Overview

Laminar was founded by infrastructure engineers from Palantir, Amazon, and Bloomberg during Y Combinator's S24 batch to address the debugging challenges of autonomous AI agents. The founders built the engine in Rust around OpenTelemetry standards to keep high-throughput trace ingestion efficient on private hardware. That origin yields a self-hosted platform that tracks non-deterministic agent executions, tool calls, and cost metrics without exporting internal prompts to third-party clouds.

Why Laminar instead of LangChain

LangChain centers its commercial telemetry around LangSmith, a proprietary SaaS platform that records execution steps, manages evaluation datasets, and meters billing by trace volume. For teams deploying agents across diverse frameworks—or making direct API calls—relying on LangSmith creates vendor lock-in and exports prompts outside internal infrastructure. Laminar replaces that hosted dependency with an open-source, self-hosted telemetry engine built on OpenTelemetry standards. Its SDK instruments multiple runtimes, capturing execution trees from LangChain, Vercel AI SDK, Browser Use, Stagehand, and direct model calls through one interface.

The operational divide centers on framework neutrality. While LangSmith favors native LangChain components, Laminar treats every agent architecture equally through standardized trace spans, ClickHouse storage, and Model Context Protocol endpoints. Engineering squads can inspect reasoning graphs, configure Slack alerts for runaway loops, and run CI evaluations without paying SaaS seat fees or adopting LangChain's wrappers. However, Laminar covers only observability and evaluations; teams still use LangChain or alternative libraries to structure prompts and dispatch tools.

What it does well

OpenTelemetry auto-instrumentation capturing trace spans from OpenAI, Anthropic, Gemini, Vercel AI SDK, and LangChain with minimal code changes.
Rust telemetry engine applying twenty-fold compression to minimize storage footprints and network ingestion overhead.
Model Context Protocol server and CLI letting coding agents query execution traces and spans using raw SQL.
Natural-language signal tracking that monitors live agent runs and alerts Slack when an agent stalls or loops.
Offline evaluation framework and CLI tool that run regression tests against versioned datasets in CI/CD pipelines.

cat > .env <<EOF POSTGRES_USER=postgres POSTGRES_PASSWORD=$(openssl rand -hex 12) POSTGRES_DB=postgres CLICKHOUSE_USER=ch_user CLICKHOUSE_PASSWORD=$(openssl rand -hex 12) AEAD_SECRET_KEY=$(openssl rand -hex 32) NEXTAUTH_SECRET=$(openssl rand -hex 16) SHARED_SECRET_TOKEN=$(openssl rand -hex 16) NEXTAUTH_URL=http://localhost:5667 NEXT_PUBLIC_URL=http://localhost:5667 EOF

