| 0ac082ca7c47e4ad… | The CXU lifecycle progresses through DRAFT, ACTIVE, INACTIVE, and VERSIONED states, with an approval workflow required for REGULATED and ABSOLUTE classifications so that controlled content changes follow governance rules. | active | contextual | yes | |
| 0d2dadca12b7e81e… | A CXU is an atomic knowledge unit containing a claim, supporting quotes, and metadata, and it uses a content-addressable ID formed from 1220 plus SHA-256 so that each unit is independently identifiable. | active | contextual | yes | |
| 1ff21ad384ed3e5d… | Lifecycle endpoints expose suggestions, approvals, and lifecycle state transitions so that CXU lifecycle management actions can be performed through the API. | active | contextual | yes | |
| 15d7807447ea91a6… | CORTEX endpoints expose status, agent health, quality scores, knowledge gaps, ambient research, and metrics so that operational and analytical information about agents can be queried. | active | contextual | yes | |
| eaca9c630b8b6216… | The FastAPI API surface exposes routes for CXUs, health checks, context APIs, rank0, sets, cortex, reports, extraction, analysis, and documents so that multiple platform capabilities are accessible over HTTP. | active | contextual | yes | |
| de4e65d11c8bf701… | The `context_engine.kag` package contains the Neo4j graph backend, Qdrant vector backend, and embedding generator so that graph storage, vector storage, and embedding creation are implemented in the KAG layer. | active | contextual | yes | |
| 23243ab63daa7f34… | The `context_engine.services` package contains a query processor with a three-strategy pipeline and a Text2Cypher service so that query execution and graph-query generation are exposed as services. | active | contextual | yes | |
| e0935abff79e5745… | The `context_engine.cortex` package contains CORTEX agents, the message bus, TEMPR memory, a reranker, and a set-relationship registry so that coordinated agent operations and memory functions are grouped together. | active | contextual | yes | |
| 90d4129b967bc15d… | The `context_engine.store` package provides the PostgreSQL storage adapter and hybrid search engine so that persistence and mixed retrieval capabilities are implemented in one module. | active | contextual | yes | |
| 4eb538de9036d0d3… | The `context_engine.extract` package performs LLM extraction through a LiteLLM proxy and Instructor for structured output so that extracted results conform to structured schemas. | active | contextual | yes | |
| 8abedcdcaaf1f0ea… | The `context_engine.core` package contains CXU models, consolidation, and similarity detection so that core knowledge-unit structures and comparison logic are centralized. | active | contextual | yes | |
| d07fbb3a7a594544… | The Context Engine workspace is organized into three Python packages while also listing six named package namespaces so that functionality is separated into modular components. | active | contextual | yes | |
| 5f89fa110a289603… | The extraction pipeline accesses language models through a LiteLLM proxy that is OpenAI-compatible so that model routing is handled through a standardized interface. | active | contextual | yes | |
| bbf3755cf64ceb4d… | NATS provides L2 agent coordination in the Context Engine using nats-py so that agents can communicate through a messaging backend. | active | contextual | yes | |
| 99153f50f1a89478… | Redis serves as the cache backend in the Context Engine using the redis client so that frequently accessed data can be stored outside primary persistence layers. | active | contextual | yes | |
| d8f91592d2772898… | Qdrant provides vector search with 768-dimensional embeddings in the Context Engine using qdrant-client so that semantic retrieval can operate over embedding vectors. | active | contextual | yes | |
| 065576ba290bf640… | Neo4j provides the knowledge graph and TEMPR memory backend in the Context Engine using neo4j-driver so that graph relationships and memory structures are stored in a graph database. | active | contextual | yes | |
| 23ea270645a1ed10… | PostgreSQL serves as the source of truth and provides JSONB and full-text search capabilities in the Context Engine using asyncpg so that canonical structured storage is maintained in the relational backend. | active | contextual | yes | |
| b1dcc6c2af883753… | The Context Engine is a multi-backend Knowledge-Augmented Graph system with five storage and messaging backends so that different persistence, search, cache, and coordination functions are distributed across specialized technologies. | active | contextual | yes | |
| e5bf9d4ca44e4ffa… | Each tenant overlay contains agent definitions, workflow configurations, data connectors, and SQL templates so that platform behavior can be configured per tenant without changing shared platform code. | active | contextual | yes | |
| 8e2122230cfccd2a… | Multi-tenancy is implemented through client overlays stored in the `clients/` directory, including examples such as `clients/jnj/` and `clients/patrick/`, so that tenant-specific configuration is isolated by client. | active | contextual | yes | |
| 829b5ca821b95d97… | The platform uses GitHub Actions for CI/CD and changesets for versioning so that build, delivery, and release version management are standardized. | active | contextual | yes | |
