdf>=1.23.0; extra == "tools"
-Requires-Dist: openpyxl>=3.1.5; extra == "tools"
-Requires-Dist: wikipedia-api>=0.6.0; extra == "tools"
-Provides-Extra: all
-Requires-Dist: noesium[google,langchain,local-llm,openai,postgres,tools,weaviate]; extra == "all"
-Provides-Extra: dev
-Requires-Dist: pytest<9,>=8.2; extra == "dev"
-Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
-Requires-Dist: pytest-asyncio>=1.1.0; extra == "dev"
-Requires-Dist: black>=23.0.0; extra == "dev"
-Requires-Dist: isort>=5.12.0; extra == "dev"
-Requires-Dist: mypy>=1.10.0; extra == "dev"
-Requires-Dist: autoflake>=2.3.1; extra == "dev"
-Requires-Dist: flake8>=7.3.0; extra == "dev"
-Dynamic: license-file
-
-# Noesium-core
-
-[![CI](https://github.com/mirasoth/noesium/actions/workflows/ci.yml/badge.svg)](https://github.com/mirasoth/noesium/actions/workflows/ci.yml)
-[![PyPI version](https://img.shields.io/pypi/v/noesium.svg)](https://pypi.org/project/noesium/)
-[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/mirasoth/noesium)
-
-Project Noesium is an initiative to develop a computation-driven, cognitive agentic system. This repo contains the foundational abstractions (Agent, Memory, Tool, Goal, Orchestration, and more) along with essential modules such as LLM clients, logging, message buses, model routing, and observability. For the underlying philosophy, refer to my talk on MAS ([link](https://github.com/caesar0301/mas-talk-2508/blob/master/mas-talk-xmingc.pdf)).
-
-## Installation
-
-```bash
-pip install -U noesium
-```
-
-## Core Modules
-
-Noesium offers a comprehensive set of modules for creating intelligent agent-based applications:
-
-### LLM Integration & Management (`noesium.core.llm`)
-- **Multi-model support**: OpenAI, OpenRouter, Ollama, LlamaCPP, and LiteLLM
-- **Advanced routing**: Dynamic complexity-based and self-assessment routing strategies
-- **Tracing & monitoring**: Built-in token tracking and Opik tracing integration
-- **Extensible architecture**: Easy to add new LLM providers
-
-### Goal Management & Planning (`noesium.core.goalith`) - *In Development*
-- **Goal decomposition**: LLM-based, callable, and simple goal decomposition strategies
-- **Graph-based structure**: DAG-based goal management with dependencies
-- **Node management**: Goal, subgoal, and task node creation and tracking
-- **Conflict detection**: Framework for automated goal conflict identification (planned)
-- **Replanning**: Dynamic goal replanning capabilities (planned)
-
-### Tool Management (`noesium.core.toolify`)
-- **Tool registry**: Centralized tool registration and management
-- **MCP integration**: Model Context Protocol support for tool discovery
-- **Execution engine**: Robust tool execution with error handling
-- **Toolkit system**: Organized tool collections and configurations
-
-### Memory Management (`noesium.core.memory`)
-- **MemU integration**: Advanced memory agent with categorization
-- **Embedding support**: Vector-based memory retrieval and linking
-- **Multi-category storage**: Activity, event, and profile memory types
-- **Memory linking**: Automatic relationship discovery between memories
-
-### Vector Storage (`noesium.core.vector_store`)
-- **PGVector support**: PostgreSQL with pgvector extension
-- **Weaviate integration**: Cloud-native vector database
-- **Semantic search**: Embedding-based document retrieval
-- **Flexible indexing**: HNSW and DiskANN indexing strategies
-
-### Message Bus (`noesium.core.msgbus`)
-- **Event-driven architecture**: Inter-component communication
-- **Watchdog patterns**: Monitoring and reactive behaviors
-- **Flexible routing**: Message filtering and delivery
-
-### Routing & Tracing (`noesium.core.routing`, `noesium.core.tracing`)
-- **Smart routing**: Dynamic model selection based on complexity
-- **Token tracking**: Comprehensive usage monitoring
-- **Opik integration**: Production-ready observability
-- **LangGraph hooks**: Workflow tracing and debugging
-
-## Quick Start
-
-### 1. LLM Client Usage
-
-```python
-from noesium.core.llm import get_llm_client
-
-# OpenAI/OpenRouter providers
-client = get_llm_client(provider="openai", api_key="sk-...")