services: postgres: image: postgres:16-alpine environment: POSTGRES_USER: ${POSTGRES_USER} POSTGRES_PASSWORD: ${POSTGRES_PASSWORD} POSTGRES_DB: ${POSTGRES_DB} volumes: - postgres-data:/var/lib/postgresql/data restart: always healthcheck: test: ["CMD-SHELL", "pg_isready -U $${POSTGRES_USER} -d $${POSTGRES_DB}"] interval: 3s timeout: 5s retries: 10 clickhouse: image: clickhouse/clickhouse-server:26.5 environment: CLICKHOUSE_USER: ${CLICKHOUSE_USER} CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD} volumes: - clickhouse-data:/var/lib/clickhouse/ - clickhouse-logs:/var/log/clickhouse-server/ configs: - source: clickhouse_profiles_config target: /etc/clickhouse-server/users.d/lmnr.xml - source: clickhouse_server_config target: /etc/clickhouse-server/config.d/lmnr.xml ulimits: nofile: soft: 262144 hard: 262144 restart: always healthcheck: test: ["CMD-SHELL", "wget --no-verbose --tries=1 -O - http://127.0.0.1:8123/ping || exit 1"] interval: 5s timeout: 5s retries: 10 quickwit: image: quickwit/quickwit:v0.9.1 environment: QW_DATA_DIR: /quickwit/qwdata command: ["run"] volumes: - quickwit-data:/quickwit/qwdata restart: always healthcheck: test: ["CMD", "bash", "-c", "exec 3<>/dev/tcp/127.0.0.1/7280 && printf 'GET /health/livez HTTP/1.0\\r\\n\\r\\n' >&3 && grep -q '200 OK' <&3"] interval: 5s timeout: 5s retries: 10 frontend: image: ghcr.io/lmnr-ai/frontend:v0.3.3 ports: - "127.0.0.1:5667:5667" depends_on: postgres: condition: service_healthy clickhouse: condition: service_healthy quickwit: condition: service_healthy app-server: condition: service_healthy environment: DATABASE_URL: postgres://${POSTGRES_USER}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB} PORT: 5667 BACKEND_URL: http://app-server:8000 BACKEND_RT_URL: http://app-server:8002 SHARED_SECRET_TOKEN: ${SHARED_SECRET_TOKEN} NEXTAUTH_URL: ${NEXTAUTH_URL} NEXTAUTH_SECRET: ${NEXTAUTH_SECRET} NEXT_PUBLIC_URL: ${NEXT_PUBLIC_URL} ENVIRONMENT: LITE LAMINAR_TELEMETRY_DISABLED: "true" CLICKHOUSE_URL: http://clickhouse:8123 CLICKHOUSE_USER: ${CLICKHOUSE_USER} CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD} CLICKHOUSE_RO_USER: ${CLICKHOUSE_USER} CLICKHOUSE_RO_PASSWORD: ${CLICKHOUSE_PASSWORD} AEAD_SECRET_KEY: ${AEAD_SECRET_KEY} QUICKWIT_SEARCH_URL: http://quickwit:7280 restart: always healthcheck: test: ["CMD-SHELL", "wget -q -O - http://127.0.0.1:5667/sign-in | grep -q 'Laminar' || exit 1"] interval: 5s timeout: 5s retries: 20 start_period: 20s app-server: image: ghcr.io/lmnr-ai/app-server:v0.3.3 ports: - "127.0.0.1:8000:8000" - "127.0.0.1:8001:8001" depends_on: postgres: condition: service_healthy clickhouse: condition: service_healthy quickwit: condition: service_healthy environment: PORT: 8000 GRPC_PORT: 8001 DATABASE_URL: postgres://${POSTGRES_USER}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB} SHARED_SECRET_TOKEN: ${SHARED_SECRET_TOKEN} CLICKHOUSE_URL: http://clickhouse:8123 CLICKHOUSE_USER: ${CLICKHOUSE_USER} CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD} CLICKHOUSE_RO_USER: ${CLICKHOUSE_USER} CLICKHOUSE_RO_PASSWORD: ${CLICKHOUSE_PASSWORD} ENVIRONMENT: LITE AEAD_SECRET_KEY: ${AEAD_SECRET_KEY} QUICKWIT_SEARCH_URL: http://quickwit:7280 QUICKWIT_INGEST_URL: http://quickwit:7281 QUICKWIT_SPANS_INDEX_ID: spans_v2 restart: always healthcheck: test: ["CMD", "bash", "-c", "exec 3<>/dev/tcp/127.0.0.1/8000 && printf 'GET /health HTTP/1.0\\r\\n\\r\\n' >&3 && grep -q '200 OK' <&3"] interval: 5s timeout: 5s retries: 10 configs: clickhouse_profiles_config: content: | <?xml version="1.0"?> <clickhouse> <profiles> <default> <date_time_input_format replace="replace">best_effort</date_time_input_format> </default> </profiles> </clickhouse> clickhouse_server_config: content: | <?xml version="1.0"?> <clickhouse> <trace_log remove="1"/> <text_log remove="1"/> <part_log remove="1"/> <metric_log remove="1"/> <asynchronous_metric_log remove="1"/> <background_schedule_pool_log remove="1"/> <query_metric_log remove="1"/> <query_thread_log remove="1"/> <query_views_log remove="1"/> <session_log remove="1"/> <crash_log remove="1"/> <opentelemetry_span_log remove="1"/> <zookeeper_log remove="1"/> <blob_storage_log remove="1"/> <processors_profile_log remove="1"/> <asynchronous_insert_log remove="1"/> <query_log> <ttl>event_date + INTERVAL 3 DAY DELETE</ttl> </query_log> <error_log> <ttl>event_date + INTERVAL 3 DAY DELETE</ttl> </error_log> </clickhouse> volumes: postgres-data: clickhouse-data: clickhouse-logs: quickwit-data:

