cognee 0.5.4.dev0__tar.gz → 0.5.4.dev2__tar.gz

{cognee-0.5.4.dev0 → cognee-0.5.4.dev2}/.env.template

@@ -286,6 +286,23 @@ LITELLM_LOG="ERROR"
 WEB_SCRAPER_TIMEOUT=15.0
 WEB_SCRAPER_MAX_DELAY=10.0
 
+################################################################################
+#  📡  OpenTelemetry / Tracing Settings
+################################################################################
+# Enable Cognee's built-in OTEL tracing (spans are buffered in-memory by default)
+# COGNEE_TRACING_ENABLED=true
+
+# -- To export traces to an OTLP-compatible backend (Dash0, Grafana, Jaeger, etc.),
+#    set the endpoint and optional auth headers: ---------------------
+# OTEL_EXPORTER_OTLP_ENDPOINT="https://ingress.eu-west.dash0.com:4317"
+# OTEL_EXPORTER_OTLP_HEADERS="Authorization=Bearer <your-token>"
+
+# Override the service name reported in traces (default: "cognee")
+# OTEL_SERVICE_NAME="cognee"
+
+# Add extra resource attributes (useful for Kubernetes, multi-instance deployments)
+# OTEL_RESOURCE_ATTRIBUTES="service.namespace=my-team,service.version=1.0"
+
 ------------------------------- END OF POSSIBLE SETTINGS -------------------------------
 
 

{cognee-0.5.4.dev0 → cognee-0.5.4.dev2}/.gitignore

@@ -1,5 +1,7 @@
 .data
 .env
+.env.example
+cognee/cognee_skills/.env.example
 .local.env
 .prod.env
 cognee/.data/
@@ -204,3 +206,6 @@ SWE-bench_testsample/
 .chromadb_data/
 
 deployment/helm/values-local.yml
+
+# cognee skills generated artifacts
+cognee/skills/graph.html

{cognee-0.5.4.dev0 → cognee-0.5.4.dev2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cognee
-Version: 0.5.4.dev0
+Version: 0.5.4.dev2
 Summary: Cognee - is a library for enriching LLM context with a semantic layer for better understanding and reasoning.
 Project-URL: Homepage, https://www.cognee.ai
 Project-URL: Repository, https://github.com/topoteretes/cognee
@@ -130,6 +130,10 @@ Provides-Extra: mistral
 Requires-Dist: mistral-common<2,>=1.5.2; extra == 'mistral'
 Provides-Extra: monitoring
 Requires-Dist: langfuse<3,>=2.32.0; extra == 'monitoring'
+Requires-Dist: opentelemetry-api<2,>=1.20.0; extra == 'monitoring'
+Requires-Dist: opentelemetry-exporter-otlp-proto-grpc<2,>=1.20.0; extra == 'monitoring'
+Requires-Dist: opentelemetry-exporter-otlp-proto-http<2,>=1.20.0; extra == 'monitoring'
+Requires-Dist: opentelemetry-sdk<2,>=1.20.0; extra == 'monitoring'
 Requires-Dist: sentry-sdk[fastapi]<3,>=2.9.0; extra == 'monitoring'
 Provides-Extra: neo4j
 Requires-Dist: neo4j<6,>=5.28.0; extra == 'neo4j'
@@ -159,6 +163,11 @@ Requires-Dist: lxml<6,>=5; (python_version >= '3.13') and extra == 'scraping'
 Requires-Dist: playwright>=1.9.0; extra == 'scraping'
 Requires-Dist: protego>=0.1; extra == 'scraping'
 Requires-Dist: tavily-python>=0.7.12; extra == 'scraping'
+Provides-Extra: tracing
+Requires-Dist: opentelemetry-api<2,>=1.20.0; extra == 'tracing'
+Requires-Dist: opentelemetry-exporter-otlp-proto-grpc<2,>=1.20.0; extra == 'tracing'
+Requires-Dist: opentelemetry-exporter-otlp-proto-http<2,>=1.20.0; extra == 'tracing'
+Requires-Dist: opentelemetry-sdk<2,>=1.20.0; extra == 'tracing'
 Description-Content-Type: text/markdown
 