-client = get_llm_client(provider="openrouter", api_key="sk-...")
-
-# Local providers
-client = get_llm_client(provider="ollama", base_url="http://localhost:11434")
-client = get_llm_client(provider="llamacpp", model_path="/path/to/model.gguf")
-
-# Basic chat completion
-response = client.completion([
-    {"role": "user", "content": "Hello!"}
-])
-
-# Structured output (requires structured_output=True)
-from pydantic import BaseModel
-
-class Response(BaseModel):
-    answer: str
-    confidence: float
-
-client = get_llm_client(provider="openai", structured_output=True)
-result = client.structured_completion(messages, Response)
-```
-
-### 2. Goal Management with Goalith
-
-**Note**: The Goalith goal management system is currently under development. The core components are available but the full service integration is not yet complete.
-
-```python
-# Basic goal node creation and management
-from noesium.core.goalith.goalgraph.node import GoalNode, NodeStatus
-from noesium.core.goalith.goalgraph.graph import GoalGraph
-from noesium.core.goalith.decomposer import LLMDecomposer
-
-# Create a goal node
-goal_node = GoalNode(
-    description="Plan and execute a product launch",
-    priority=8.0,
-    context={
-        "budget": "$50,000",
-        "timeline": "3 months",
-        "target_audience": "young professionals"
-    },
-    tags=["product", "launch", "marketing"]
-)
-
-# Create goal graph for management
-graph = GoalGraph()
-graph.add_node(goal_node)
-
-# Use LLM decomposer directly
-decomposer = LLMDecomposer()
-subgoals = decomposer.decompose(goal_node, context={
-    "team_size": "5 people",
-    "experience_level": "intermediate"
-})
-
-print(f"Goal: {goal_node.description}")
-print(f"Status: {goal_node.status}")
-print(f"Generated {len(subgoals)} subgoals")
-```
-
-### 3. Memory Management
-
-```python
-from noesium.core.memory.memu import MemoryAgent
-
-# Initialize memory agent
-memory_agent = MemoryAgent(
-    agent_id="my_agent",
-    user_id="user123",
-    memory_dir="/tmp/memory_storage",
-    enable_embeddings=True
-)
-
-# Add activity memory
-activity_content = """
-USER: Hi, I'm Sarah and I work as a software engineer.
-ASSISTANT: Nice to meet you Sarah! What kind of projects do you work on?
-USER: I mainly work on web applications using Python and React.
-"""
-
-result = memory_agent.call_function(
-    "add_activity_memory",
-    {
-        "character_name": "Sarah",
-        "content": activity_content
-    }
-)
-
-# Generate memory suggestions
-if result.get("success"):
-    memory_items = result.get("memory_items", [])
-    suggestions = memory_agent.call_function(
-        "generate_memory_suggestions",
-        {
-            "character_name": "Sarah",
-            "new_memory_items": memory_items
-        }
-    )
-```
-
-### 4. Vector Store Operations
-
-```python
-from noesium.core.vector_store import PGVectorStore
-from noesium.core.llm import get_llm_client
-
-# Initialize vector store
-vector_store = PGVectorStore(
-    collection_name="my_documents",
-    embedding_model_dims=768,
-    dbname="vectordb",
-    user="postgres",
-    password="postgres",
-    host="localhost",
-    port=5432
-)
-
-# Initialize embedding client
-embed_client = get_llm_client(provider="ollama", embed_model="nomic-embed-text")
-
-# Prepare documents
-documents = [
-    {
-        "id": "doc1",
-        "content": "Machine learning is a subset of AI...",
-        "metadata": {"category": "AI", "type": "definition"}
-    }
-]
-
-# Generate embeddings and store
-vectors = []
-payloads = []
-ids = []
-
-for doc in documents:
-    embedding = embed_client.embed(doc["content"])
-    vectors.append(embedding)
-    payloads.append(doc["metadata"])
-    ids.append(doc["id"])
-
-# Insert into vector store
-vector_store.insert(vectors=vectors, payloads=payloads, ids=ids)
-
-# Search
-query = "What is artificial intelligence?"