postgres-1 | 2026-11-03T07:48:00.011012376Z 2026-11-03 07:48:00.010 UTC [40] LOG: background worker "logical replication launcher" (PID 46) exited with exit code 1 postgres-1 | 2026-11-03T07:48:00.011059584Z 2026-11-03 07:48:00.011 UTC [41] LOG: shutting down postgres-1 | 2026-11-03T07:48:00.012873584Z 2026-11-03 07:48:00.012 UTC [41] LOG: checkpoint starting: shutdown immediate postgres-1 | 2026-11-03T07:48:00.016367501Z 2026-11-03 07:48:00.016 UTC [41] LOG: checkpoint complete: wrote 3 buffers (0.0%); 0 WAL file(s) added, 0 removed, 0 recycled; write=0.001 s, sync=0.001 s, total=0.006 s; sync files=2, longest=0.001 s, average=0.001 s; distance=0 kB, estimate=0 kB; lsn=0/14F7160, redo lsn=0/14F7160 postgres-1 | 2026-11-03T07:48:00.017742084Z 2026-11-03 07:48:00.017 UTC [40] LOG: database system is shut down postgres-1 | 2026-11-03T07:48:00.107598668Z done postgres-1 | 2026-11-03T07:48:00.107635960Z server stopped postgres-1 | 2026-11-03T07:48:00.108125168Z postgres-1 | 2026-11-03T07:48:00.108128168Z PostgreSQL init process complete; ready for start up. postgres-1 | 2026-11-03T07:48:00.108128960Z postgres-1 | 2026-11-03T07:48:00.117691210Z 2026-11-03 07:48:00.117 UTC [1] LOG: starting PostgreSQL 16.15 on aarch64-unknown-linux-musl, compiled by gcc (Alpine 15.2.0) 15.2.0, 64-bit postgres-1 | 2026-11-03T07:48:00.117704918Z 2026-11-03 07:48:00.117 UTC [1] LOG: listening on IPv4 address "0.0.0.0", port 5432 postgres-1 | 2026-11-03T07:48:00.117706210Z 2026-11-03 07:48:00.117 UTC [1] LOG: listening on IPv6 address "::", port 5432 postgres-1 | 2026-11-03T07:48:00.118972293Z 2026-11-03 07:48:00.118 UTC [1] LOG: listening on Unix socket "/var/run/postgresql/.s.PGSQL.5432" postgres-1 | 2026-11-03T07:48:00.120424710Z 2026-11-03 07:48:00.120 UTC [54] LOG: database system was shut down at 2026-11-03 07:48:00 UTC postgres-1 | 2026-11-03T07:48:00.122791210Z 2026-11-03 07:48:00.122 UTC [1] LOG: database system is ready to accept connections app-server-1 | 2026-11-03T07:48:05.167005837Z 2026-11-03T07:48:05.166996Z INFO app_server::batch_worker::worker: Worker d9aedc43-8487-4ed7-8adb-7ec0ab12010b (Spans) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.167023045Z 2026-11-03T07:48:05.167016Z INFO app_server::batch_worker::worker: Worker c85413e8-30fc-4f0b-94f9-2c0d9fb0d9fc (Spans) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.167031587Z 2026-11-03T07:48:05.167027Z INFO app_server::batch_worker::worker: Worker 64fd5cb1-d971-49fe-bba1-0f6124b52526 (Spans) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.167041629Z 2026-11-03T07:48:05.167037Z INFO app_server::worker: Worker 55177fd4-6333-47f0-883d-9c29ffdceac3 (SpansIndexer) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.167059754Z 2026-11-03T07:48:05.167048Z INFO app_server::worker: Worker 1474d538-12f2-46c0-8a80-e2b1adb319da (SpansIndexer) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.167075295Z 2026-11-03T07:48:05.167067Z INFO app_server::worker: Worker 18759d80-1b38-4453-8936-c627674c2087 (SpansIndexer) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.167098795Z 2026-11-03T07:48:05.167091Z INFO app_server::batch_worker::worker: Worker 77b656a8-e3d7-48a5-9e45-e7cc223a7747 (Spans) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.167157379Z 2026-11-03T07:48:05.166803Z WARN app_server::auth::cli_user: NEXT_INTERNAL_URL/NEXT_PUBLIC_URL unset; CLI-auth JWKS defaults to https://laminar.sh app-server-1 | 2026-11-03T07:48:05.173130420Z 2026-11-03T07:48:05.172992Z INFO