 <div align="center">
@@ -171,7 +180,7 @@ Description-Content-Type: text/markdown
   Cognee - Build AI memory with a Knowledge Engine that learns
 
   <p align="center">
-  <a href="https://www.youtube.com/watch?v=1bezuvLwJmw&t=2s">Demo</a>
+  <a href="https://www.youtube.com/watch?v=8hmqS2Y5RVQ&t=13s">Demo</a>
   .
   <a href="https://docs.cognee.ai/">Docs</a>
   .
@@ -195,10 +204,6 @@ Description-Content-Type: text/markdown
   <a href="https://github.com/sponsors/topoteretes"><img src="https://img.shields.io/badge/Sponsor-❤️-ff69b4.svg" alt="Sponsor"></a>
 
 <p>
-  <a href="https://www.producthunt.com/posts/cognee?embed=true&utm_source=badge-top-post-badge&utm_medium=badge&utm_souce=badge-cognee" target="_blank" style="display:inline-block; margin-right:10px;">
-    <img src="https://api.producthunt.com/widgets/embed-image/v1/top-post-badge.svg?post_id=946346&theme=light&period=daily&t=1744472480704" alt="cognee - Memory&#0032;for&#0032;AI&#0032;Agents&#0032;&#0032;in&#0032;5&#0032;lines&#0032;of&#0032;code | Product Hunt" width="250" height="54" />
-  </a>
-
   <a href="https://trendshift.io/repositories/13955" target="_blank" style="display:inline-block;">
     <img src="https://trendshift.io/api/badge/repositories/13955" alt="topoteretes%2Fcognee | Trendshift" width="250" height="55" />
   </a>
@@ -222,7 +227,7 @@ Use our knowledge engine to build personalized and dynamic memory for AI Agents.
 
 
 <div style="text-align: center">
-  <img src="https://raw.githubusercontent.com/topoteretes/cognee/refs/heads/main/assets/cognee_benefits.png" alt="Why cognee?" width="50%" />
+  <img src="https://raw.githubusercontent.com/topoteretes/cognee/refs/heads/main/assets/cognee_benefits.png" alt="Why cognee?" width="80%" />
 </div>
 </div>
 
@@ -231,21 +236,19 @@ Use our knowledge engine to build personalized and dynamic memory for AI Agents.
 
 ## About Cognee
 
-Cognee is an open-source knowledge engine that transforms your raw data into persistent and dynamic AI memory for Agents. It combines vector search, graph databases and self-improvement to make your documents both searchable by meaning and connected by relationships as they change and evolve.
+Cognee is an open-source knowledge engine that lets you ingest data in any format or structure and continuously learns to provide the right context for AI agents. It combines vector search, graph databases and cognitive science approaches to make your documents both searchable by meaning and connected by relationships as they change and evolve.
 
-Cognee offers default knowledge creation and search which we describe bellow. But with Cognee you can build your modular knowledge blocks!
 
 
 :star: _Help us reach more developers and grow the cognee community. Star this repo!_
 
 
-### Cognee Open Source:
+### Why use Cognee:
+
+- Knowledge infrastructure — unified ingestion, graph/vector search, runs locally, ontology grounding, multimodal
+- Persistent and Learning Agents - learn from feedback, context management, cross-agent knowledge sharing
+- Reliable and Trustworthy Agents - agentic user/tenant isolation, traceability, OTEL collector, audit traits
 
-- Interconnects any type of data — including past conversations, files, images, and audio transcriptions
-- Replaces traditional database lookups with a unified knowledge engine built with graphs and vectors
-- Reduces developer effort and infrastructure cost while improving quality and precision
-- Provides Pythonic data pipelines for ingestion from 30+ data sources
-- Offers high customizability through user-defined tasks, modular pipelines, and built-in search endpoints
 