-query_embedding = embed_client.embed(query)
-results = vector_store.search(query=query, vectors=query_embedding, limit=5)
-```
-
-### 5. Tool Management
-
-```python
-from noesium.core.toolify import BaseToolkit, ToolkitConfig, ToolkitRegistry, register_toolkit
-from typing import Dict, Callable
-
-# Create a custom toolkit using decorator
-@register_toolkit("calculator")
-class CalculatorToolkit(BaseToolkit):
-    def get_tools_map(self) -> Dict[str, Callable]:
-        return {
-            "add": self.add,
-            "multiply": self.multiply
-        }
-
-    def add(self, a: float, b: float) -> float:
-        """Add two numbers."""
-        return a + b
-
-    def multiply(self, a: float, b: float) -> float:
-        """Multiply two numbers."""
-        return a * b
-
-# Alternative: Manual registration
-config = ToolkitConfig(name="calculator", description="Basic math operations")
-ToolkitRegistry.register("calculator", CalculatorToolkit)
-
-# Create and use toolkit
-calculator = ToolkitRegistry.create_toolkit("calculator", config)
-result = calculator.call_tool("add", a=5, b=3)
-print(f"5 + 3 = {result}")
-```
-
-### 6. Message Bus and Events
-
-```python
-from noesium.core.msgbus import EventBus, BaseEvent, BaseWatchdog
-
-# Define custom event
-class TaskCompleted(BaseEvent):
-    def __init__(self, task_id: str, result: str):
-        super().__init__()
-        self.task_id = task_id
-        self.result = result
-
-# Create event bus
-bus = EventBus()
-
-# Define watchdog
-class TaskWatchdog(BaseWatchdog):
-    def handle_event(self, event: BaseEvent):
-        if isinstance(event, TaskCompleted):
-            print(f"Task {event.task_id} completed with result: {event.result}")
-
-# Register watchdog and publish event
-watchdog = TaskWatchdog()
-bus.register_watchdog(watchdog)
-bus.publish(TaskCompleted("task_1", "success"))
-```
-
-### 7. Token Tracking and Tracing
-
-```python
-from noesium.core.tracing import get_token_tracker
-from noesium.core.llm import get_llm_client
-
-# Initialize client and tracker
-client = get_llm_client(provider="openai")
-tracker = get_token_tracker()
-
-# Reset tracker
-tracker.reset()
-
-# Make LLM calls (automatically tracked)
-response1 = client.completion([{"role": "user", "content": "Hello"}])
-response2 = client.completion([{"role": "user", "content": "How are you?"}])
-
-# Get usage statistics
-stats = tracker.get_stats()
-print(f"Total tokens: {stats['total_tokens']}")
-print(f"Total calls: {stats['total_calls']}")
-print(f"Average tokens per call: {stats.get('avg_tokens_per_call', 0)}")
-```
-
-## Environment Variables
-
-Set these environment variables for different providers:
-
-```bash
-# Default LLM provider
-export NOESIUM_LLM_PROVIDER="openai"
-
-# OpenAI
-export OPENAI_API_KEY="sk-..."
-
-# OpenRouter
-export OPENROUTER_API_KEY="sk-..."