app_server::worker: Queue 'notifications' prefetch_count=128 (override via NOTIFICATIONS_PREFETCH_COUNT) app-server-1 | 2026-11-03T07:48:05.173165462Z 2026-11-03T07:48:05.173018Z INFO app_server::worker: Spawning worker fc74172f-1606-4a98-beae-64b15d0a85d9 (Notifications) instance 0 app-server-1 | 2026-11-03T07:48:05.176821837Z 2026-11-03T07:48:05.173101Z INFO app_server::worker: Worker fc74172f-1606-4a98-beae-64b15d0a85d9 (Notifications) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.176852004Z 2026-11-03T07:48:05.173158Z INFO app_server::worker: Spawning worker e8c69f5e-705f-4f7c-9c81-b8766ae33141 (Notifications) instance 1 app-server-1 | 2026-11-03T07:48:05.176856129Z 2026-11-03T07:48:05.173172Z INFO app_server::worker: Worker e8c69f5e-705f-4f7c-9c81-b8766ae33141 (Notifications) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.177158170Z 2026-11-03T07:48:05.177107Z INFO app_server: Spinning up full HTTP server app-server-1 | 2026-11-03T07:48:05.177369004Z 2026-11-03T07:48:05.177349Z INFO actix_server::builder: starting 2 workers app-server-1 | 2026-11-03T07:48:05.177398670Z 2026-11-03T07:48:05.177389Z INFO actix_server::server: Tokio runtime found; starting in existing Tokio runtime app-server-1 | 2026-11-03T07:48:05.177407337Z 2026-11-03T07:48:05.177402Z INFO actix_server::server: starting service: "actix-web-service-0.0.0.0:8000", workers: 2, listening on: 0.0.0.0:8000 app-server-1 | 2026-11-03T07:48:05.193138254Z 2026-11-03T07:48:05.193056Z INFO app_server::worker: Queue 'notification_deliveries' prefetch_count=128 (override via NOTIFICATION_DELIVERIES_PREFETCH_COUNT) app-server-1 | 2026-11-03T07:48:05.193157504Z 2026-11-03T07:48:05.193075Z INFO app_server::worker: Spawning worker f044d1b0-2716-4637-9983-dfc16b4d7070 (NotificationDeliveries) instance 0 app-server-1 | 2026-11-03T07:48:05.193171045Z 2026-11-03T07:48:05.193119Z INFO app_server::worker: Worker f044d1b0-2716-4637-9983-dfc16b4d7070 (NotificationDeliveries) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193172212Z 2026-11-03T07:48:05.193129Z INFO app_server::worker: Spawning worker 0e1ec949-831a-4cea-81dc-568e5b2dd812 (NotificationDeliveries) instance 1 app-server-1 | 2026-11-03T07:48:05.193180129Z 2026-11-03T07:48:05.193136Z INFO app_server::worker: Worker 0e1ec949-831a-4cea-81dc-568e5b2dd812 (NotificationDeliveries) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193181295Z 2026-11-03T07:48:05.193139Z INFO app_server::worker: Queue 'input_extraction_queue' prefetch_count=128 (override via INPUT_EXTRACTION_QUEUE_PREFETCH_COUNT) app-server-1 | 2026-11-03T07:48:05.193182045Z 2026-11-03T07:48:05.193141Z INFO app_server::worker: Spawning worker 9dcdc103-725a-480b-896c-2b1e8d868a8e (InputExtraction) instance 0 app-server-1 | 2026-11-03T07:48:05.193182712Z 2026-11-03T07:48:05.193151Z INFO app_server::worker: Worker 9dcdc103-725a-480b-896c-2b1e8d868a8e (InputExtraction) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193183379Z 2026-11-03T07:48:05.193156Z INFO app_server::worker: Spawning worker b8ad57f7-f873-4433-aba6-8d5071981325 (InputExtraction) instance 1 app-server-1 | 2026-11-03T07:48:05.193184004Z 2026-11-03T07:48:05.193162Z INFO app_server::worker: Worker b8ad57f7-f873-4433-aba6-8d5071981325 (InputExtraction) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193184670Z 2026-11-03T07:48:05.193164Z INFO app_server::worker: Queue 'user_task_regex_queue' prefetch_count=128 (override via USER_TASK_REGEX_QUEUE_PREFETCH_COUNT) app-server-1 | 