| e4da6a168cf561e2… | The orchestration layer uses Temporal workflows for long-running orchestration so that extended agent processes can be managed reliably over time. | active | contextual | yes | |
| 0a842d935a393596… | Agent orchestration uses PyranaHarness with native LLM tool calling through LiteLLM so that agents can invoke tools directly via the orchestration framework. | active | contextual | yes | |
| edf26bee21a8fb2f… | The knowledge graph design includes a named relationship registry with co-occurrence discovery so that relationships can be standardized and new associations identified. | active | contextual | yes | |
| 3338b1b592e5b156… | The CXU lifecycle includes approval workflows for REGULATED and ABSOLUTE states so that knowledge units can pass through governed approval processes. | active | contextual | yes | |
| ae433484f73f75bb… | The platform uses content-addressable identifiers based on SHA-256 multihash so that stored entities can be referenced by deterministic content-derived IDs. | active | contextual | yes | |
| 45245ca1b89bb59b… | The context engine includes a CORTEX agent layer composed of RetrievalAgent, LearningAgent, and AmbientAgent so that specialized agents support knowledge operations. | active | contextual | yes | |
| b9d613f6c1ff4446… | The knowledge management architecture includes a TEMPR memory system so that memory-related capabilities are part of the context engine design. | active | contextual | yes | |
| 26e955d57d9c5a47… | The retrieval layer uses three strategies—template Cypher, edge-filter Cypher, and Text2Cypher from NLP to Cypher—so that graph retrieval can be performed through multiple query-generation methods. | active | contextual | yes | |
| b540ebffb13f51bf… | The context engine includes a CXU extraction pipeline that proceeds from chunking to parallel lens extraction to deduplication so that knowledge units are systematically derived from source content. | active | contextual | yes | |
| fa980b70f950672b… | The context engine and knowledge management area includes a KAG triple-store architecture that combines PostgreSQL, Neo4j, and Qdrant so that knowledge is managed across multiple storage modalities. | active | contextual | yes | |
| 2a9f59853e47b2e6… | When evaluating AI research papers for PYRANA relevance, reviewers should consider specific technical areas including context engine and knowledge management, agent orchestration, and code execution so that relevance is judged against platform architecture priorities. | active | contextual | yes | |
| d4881e171155aeda… | The demo frontend uses the same @pyrana library architecture and contains the directories client, deploy, docs, frontend, infrastructure, and scripts so that its structure aligns with the broader platform conventions. | active | contextual | yes | |
| f950aef35ddc311a… | The pyrana-demo-2 frontend is a financial analysis demo on branch financial-analysis-demo and includes PLANNING.md for financial analysis components and action items so that demo-specific planning artifacts are available. | active | contextual | yes | |
| 069c81491419f612… | Running pnpm run scaffold:client-page with a route argument creates both a component and a route wrapper so that new client pages can be scaffolded consistently. | active | contextual | yes | |
| 671ef1a63566d15f… | Frontend customization is performed by editing pages and views under frontend/src/client/pages, navigation in frontend/src/client/config/navigation.ts, and optional branding, assets, and client configs so that client-specific UI behavior can be tailored. | active | contextual | yes | |
| 4ca2f78e1e77154d… | The frontend template comes pre-set with app router, layouts and providers, telemetry hooks, auth guard, and environment wiring so that foundational frontend infrastructure is already configured. | active | contextual | yes | |
| 8caeb7dfa029cea1… | The frontend template includes @pyrana libraries for auth, admin, config, SDK, telemetry, types, UI, and charts, with core admin navigation automatically injected so that common platform capabilities are pre-integrated. | active | contextual | yes | |
| 5c71514179d72aef… | Tier 1 execution applies seccomp syscall filtering so that process isolation is strengthened through restricted system call access. | active | contextual | yes | |
| a8c5e107c1fe255d… | Code execution has a 10 second timeout that is configurable per plan so that runaway executions are bounded while allowing plan-based variation. | active | contextual | yes | |
| 06e93912881155b2… | The platform enforces a PID limit of 50 to prevent fork bombs so that process creation abuse is constrained inside execution environments. | active | contextual | yes | |
| 8868ffc0fd0104cf… | Container execution is limited to 128MB of memory and 0.5 CPU cores so that resource consumption remains constrained during runs. | active | contextual | yes | |
| 2992d84403728976… | Containers run with networking disabled so that executed code cannot access external networks from within the sandbox. | active | contextual | yes | |
| b0ff2131a64f1c72… | The GET /metrics API endpoint exposes concurrency metrics including active_executions, max_concurrent, and available_slots so that runtime capacity can be observed externally. | active | contextual | yes | |
| e31f413cda14e063… | The GET /health API endpoint serves Kubernetes probes so that orchestration systems can verify service health. | active | contextual | yes | |