-
-# LlamaCPP
-export LLAMACPP_MODEL_PATH="/path/to/model.gguf"
-
-# Ollama
-export OLLAMA_BASE_URL="http://localhost:11434"
-
-# PostgreSQL (for vector store)
-export POSTGRES_HOST="localhost"
-export POSTGRES_PORT="5432"
-export POSTGRES_DB="vectordb"
-export POSTGRES_USER="postgres"
-export POSTGRES_PASSWORD="postgres"
-```
-
-## Advanced Usage
-
-### Custom Goal Decomposer
-
-```python
-from noesium.core.goalith.decomposer.base import GoalDecomposer
-from noesium.core.goalith.goalgraph.node import GoalNode
-from typing import List, Dict, Any, Optional
-import copy
-
-class CustomDecomposer(GoalDecomposer):
-    @property
-    def name(self) -> str:
-        return "custom_decomposer"
-
-    def decompose(self, goal_node: GoalNode, context: Optional[Dict[str, Any]] = None) -> List[GoalNode]:
-        # Custom decomposition logic
-        subtasks = [
-            "Research requirements",
-            "Design solution",
-            "Implement features",
-            "Test and deploy"
-        ]
-
-        nodes = []
-        for i, subtask in enumerate(subtasks):
-            # Deep copy context to avoid shared references
-            context_copy = copy.deepcopy(goal_node.context) if goal_node.context else {}
-
-            node = GoalNode(
-                description=subtask,
-                parent=goal_node.id,
-                priority=goal_node.priority - i * 0.1,
-                context=context_copy,
-                tags=goal_node.tags.copy() if goal_node.tags else [],
-                decomposer_name=self.name
-            )
-            nodes.append(node)
-
-        return nodes
-
-# Use the decomposer directly
-custom_decomposer = CustomDecomposer()
-goal_node = GoalNode(description="Build a web application")
-subgoals = custom_decomposer.decompose(goal_node)
-```
-
-### LLM Routing Strategies
-
-```python
-from noesium.core.routing import ModelRouter, DynamicComplexityStrategy
-from noesium.core.llm import get_llm_client
-
-# Create a lite client for complexity assessment
-lite_client = get_llm_client(provider="ollama", chat_model="llama3.2:1b")
-
-# Create router with dynamic complexity strategy
-router = ModelRouter(
-    strategy="dynamic_complexity",
-    lite_client=lite_client,
-    strategy_config={
-        "complexity_threshold_low": 0.3,
-        "complexity_threshold_high": 0.7
-    }
-)
-
-# Route queries to get tier recommendations
-simple_query = "What is 2+2?"
-result = router.route(simple_query)
-print(f"Query: {simple_query}")
-print(f"Recommended tier: {result.tier}")  # Likely ModelTier.LITE
-print(f"Confidence: {result.confidence}")
-
-complex_query = "Explain quantum computing and its applications"
-result = router.route(complex_query)
-print(f"Query: {complex_query}")
-print(f"Recommended tier: {result.tier}")  # Likely ModelTier.POWER
-print(f"Confidence: {result.confidence}")
-
-# Get recommended model configuration
-routing_result, model_config = router.route_and_configure(complex_query)
-print(f"Recommended config: {model_config}")
-```
-
-## Examples
-
-Check the `examples/` directory for comprehensive usage examples:
-
-- **LLM Examples**: `examples/llm/` - OpenAI, Ollama, LlamaCPP, token tracking
-- **Goal Management**: `examples/goals/` - Goal decomposition and planning
-- **Memory Examples**: `examples/memory/` - Memory agent operations
-- **Vector Store**: `examples/vector_store/` - PGVector and Weaviate usage
-- **Message Bus**: `examples/msgbus/` - Event-driven patterns
-- **Tools**: Various toolkit implementations
-
-## Development
-
-```bash
-# Install development dependencies
-make install
-
-# Run tests
-make test
-
-# Run specific test categories
-make test-unit          # Unit tests only
-make test-integration   # Integration tests only
-
-# Format code
-make format
-```
-
-## License
-
-MIT License - see [LICENSE](LICENSE) file for details.