| 322388ba31ab1f72… | The platform uses uv for Python package management and pnpm for TypeScript package management so that dependency handling is separated by language ecosystem. | active | contextual | yes | |
| d73028519c745fa8… | The workspace structure section indicates that the Context Engine workspace is organized into three Python packages. | active | contextual | yes | |
| e8e888be56d68190… | The Context Engine extraction pipeline accesses LLMs through a LiteLLM proxy that presents an OpenAI-compatible interface for model routing. | active | contextual | yes | |
| 591f7970f43d5edb… | Within the Context Engine, NATS provides L2 agent coordination through the nats-py client library. | active | contextual | yes | |
| dcb3b83b017f6522… | Within the Context Engine, Redis is used as the cache backend through the redis client library. | active | contextual | yes | |
| b7a0d0c9b481a593… | Within the Context Engine, Qdrant provides vector search using 768-dimensional embeddings through the qdrant-client. | active | contextual | yes | |
| 8e6623eece168acd… | Within the Context Engine, Neo4j provides the knowledge graph and TEMPR memory capabilities through the neo4j-driver. | active | contextual | yes | |
| e4a7608c8f40591a… | Within the Context Engine, PostgreSQL serves as the source of truth and provides JSONB and full-text search capabilities through asyncpg. | active | contextual | yes | |
| 49af82b9e5dd04b5… | The Context Engine is a multi-backend Knowledge-Augmented Graph system that uses five storage and messaging backends to support its architecture. | active | contextual | yes | |
| ba52368ca76393a1… | Client overlays do not contain platform code; they only configure platform behavior on a per-tenant basis. | active | contextual | yes | |
| c4df3ccbdb2cefb0… | Tenant overlays contain per-tenant agent definitions, workflow configurations, data connectors, and SQL templates to configure platform behavior for each tenant. | active | contextual | yes | |
| 3bc2fe620cc50495… | The platform supports multi-tenancy through client overlays in the clients/ directory, such as clients/jnj/ and clients/patrick/, to separate tenant-specific configuration. | active | contextual | yes | |
| f14ff24125993e35… | The CI/CD toolchain uses GitHub Actions and changesets for versioning so that builds and releases can be automated and versioned consistently. | active | contextual | yes | |
| 8753839d659b149d… | Package management is split between uv for Python dependencies and pnpm for TypeScript dependencies across the platform. | active | contextual | yes | |
| 2d982116203a73a5… | The infrastructure stack uses Docker or Podman, Kubernetes, Helm, and Azure to package, orchestrate, and host the platform. | active | contextual | yes | |
| 60943dfba9de9331… | The observability stack includes the full OpenTelemetry suite, Langfuse, and Prometheus for monitoring and tracing platform behavior. | active | contextual | yes | |
| d8fa6951a0b00aef… | The authentication stack includes Azure AD, OAuth, and JWT implemented with PyJWT and MSAL for identity and token handling. | active | contextual | yes | |
| a3828647aefb10f1… | The frontend technology stack uses Next.js 16, React 19, Vite, and TypeScript for client-side application development. | active | contextual | yes | |
| c5fec82b6e602563… | The backend technology stack consists of FastAPI, Temporal, PostgreSQL, Redis, and a LiteLLM proxy for core platform services. | active | contextual | yes | |
| 01b863d2df9e7d4e… | The output gateway processes results through the pipeline normalize, derive, validate, and persist, and this pipeline is schema-driven through pyrana-packets. | active | contextual | yes | |
| 1ffa937df9d48658… | Agent objectives use {variable} template syntax that is hydrated from the workflow execution context so that runtime values can be injected into agent goals. | active | contextual | yes | |
| ddefa830ce5bb45d… | Agent definitions are stored in YAML configuration files under clients/<client>/backend/config/agents/, while workflow configurations are stored alongside them in config/workflows/. | active | contextual | yes | |
| 20257544878839f5… | A typical platform request flows from the API to PlannerDelegator, then to an ExecutionPlan, then to GenericExecutor, then to execute_action_agent, and finally to PyranaHarness for agent execution. | active | contextual | yes | |
| c81fb3fe82c703a9… | BatchOrchestratorWorkflow processes batches of entities through a workflow so that the same workflow can be applied across multiple items. | active | contextual | yes | |
| ef16bf93b2c2d2f6… | SubagentWorkflow runs spawned child agents that are created through the dispatch-subagent tool so that delegated subagent tasks can execute independently. | active | contextual | yes | |
| d83f1f07c5a1545f… | GenericExecutorWorkflow executes DAG-based plans by dispatching execute_action_agent for each node so that planned work is carried out across the graph. | active | contextual | yes | |
| ee623f7732435ab8… | PlannerDelegatorWorkflow serves as the top-level planner that creates execution plans and delegates work to action agents within the Temporal orchestration layer. | active | contextual | yes | |
| 0e5aa19ac6618d06… | The platform organizes tools into the categories discovery, data fetching, artifacts, context management, completion, delegation, hierarchy, HITL, lifecycle, and context engine to structure agent capabilities. | active | contextual | yes | |