| b0eba08c578b5e27… | The POST /run API endpoint executes Python code and can optionally use workspace, input_files, and output_files for Azure Blob I/O so that code runs can exchange artifacts with blob storage. | active | contextual | yes | |
| 487d9e0a8751818d… | The PoolStateManagerAgent consumes all events and auto-scales every 30 seconds so that pool capacity is adjusted based on observed system activity. | active | contextual | yes | |
| 7e65bfa5a3827b15… | The QueueOptimizerAgent polls queue depths every 1 second and activates backpressure at 80 percent so that queue overload is controlled before saturation occurs. | active | contextual | yes | |
| 9b3dc8833035bb13… | The PerformanceAnalyzerAgent maintains a rolling window of 200 samples per tier and computes P50, P95, and P99 metrics so that execution performance can be analyzed by tier. | active | contextual | yes | |
| e073496629e056f4… | The HealthMonitorAgent checks pool slot health every 10 seconds and restarts slots in FAILED state so that unhealthy execution capacity is automatically recovered. | active | contextual | yes | |
| ae25f657b586910e… | The platform uses five background agents in its agent system so that resource usage, health, performance, queue pressure, and pool state are continuously monitored and managed during code execution. | active | contextual | yes | |
| 877de18fd4f10924… | Azure Blob artifact I/O maps input_files to /input/ and /output/ to output artifacts so that execution can ingest inputs and emit artifacts through blob-backed paths. | active | contextual | yes | |
| 7d4f7ab197ebc608… | Seccomp syscall filtering is used for process isolation in the code execution architecture so that system call access is constrained during execution. | active | contextual | yes | |
| 1057a572fc559bf3… | The execution system supports auto-scaling with utilization-based triggers so that capacity can increase or decrease according to observed utilization. | active | contextual | yes | |
| a2c5e4696559ac68… | Agent coordination uses an in-process asyncio message bus so that background agents can communicate within the execution system. | active | contextual | yes | |
| 9e86c4babbce8d52… | The code execution architecture includes a five-agent background monitoring system covering resource, health, performance, queue, and pool state so that runtime behavior is continuously supervised. | active | contextual | yes | |
| bf4f9df1ba995980… | Code is classified into LIGHT, STANDARD, and HEAVY categories so that execution handling can distinguish workloads by class. | active | contextual | yes | |
| 437817e804ad1fde… | Execution entitlements are plan-based across Bronze, Silver, and Gold tiers so that available execution capabilities can differ by subscription plan. | active | contextual | yes | |
| 02b1272725f3f0c6… | Code execution is organized into three tiers consisting of subprocess for Tier 1, Docker container for Tier 2, and Firecracker VM for Tier 3 so that execution isolation can vary by tier. | active | contextual | yes | |
| 7a189efb2e13eeb0… | The orchestration architecture includes human-in-the-loop capabilities so that human intervention can participate in agent workflows. | active | contextual | yes | |
| a44586b18babde40… | BatchOrchestratorWorkflow is used for entity-batch processing so that orchestration can handle batches of entities as a workflow. | active | contextual | yes | |
| fa46db079aecd288… | The orchestration model supports subagent spawning and hierarchical delegation so that tasks can be decomposed across nested agents. | active | contextual | yes | |
| a4328b26cc809b68… | AgentContext is defined as a persisted belief state in Redis so that agent state can be stored durably in Redis. | active | contextual | yes | |
| 42089c1e982a551f… | LoopAgentState supports checkpointing for pause and resume so that agent execution state can be persisted and continued later. | active | contextual | yes | |
| 3cfb6faadbfdba54… | The platform provides an in-process MCP tool system that uses @tool() decorators so that tools can be registered and invoked within the process. | active | contextual | yes | |
| 752abcce027ce7d0… | Execution plans are DAG-based and flow from PlannerDelegator to GenericExecutor so that orchestration follows a directed execution structure. | active | contextual | yes | |
| 1c6339e28d7cb7bd… | Temporal workflows are used for long-running orchestration so that extended agent processes can be managed over time. | active | contextual | yes | |
| e8c24954e1345d16… | PyranaHarness uses native LLM tool calling through LiteLLM so that agent orchestration can invoke tools via the LLM integration layer. | active | contextual | yes | |
| 7e39d2d3df97765a… | The knowledge system includes a named relationship registry with co-occurrence discovery so that relationships can be cataloged and discovered from co-occurrence patterns. | active | contextual | yes | |
| 5dc253393b9dcb06… | The CXU lifecycle includes approval workflows with REGULATED and ABSOLUTE states so that context units can pass through governed approval categories. | active | contextual | yes | |
| cefc77cf02367a27… | Content-addressable IDs are based on SHA-256 multihash so that content identity can be derived deterministically from the content itself. | active | contextual | yes | |