 
 ## Basic Usage & Feature Guide
@@ -281,7 +284,7 @@ To integrate other LLM providers, see our [LLM Provider Documentation](https://d
 
 ### Step 3: Run the Pipeline
 
-Cognee will take your documents, generate a knowledge graph from them and then query the graph based on combined relationships.
+Cognee will take your documents, load them into the knowledge angine and search combined vector/graph relationships.
 
 Now, run a minimal pipeline:
 
@@ -295,12 +298,9 @@ async def main():
     # Add text to cognee
     await cognee.add("Cognee turns documents into AI memory.")
 
-    # Generate the knowledge graph
+    # Add to knowledge engine
     await cognee.cognify()
 
-    # Add memory algorithms to the graph
-    await cognee.memify()
-
     # Query the knowledge graph
     results = await cognee.search("What does Cognee do?")
 
@@ -345,15 +345,7 @@ See Cognee in action:
 
 ### Persistent Agent Memory
 
-[Cognee Memory for LangGraph Agents](https://github.com/user-attachments/assets/e113b628-7212-4a2b-b288-0be39a93a1c3)
-
-### Simple GraphRAG
-
-[Watch Demo](https://github.com/user-attachments/assets/f2186b2e-305a-42b0-9c2d-9f4473f15df8)
-
-### Cognee with Ollama
-
-[Watch Demo](https://github.com/user-attachments/assets/39672858-f774-4136-b957-1e2de67b8981)
+[![Watch Demo](https://img.youtube.com/vi/8hmqS2Y5RVQ/maxresdefault.jpg)](https://www.youtube.com/watch?v=8hmqS2Y5RVQ&t=13s)
 
 
 ## Community & Support

{cognee-0.5.4.dev0 → cognee-0.5.4.dev2}/README.md

@@ -8,7 +8,7 @@
   Cognee - Build AI memory with a Knowledge Engine that learns
 
   <p align="center">
-  <a href="https://www.youtube.com/watch?v=1bezuvLwJmw&t=2s">Demo</a>
+  <a href="https://www.youtube.com/watch?v=8hmqS2Y5RVQ&t=13s">Demo</a>
   .
   <a href="https://docs.cognee.ai/">Docs</a>
   .
@@ -32,10 +32,6 @@
   <a href="https://github.com/sponsors/topoteretes"><img src="https://img.shields.io/badge/Sponsor-❤️-ff69b4.svg" alt="Sponsor"></a>
 
 <p>
-  <a href="https://www.producthunt.com/posts/cognee?embed=true&utm_source=badge-top-post-badge&utm_medium=badge&utm_souce=badge-cognee" target="_blank" style="display:inline-block; margin-right:10px;">
-    <img src="https://api.producthunt.com/widgets/embed-image/v1/top-post-badge.svg?post_id=946346&theme=light&period=daily&t=1744472480704" alt="cognee - Memory&#0032;for&#0032;AI&#0032;Agents&#0032;&#0032;in&#0032;5&#0032;lines&#0032;of&#0032;code | Product Hunt" width="250" height="54" />
-  </a>
-
   <a href="https://trendshift.io/repositories/13955" target="_blank" style="display:inline-block;">
     <img src="https://trendshift.io/api/badge/repositories/13955" alt="topoteretes%2Fcognee | Trendshift" width="250" height="55" />
   </a>
@@ -59,7 +55,7 @@ Use our knowledge engine to build personalized and dynamic memory for AI Agents.
 