2026-11-03T07:48:05.193190379Z 2026-11-03T07:48:05.193165Z INFO app_server::worker: Spawning worker 1c8200eb-7b7b-402d-b111-3966cb7d98c7 (UserTaskRegex) instance 0 app-server-1 | 2026-11-03T07:48:05.193198545Z 2026-11-03T07:48:05.193170Z INFO app_server::worker: Worker 1c8200eb-7b7b-402d-b111-3966cb7d98c7 (UserTaskRegex) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193199504Z 2026-11-03T07:48:05.193174Z INFO app_server::worker: Spawning worker d9e6b2c2-9c07-431c-9eb8-1c88b8b9b457 (UserTaskRegex) instance 1 app-server-1 | 2026-11-03T07:48:05.193200170Z 2026-11-03T07:48:05.193180Z INFO app_server::worker: Worker d9e6b2c2-9c07-431c-9eb8-1c88b8b9b457 (UserTaskRegex) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193200837Z 2026-11-03T07:48:05.193183Z INFO app_server::worker: Queue 'logs_queue' prefetch_count=128 (override via LOGS_QUEUE_PREFETCH_COUNT) app-server-1 | 2026-11-03T07:48:05.193201504Z 2026-11-03T07:48:05.193184Z INFO app_server::worker: Spawning worker 5933f700-94fe-46b0-82eb-dedbf52e90df (Logs) instance 0 app-server-1 | 2026-11-03T07:48:05.193202129Z 2026-11-03T07:48:05.193189Z INFO app_server::worker: Worker 5933f700-94fe-46b0-82eb-dedbf52e90df (Logs) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193203837Z 2026-11-03T07:48:05.193191Z INFO app_server::worker: Spawning worker 625b9e03-a0eb-4b73-91cb-a57e3cf21088 (Logs) instance 1 app-server-1 | 2026-11-03T07:48:05.193211712Z 2026-11-03T07:48:05.193195Z INFO app_server::worker: Worker 625b9e03-a0eb-4b73-91cb-a57e3cf21088 (Logs) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193212962Z 2026-11-03T07:48:05.193197Z INFO app_server::worker: Spawning worker 1784d140-e521-456e-80f5-f19a1928b70f (Logs) instance 2 app-server-1 | 2026-11-03T07:48:05.193213587Z 2026-11-03T07:48:05.193200Z INFO app_server::worker: Worker 1784d140-e521-456e-80f5-f19a1928b70f (Logs) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193214254Z 2026-11-03T07:48:05.193202Z INFO app_server::worker: Spawning worker fc9b76ef-65e2-4190-96d5-836a2270c7fc (Logs) instance 3 app-server-1 | 2026-11-03T07:48:05.193221420Z 2026-11-03T07:48:05.193207Z INFO app_server::worker: Worker fc9b76ef-65e2-4190-96d5-836a2270c7fc (Logs) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193222587Z 2026-11-03T07:48:05.193209Z INFO app_server::worker: Queue 'static_prompt_queue' prefetch_count=128 (override via STATIC_PROMPT_QUEUE_PREFETCH_COUNT) app-server-1 | 2026-11-03T07:48:05.193223295Z 2026-11-03T07:48:05.193210Z INFO app_server::worker: Spawning worker f7f894e0-6cb1-4537-ab14-aa32df857436 (StaticPrompt) instance 0 app-server-1 | 2026-11-03T07:48:05.193228879Z 2026-11-03T07:48:05.193218Z INFO app_server::worker: Worker f7f894e0-6cb1-4537-ab14-aa32df857436 (StaticPrompt) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193229754Z 2026-11-03T07:48:05.193221Z INFO app_server::worker: Spawning worker c3866638-4cb5-4516-b218-5a927390631b (StaticPrompt) instance 1 app-server-1 | 2026-11-03T07:48:05.193233295Z 2026-11-03T07:48:05.193226Z INFO app_server::worker: Worker c3866638-4cb5-4516-b218-5a927390631b (StaticPrompt) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193234087Z 2026-11-03T07:48:05.193228Z INFO app_server::worker: Queue 'sp_versioning_queue' prefetch_count=128 (override via SP_VERSIONING_QUEUE_PREFETCH_COUNT) app-server-1 | 2026-11-03T07:48:05.193234795Z 2026-11-03T07:48:05.193229Z INFO app_server::worker: Spawning worker bbced2c6-8ba0-4637-8c27-04019f86a972 (SpVersioning) instance 0 app-server-1 | 2026-11-03T07:48:05.193238087Z 2026-11-03T07:48:05.193233Z INFO app_server::worker: Worker bbced2c6-8ba0-4637-8c27-04019f86a972 (SpVersioning) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193238837Z 2026-11-03T07:48:05.193235Z INFO app_server::worker: Spawning worker 12f3474d-58c1-44d2-8452-02ea87da157a (SpVersioning) instance 1 app-server-1 | 2026-11-03T07:48:05.193243004Z 2026-11-03T07:48:05.193239Z INFO app_server::worker: Worker 12f3474d-58c1-44d2-8452-02ea87da157a (SpVersioning) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193246504Z 2026-11-03T07:48:05.193241Z INFO app_server::worker: Queue 'user_template_versioning_queue' prefetch_count=128 (override via USER_TEMPLATE_VERSIONING_QUEUE_PREFETCH_COUNT) app-server-1 | 2026-11-03T07:48:05.193247420Z 2026-11-03T07:48:05.193242Z INFO app_server::worker: Spawning worker 2203c8b2-75cc-4e9c-b4b1-a14cee2ccfdf (UserTemplateVersioning) instance 0 app-server-1 | 2026-11-03T07:48:05.193251337Z 2026-11-03T07:48:05.193246Z INFO app_server::worker: Worker 2203c8b2-75cc-4e9c-b4b1-a14cee2ccfdf (UserTemplateVersioning) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193252129Z 2026-11-03T07:48:05.193248Z INFO app_server::worker: Spawning worker 197ef589-39da-4cdd-8ca1-17a5b6483d80 (UserTemplateVersioning) instance 1 app-server-1 | 2026-11-03T07:48:05.193255462Z 2026-11-03T07:48:05.193251Z INFO app_server::worker: Worker 197ef589-39da-4cdd-8ca1-17a5b6483d80 (UserTemplateVersioning) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193262462Z 2026-11-03T07:48:05.193253Z INFO app_server::worker: Queue 'sp_regex_extraction_queue' prefetch_count=128 (override via SP_REGEX_EXTRACTION_QUEUE_PREFETCH_COUNT) app-server-1 | 2026-11-03T07:48:05.193263379Z 2026-11-03T07:48:05.193254Z INFO app_server::worker: Spawning worker 4a711f7a-dcb6-47bd-b710-639aa58de80d (SpRegexExtraction) instance 0 app-server-1 | 2026-11-03T07:48:05.193268295Z 2026-11-03T07:48:05.193259Z INFO app_server::worker: Worker 4a711f7a-dcb6-47bd-b710-639aa58de80d (SpRegexExtraction) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193269212Z 2026-11-03T07:48:05.193261Z INFO app_server::worker: Spawning worker ae437b3e-efa3-411d-90a7-2ee5f4bf75e6 (SpRegexExtraction) instance 1 app-server-1 | 2026-11-03T07:48:05.193277212Z 2026-11-03T07:48:05.193265Z INFO app_server::worker: Worker ae437b3e-efa3-411d-90a7-2ee5f4bf75e6 (SpRegexExtraction) connected and ready to process messages app-server-1 | 2026-11-03T07:48:05.193353962Z 2026-11-03T07:48:05.193318Z INFO actix_server::builder: starting 2 workers app-server-1 | 2026-11-03T07:48:05.193358212Z 2026-11-03T07:48:05.193328Z INFO actix_server::server: Tokio runtime found; starting in existing Tokio runtime app-server-1 | 2026-11-03T07:48:05.193359462Z 2026-11-03T07:48:05.193330Z INFO actix_server::server: starting service: "actix-web-service-0.0.0.0:8002", workers: 2, listening on: 0.0.0.0:8002 frontend-1 | 2026-11-03T07:48:11.443949048Z line: '12298', frontend-1 | 2026-11-03T07:48:11.443949590Z routine: 'ATExecDropConstraint' frontend-1 | 2026-11-03T07:48:11.443950090Z } frontend-1 | 2026-11-03T07:48:11.465114465Z ✓ Postgres migrations applied successfully frontend-1 | 2026-11-03T07:48:11.465826340Z Skipped provisioning the ClickHouse Postgres role: CLICKHOUSE_POSTGRES_USER and CLICKHOUSE_POSTGRES_PASSWORD are not set (see README, SQL access to Postgres entities) frontend-1 | 2026-11-03T07:48:11.467855673Z ✓ Postgres data initialized successfully frontend-1 | 