Langsmith Python Packages

graphharbor-runtime

Enterprise-grade, open-source LangGraph Agent Server powered by PostgreSQL checkpoints & Redis distributed workers. Subagent traceability & SSE resilience.

graphharbor

Enterprise-grade, open-source LangGraph Agent Server powered by PostgreSQL checkpoints & Redis distributed workers. Subagent traceability & SSE resilience.

funcchain

⛓️ build cognitive systems, pythonic

langgraph-runtime-pg

Open-source, self-hosted LangGraph Agent Server. Production Postgres + Redis. Same SDK. Same Studio. Zero code changes.

langhost

Open-source, self-hosted LangGraph Agent Server. Production Postgres + Redis. Same SDK. Same Studio. Zero code changes.

agent-panorama

See what your AI agents do, whether it's worth it, and what it costs - a manager-readable report + local dashboard from Langfuse/LangSmith traces (or a one-line live callback). Open source, runs locally.

mlflow-langsmith

Import selected LangSmith traces into MLflow as native MLflow traces for debugging, comparison, and evaluation dataset creation.

agent-nexus-cli

Nexus is an autonomous CLI coding agent powered by LangGraph and MCP. It plans complex tasks, persists context via SQLite, and securely orchestrates tools. Features specialized Architect/Code modes, real-time metrics, and human-in-the-loop safety for production workflows.

llm-failure-atlas

A graph-based failure modeling and deterministic detection system for LLM agent runtimes.

promplate-trace

integrate with @langfuse or langsmith - plug-and-play observability for @promplate

graphobs

Graph Observability Kit (graphobs) is a Python library for contract-first observability in graph-based applications. It helps teams describe graph state boundaries once, then reuse those declarations for trace payloads, structured logs, and validation.

dash-langsmith

Dash plugin for automatic Dash MCP tracing to LangSmith

ooai-persistence

Typed persistence utilities for LangGraph-based OOAI applications.

docket-runtime

Observability-platform-agnostic triage runtime for LLM agent traces: classifies traces against a YAML failure-mode taxonomy, clusters failures, and drafts issues into trackers for human review.

sunder-cli

An agentic zero-trust sandbox testing framework for enterprise codebases

trace2train

Local CLI to turn failed AI agent traces (wrong tool, bad args, over-refusals) from LangSmith/Langfuse into clean SFT/DPO fine-tuning data

langgraph-sfm

Causal intent monitoring for LangGraph agents.