 
 <div style="text-align: center">
-  <img src="https://raw.githubusercontent.com/topoteretes/cognee/refs/heads/main/assets/cognee_benefits.png" alt="Why cognee?" width="50%" />
+  <img src="https://raw.githubusercontent.com/topoteretes/cognee/refs/heads/main/assets/cognee_benefits.png" alt="Why cognee?" width="80%" />
 </div>
 </div>
 
@@ -68,21 +64,19 @@ Use our knowledge engine to build personalized and dynamic memory for AI Agents.
 
 ## About Cognee
 
-Cognee is an open-source knowledge engine that transforms your raw data into persistent and dynamic AI memory for Agents. It combines vector search, graph databases and self-improvement to make your documents both searchable by meaning and connected by relationships as they change and evolve.
+Cognee is an open-source knowledge engine that lets you ingest data in any format or structure and continuously learns to provide the right context for AI agents. It combines vector search, graph databases and cognitive science approaches to make your documents both searchable by meaning and connected by relationships as they change and evolve.
 
-Cognee offers default knowledge creation and search which we describe bellow. But with Cognee you can build your modular knowledge blocks!
 
 
 :star: _Help us reach more developers and grow the cognee community. Star this repo!_
 
 
-### Cognee Open Source:
+### Why use Cognee:
+
+- Knowledge infrastructure — unified ingestion, graph/vector search, runs locally, ontology grounding, multimodal
+- Persistent and Learning Agents - learn from feedback, context management, cross-agent knowledge sharing
+- Reliable and Trustworthy Agents - agentic user/tenant isolation, traceability, OTEL collector, audit traits
 
-- Interconnects any type of data — including past conversations, files, images, and audio transcriptions
-- Replaces traditional database lookups with a unified knowledge engine built with graphs and vectors
-- Reduces developer effort and infrastructure cost while improving quality and precision
-- Provides Pythonic data pipelines for ingestion from 30+ data sources
-- Offers high customizability through user-defined tasks, modular pipelines, and built-in search endpoints
 
 
 ## Basic Usage & Feature Guide
@@ -118,7 +112,7 @@ To integrate other LLM providers, see our [LLM Provider Documentation](https://d
 
 ### Step 3: Run the Pipeline
 
-Cognee will take your documents, generate a knowledge graph from them and then query the graph based on combined relationships.
+Cognee will take your documents, load them into the knowledge angine and search combined vector/graph relationships.
 
 Now, run a minimal pipeline:
 
@@ -132,12 +126,9 @@ async def main():
     # Add text to cognee
     await cognee.add("Cognee turns documents into AI memory.")
 
-    # Generate the knowledge graph
+    # Add to knowledge engine
     await cognee.cognify()
 
-    # Add memory algorithms to the graph
-    await cognee.memify()
-
     # Query the knowledge graph
     results = await cognee.search("What does Cognee do?")
 
@@ -182,15 +173,7 @@ See Cognee in action:
 
 ### Persistent Agent Memory
 
-[Cognee Memory for LangGraph Agents](https://github.com/user-attachments/assets/e113b628-7212-4a2b-b288-0be39a93a1c3)
-
-### Simple GraphRAG
-
-[Watch Demo](https://github.com/user-attachments/assets/f2186b2e-305a-42b0-9c2d-9f4473f15df8)
-
-### Cognee with Ollama
-
-[Watch Demo](https://github.com/user-attachments/assets/39672858-f774-4136-b957-1e2de67b8981)
+[![Watch Demo](https://img.youtube.com/vi/8hmqS2Y5RVQ/maxresdefault.jpg)](https://www.youtube.com/watch?v=8hmqS2Y5RVQ&t=13s)
 
 
 ## Community & Support

{cognee-0.5.4.dev0 → cognee-0.5.4.dev2}/cognee/__init__.py

@@ -36,3 +36,15 @@ from .api.v1.session import session
 from .modules import pipelines
 
 from cognee.run_migrations import run_migrations
+
+# Tracing / Observability
+from cognee.modules.observability.trace_context import (
+    enable_tracing,
+    disable_tracing,
+    get_last_trace,
+    get_all_traces,
+    clear_traces,
+)
+
+# Skills routing
+from cognee.cognee_skills.client import skills