2026-11-03T07:48:11.480919715Z Fetching model costs... frontend-1 | 2026-11-03T07:48:22.003069678Z Continuing without model costs data... frontend-1 | 2026-11-03T07:48:22.003137262Z Applying ClickHouse schema. This may take a while... frontend-1 | 2026-11-03T07:48:22.003154137Z Failed to initialize model costs: [TypeError: fetch failed] { frontend-1 | 2026-11-03T07:48:22.003156845Z [cause]: Error [ConnectTimeoutError]: Connect Timeout Error (attempted addresses: 185.199.111.133:443, timeout: 10000ms) frontend-1 | 2026-11-03T07:48:22.003158470Z at ignore-listed frames { frontend-1 | 2026-11-03T07:48:22.003159762Z code: 'UND_ERR_CONNECT_TIMEOUT' frontend-1 | 2026-11-03T07:48:22.003178845Z } frontend-1 | 2026-11-03T07:48:22.003180595Z } frontend-1 | 2026-11-03T07:48:22.017929845Z Turning off the ClickHouse `pg` database: CLICKHOUSE_POSTGRES_USER and CLICKHOUSE_POSTGRES_PASSWORD are not set (see README, SQL access to Postgres entities) frontend-1 | 2026-11-03T07:48:28.964836000Z clickhouse-migrations : The migration(s) 1_squashed.sql, 2_labels-to-tags.sql, 3_eval-scores-span-tags.sql, 4_views.sql, 5_trace-summaries.sql, 6_trace-summary-views.sql, 7_versioned-datasets.sql, 8_eval_to_dataset_link.sql, 9_success_status.sql, 10_trace_browser_session.sql, 11_tags_re_index.sql, 12_events_source.sql, 13_traces_replacing.sql, 14_signal_runs.sql, 15_span_names.sql, 16_logs.sql, 17_signal_runs_fix.sql, 18_remove_span_ngram_idx.sql, 19_denorm_evals.sql, 20_span_events_column.sql, 21_signal_events_update.sql, 22_events_to_clusters.sql, 23_new_evals_datapoints_columns.sql, 24_evals_rmt_final.sql, 25_clusters.sql, 26_root_span_input_output.sql, 27_notification_logs.sql, 28_indexed_clusters.sql, 29_events_to_clusters_rmt.sql, 30_hotfix_clusters_view.sql, 31_signal_runs_mode.sql, 32_evaluation_datapoints_order_key.sql, 33_spans_new_order_with_projection.sql, 34_hide_l0_clusters.sql, 35_signal_messages_ttl.sql, 36_trace_tags.sql, 37_signal_runs_steps_processed.sql, 38_notifications.sql, 39_signal_events_severity.sql, 40_all_clusters_events_views.sql, 41_evaluation_datapoints_view_top_span_id.sql, 42_labeling_queue_items.sql, 43_llm_messages.sql, 44_spans_input_new_message_indices.sql, 45_drop_llm_messages_dict.sql, 46_deduped_content_project_scope.sql, 47_clusters_v0_drop_centroid.sql, 48_clusters_centroid_dim_768.sql, 49_trace_cache_reasoning_tokens.sql, 50_drop_events_tags.sql, 51_signal_token_columns.sql, 52_clusters_centroid_at_naming.sql, 53_traces_v0_start_time_params.sql, 54_traces_agg.sql, 55_evaluation_datapoints_v0_traces_agg.sql, 56_system_prompt_versions.sql, 57_signal_event_summaries.sql, 58_drop_unused_tables.sql, 59_signal_runs_stages.sql, 60_clusters_size_at_naming.sql, 61_spans_token_details.sql, 62_signal_version.sql, 63_evaluation_datapoints_v0_pushdown.sql, 64_unique_content.sql, 65_trace_signal_clusters.sql, 66_pii_dual_storage.sql, 67_user_template_versions.sql, 68_clusters_parent_id_index.sql, 69_signal_run_credit_applied.sql, 70_spans_original_size.sql, 71_clusters_replacing_deleted.sql, 72_trace_agent_versions.sql, 73_pg_entity_views.sql, 74_tool_definition_versions.sql, 75_signal_events_named_cluster_details.sql, 76_agent_prompts.sql, 77_drop_tool_definition_versions.sql, 78_pg_dashboard_views.sql, 79_trace_release.sql, 80_task_id.sql was successfully applied! frontend-1 | 2026-11-03T07:48:29.011571166Z ✓ ClickHouse schema applied successfully frontend-1 | 2026-11-03T07:48:29.011631250Z CLICKHOUSE_RO_USER equals CLICKHOUSE_USER; skipping