Filtered Trace Search And Analytics With Custom View Creation

via “web ui with virtualized table rendering and real-time filtering”

Open-source LLM observability — tracing, prompt management, evaluation, cost tracking, self-hosted.

Unique: Virtualized table rendering using React windowing libraries enables rendering 100K+ traces without performance degradation, with debounced filtering to reduce API calls. Timeline visualization is built with custom SVG rendering for efficient layout of nested observations.

vs others: More responsive than non-virtualized UIs because only visible rows are rendered, reducing DOM size and improving scroll performance. Real-time filtering with debouncing balances responsiveness with API efficiency, whereas non-debounced filtering would cause excessive API calls.

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

Unique: Virtualized table rendering with complex filter combinations and saved views, enabling efficient exploration of 10k+ traces without performance degradation or manual query writing

vs others: Supports complex filter combinations (vs simple search in competitors), with virtualized rendering enabling 10k+ trace display vs competitors limiting to 1k-5k traces

via “trace querying and filtering via graphql api”

AI Observability & Evaluation

Unique: Uses Strawberry GraphQL framework with type-safe schema generation from Python dataclasses, enabling automatic schema validation and IDE autocomplete for query construction. Translates GraphQL queries directly to optimized SQL rather than loading full datasets into memory.

vs others: More flexible than REST APIs for complex filtering scenarios and more efficient than full-dataset retrieval; GraphQL schema is self-documenting and supports introspection for dynamic client generation.

via “trace filtering and aggregation by custom attributes”

** - Query and analyze your [Opik](https://github.com/comet-ml/opik) logs, traces, prompts and all other telemtry data from your LLMs in natural language.

Unique: Supports arbitrary custom attributes defined by users at trace time, rather than enforcing a fixed schema. Uses Opik's flexible metadata storage to enable ad-hoc dimensional analysis without schema migrations.

vs others: More flexible than pre-built dashboards because it supports user-defined dimensions; faster than post-processing trace exports because aggregation happens at query time in the backend

via “batch trace filtering and search”