{cognee-0.5.4.dev0 → cognee-0.5.4.dev2}/cognee/api/v1/cognify/cognify.py

@@ -31,10 +31,12 @@ from cognee.tasks.temporal_graph.extract_events_and_entities import extract_even
 from cognee.tasks.temporal_graph.extract_knowledge_graph_from_events import (
     extract_knowledge_graph_from_events,
 )
+from cognee.modules.observability import new_span, COGNEE_PIPELINE_NAME, COGNEE_RESULT_SUMMARY
 
 
 logger = get_logger("cognify")
 
+
 update_status_lock = asyncio.Lock()
 
 
@@ -194,55 +196,73 @@ async def cognify(
         - LLM_RATE_LIMIT_ENABLED: Enable rate limiting (default: False)
         - LLM_RATE_LIMIT_REQUESTS: Max requests per interval (default: 60)
     """
-    if config is None:
-        ontology_config = get_ontology_env_config()
-        if (
-            ontology_config.ontology_file_path
-            and ontology_config.ontology_resolver
-            and ontology_config.matching_strategy
-        ):
-            config: Config = {
-                "ontology_config": {
-                    "ontology_resolver": get_ontology_resolver_from_env(**ontology_config.to_dict())
+    with new_span("cognee.api.cognify") as span:
+        span.set_attribute(COGNEE_PIPELINE_NAME, "cognify")
+        if datasets is not None:
+            span.set_attribute("cognee.cognify.datasets", str(datasets))
+
+        if config is None:
+            ontology_config = get_ontology_env_config()
+            if (
+                ontology_config.ontology_file_path
+                and ontology_config.ontology_resolver
+                and ontology_config.matching_strategy
+            ):
+                config: Config = {
+                    "ontology_config": {
+                        "ontology_resolver": get_ontology_resolver_from_env(
+                            **ontology_config.to_dict()
+                        )
+                    }
+                }
+            else:
+                config: Config = {
+                    "ontology_config": {"ontology_resolver": get_default_ontology_resolver()}
                 }
-            }
-        else:
-            config: Config = {
-                "ontology_config": {"ontology_resolver": get_default_ontology_resolver()}
-            }
 
-    if temporal_cognify:
-        tasks = await get_temporal_tasks(
-            user=user, chunker=chunker, chunk_size=chunk_size, chunks_per_batch=chunks_per_batch
-        )
-    else:
-        tasks = await get_default_tasks(
+        if temporal_cognify:
+            tasks = await get_temporal_tasks(
+                user=user,
+                chunker=chunker,
+                chunk_size=chunk_size,
+                chunks_per_batch=chunks_per_batch,
+            )
+        else:
+            tasks = await get_default_tasks(
+                user=user,
+                graph_model=graph_model,
+                chunker=chunker,
+                chunk_size=chunk_size,
+                config=config,
+                custom_prompt=custom_prompt,
+                chunks_per_batch=chunks_per_batch,
+                **kwargs,
+            )
+
+        # By calling get pipeline executor we get a function that will have the run_pipeline run in the background or a function that we will need to wait for
+        pipeline_executor_func = get_pipeline_executor(run_in_background=run_in_background)
+
+        # Run the run_pipeline in the background or blocking based on executor
+        result = await pipeline_executor_func(
+            pipeline=run_pipeline,
+            tasks=tasks,
             user=user,
-            graph_model=graph_model,
-            chunker=chunker,
-            chunk_size=chunk_size,
-            config=config,
-            custom_prompt=custom_prompt,
-            chunks_per_batch=chunks_per_batch,
-            **kwargs,
+            datasets=datasets,
+            vector_db_config=vector_db_config,
+            graph_db_config=graph_db_config,
+            incremental_loading=incremental_loading,
+            use_pipeline_cache=True,
+            pipeline_name="cognify_pipeline",
+            data_per_batch=data_per_batch,
+        )
+
+        dataset_desc = str(datasets) if datasets else "all datasets"
+        span.set_attribute(
+            COGNEE_RESULT_SUMMARY,
+            f"Cognify completed for {dataset_desc}",
         )
 