source-privilege revoke. Use a dedicated read-only ClickHouse user in production. frontend-1 | 2026-11-03T07:48:29.104238041Z 2026-11-03T07:48:29.103Z WARN [Better Auth]: [better-auth] Warning: your BETTER_AUTH_SECRET appears low-entropy. Use a randomly generated secret for production. frontend-1 | 2026-11-03T07:48:29.105058875Z [traces_agg_backfill_lock] REDIS_URL is not set, so there is no cross-replica lock. If you run MORE THAN ONE frontend replica, set REDIS_URL or run a single replica for the first boot — concurrent replicas would duplicate this backfill's writes. frontend-1 | 2026-11-03T07:48:29.113762250Z No projects need default signals, skipping seeding frontend-1 | 2026-11-03T07:48:29.118237333Z [traces-agg-backfill] traces_replacing is empty; nothing to migrate frontend-1 | 2026-11-03T07:48:29.118420541Z [signal_clusters_backfill_lock] REDIS_URL is not set, so there is no cross-replica lock. If you run MORE THAN ONE frontend replica, set REDIS_URL or run a single replica for the first boot — concurrent replicas would duplicate this backfill's writes. frontend-1 | 2026-11-03T07:48:29.125170541Z Found 3 Quickwit index configuration(s) frontend-1 | 2026-11-03T07:48:29.139375541Z Found 2 existing Quickwit index(es) frontend-1 | 2026-11-03T07:48:29.139980708Z [signal_clusters_rebuild_lock] REDIS_URL is not set, so there is no cross-replica lock. If you run MORE THAN ONE frontend replica, set REDIS_URL or run a single replica for the first boot — concurrent replicas would duplicate this backfill's writes. frontend-1 | 2026-11-03T07:48:29.156075250Z Creating index "events"... frontend-1 | 2026-11-03T07:48:29.167294291Z ✓ Index "events" created successfully frontend-1 | 2026-11-03T07:48:29.169260791Z Creating index "signal_events"... frontend-1 | 2026-11-03T07:48:29.181608875Z [signal-clusters-rebuild] copied 0 clusters into signal_event_clusters_v2 frontend-1 | 2026-11-03T07:48:29.188117041Z [signal-clusters-rebuild] delta: re-copied 0 changed clusters, tombstoned 0 deleted ones frontend-1 | 2026-11-03T07:48:29.192464208Z [signal-clusters-rebuild] swapped; restart the app-server to start clustering on the new table frontend-1 | 2026-11-03T07:48:29.196449000Z [signal-clusters-rebuild] delta2: re-copied 0 clusters written during the swap; the old table is now old_unpartitioned_signal_event_clusters frontend-1 | 2026-11-03T07:48:31.173172709Z ✓ Index "signal_events" created successfully frontend-1 | 2026-11-03T07:48:31.178344667Z Creating index "spans_v2"... frontend-1 | 2026-11-03T07:48:33.170761793Z ✓ Index "spans_v2" created successfully frontend-1 | 2026-11-03T07:48:33.171061002Z ✓ Quickwit indexes initialized successfully frontend-1 | 2026-11-03T07:48:33.321607127Z 2026-11-03T07:48:33.321Z WARN [Better Auth]: [better-auth] Warning: your BETTER_AUTH_SECRET appears low-entropy. Use a randomly generated secret for production. frontend-1 | 2026-11-03T07:48:33.479947419Z 2026-11-03T07:48:33.479Z WARN [Better Auth]: [better-auth] Warning: your BETTER_AUTH_SECRET appears low-entropy. Use a randomly generated secret for production.

Laminar

Overview

Why Laminar instead of LangChain

What it does well

Similar Open Source Tools

Mem0

Limitations

Who should use it

FAQ

Verdict

Self-host Laminar with Docker

Download the compose file

Create .env with fresh secrets

Start it

First run

Project README

GitHub Repository Metrics

Supported Platforms

The modern standard for Protobuf workflows

Maintainer? Add the badge

LiteLLM

Langfuse