-    # By calling get pipeline executor we get a function that will have the run_pipeline run in the background or a function that we will need to wait for
-    pipeline_executor_func = get_pipeline_executor(run_in_background=run_in_background)
-
-    # Run the run_pipeline in the background or blocking based on executor
-    return await pipeline_executor_func(
-        pipeline=run_pipeline,
-        tasks=tasks,
-        user=user,
-        datasets=datasets,
-        vector_db_config=vector_db_config,
-        graph_db_config=graph_db_config,
-        incremental_loading=incremental_loading,
-        use_pipeline_cache=True,
-        pipeline_name="cognify_pipeline",
-        data_per_batch=data_per_batch,
-    )
+        return result
 
 
 async def get_default_tasks(  # TODO: Find out a better way to do this (Boris's comment)

{cognee-0.5.4.dev0 → cognee-0.5.4.dev2}/cognee/api/v1/search/search.py

@@ -13,6 +13,13 @@ from cognee.shared.logging_utils import get_logger
 from cognee.infrastructure.databases.exceptions import DatabaseNotCreatedError
 from cognee.exceptions import CogneeValidationError
 from cognee.modules.users.exceptions.exceptions import UserNotFoundError
+from cognee.modules.observability import (
+    new_span,
+    COGNEE_SEARCH_QUERY,
+    COGNEE_SEARCH_TYPE,
+    COGNEE_RESULT_SUMMARY,
+    COGNEE_RESULT_COUNT,
+)
 
 logger = get_logger()
 
@@ -174,47 +181,61 @@ async def search(
         - GRAPH_DATABASE_PROVIDER: Must match what was used during cognify
 
     """
-    # We use lists from now on for datasets
-    if isinstance(datasets, UUID) or isinstance(datasets, str):
-        datasets = [datasets]
-
-    if user is None:
-        try:
-            user = await get_default_user()
-        except (DatabaseNotCreatedError, UserNotFoundError) as error:
-            # Provide a clear, actionable message instead of surfacing low-level stacktraces
-            raise CogneeValidationError(
-                message=(
-                    "Search prerequisites not met: no database/default user found. "
-                    "Initialize Cognee before searching by:\n"
-                    "• running `await cognee.add(...)` followed by `await cognee.cognify()`."
-                ),
-                name="SearchPreconditionError",
-            ) from error
-
-    await set_session_user_context_variable(user)
-
-    # Transform string based datasets to UUID - String based datasets can only be found for current user
-    if datasets is not None and [all(isinstance(dataset, str) for dataset in datasets)]:
-        datasets = await get_authorized_existing_datasets(datasets, "read", user)
-        datasets = [dataset.id for dataset in datasets]
-
-    filtered_search_results = await search_function(
-        query_text=query_text,
-        query_type=query_type,
-        dataset_ids=dataset_ids if dataset_ids else datasets,
-        user=user,
-        system_prompt_path=system_prompt_path,
-        system_prompt=system_prompt,
-        top_k=top_k,
-        node_type=node_type,
-        node_name=node_name,
-        only_context=only_context,
-        session_id=session_id,
-        wide_search_top_k=wide_search_top_k,
-        triplet_distance_penalty=triplet_distance_penalty,
-        verbose=verbose,
-        retriever_specific_config=retriever_specific_config,
-    )
-
-    return filtered_search_results
+    with new_span("cognee.api.search") as span:
+        span.set_attribute(COGNEE_SEARCH_QUERY, query_text[:500])
+        span.set_attribute(COGNEE_SEARCH_TYPE, str(query_type.value))
+        span.set_attribute("cognee.search.top_k", top_k)
+
+        # We use lists from now on for datasets
+        if isinstance(datasets, UUID) or isinstance(datasets, str):
+            datasets = [datasets]
+
+        if user is None:
+            try:
+                user = await get_default_user()
+            except (DatabaseNotCreatedError, UserNotFoundError) as error:
+                # Provide a clear, actionable message instead of surfacing low-level stacktraces
+                raise CogneeValidationError(
+                    message=(
+                        "Search prerequisites not met: no database/default user found. "
+                        "Initialize Cognee before searching by:\n"
+                        "• running `await cognee.add(...)` followed by `await cognee.cognify()`."
+                    ),
+                    name="SearchPreconditionError",
+                ) from error
+
+        await set_session_user_context_variable(user)
+
+        # Transform string based datasets to UUID - String based datasets can only be found for current user
+        if datasets is not None and [all(isinstance(dataset, str) for dataset in datasets)]:
+            datasets = await get_authorized_existing_datasets(datasets, "read", user)
+            datasets = [dataset.id for dataset in datasets]
+            if not datasets:
+                raise DatasetNotFoundError(message="No datasets found.")
+
+        filtered_search_results = await search_function(
+            query_text=query_text,
+            query_type=query_type,
+            dataset_ids=dataset_ids if dataset_ids else datasets,
+            user=user,
+            system_prompt_path=system_prompt_path,
+            system_prompt=system_prompt,
+            top_k=top_k,
+            node_type=node_type,
+            node_name=node_name,
+            only_context=only_context,
+            session_id=session_id,
+            wide_search_top_k=wide_search_top_k,
+            triplet_distance_penalty=triplet_distance_penalty,
+            verbose=verbose,
+            retriever_specific_config=retriever_specific_config,
+        )
+
+        n = len(filtered_search_results) if filtered_search_results else 0
+        span.set_attribute(COGNEE_RESULT_COUNT, n)
+        span.set_attribute(
+            COGNEE_RESULT_SUMMARY,
+            f"Found {n} result(s) via {query_type.value}",
+        )
+
+        return filtered_search_results

{cognee-0.5.4.dev0 → cognee-0.5.4.dev2}/cognee/base_config.py

@@ -47,6 +47,17 @@ class BaseConfig(BaseSettings):
     langfuse_host: Optional[str] = os.getenv("LANGFUSE_HOST")
     default_user_email: Optional[str] = os.getenv("DEFAULT_USER_EMAIL")
     default_user_password: Optional[str] = os.getenv("DEFAULT_USER_PASSWORD")
+
+    # OpenTelemetry / tracing
+    cognee_tracing_enabled: bool = os.getenv("COGNEE_TRACING_ENABLED", "false").lower() in (
+        "true",
+        "1",
+        "yes",
+    )
+    otel_service_name: str = os.getenv("OTEL_SERVICE_NAME", "cognee")
+    otel_exporter_otlp_endpoint: Optional[str] = os.getenv("OTEL_EXPORTER_OTLP_ENDPOINT")
+    otel_exporter_otlp_headers: Optional[str] = os.getenv("OTEL_EXPORTER_OTLP_HEADERS")
+
     model_config = SettingsConfigDict(env_file=".env", extra="allow")
 
     def to_dict(self) -> dict:

{cognee-0.5.4.dev0 → cognee-0.5.4.dev2}/cognee/cli/_cognee.py

@@ -92,6 +92,7 @@ def _discover_commands() -> List[Type[SupportsCliCommand]]:
         ("cognee.cli.commands.cognify_command", "CognifyCommand"),
         ("cognee.cli.commands.delete_command", "DeleteCommand"),
         ("cognee.cli.commands.config_command", "ConfigCommand"),
+        ("cognee.cli.commands.skills_command", "SkillsCommand"),
     ]
 
     for module_path, class_name in command_modules: