v0.2.0 · Self-host free · BSL 1.1

Your agent failed.
Which tool broke
— and why?

Trace what your agents called. Find what broke, what's expensive, and what's unsafe. For MCP servers, get health checks, schema drift alerts, and security scanning built in.

Not another prompt, eval, or simulation platform. LangSight monitors the runtime layer: the tools your agents depend on.
$pip install langsight&&langsight init
LangChain · CrewAI · Pydantic AIPostgres + ClickHouse1,003 tests · 77% coverage
langsight · session trace

What question are you
trying to answer?

Use LangSight with LangWatch, Langfuse, or LangSmith — not instead of them. They evaluate model behavior. LangSight monitors the tool layer underneath.

QuestionBest tool
Did the prompt/model perform well?LangWatch / Langfuse / LangSmith
Should I change prompts or eval policy?LangWatch / Langfuse / LangSmith
Is my server CPU/memory healthy?Datadog / New Relic
Which tool call failed in production?LangSight
Is an MCP server unhealthy or drifting?LangSight
Is an MCP server exposed or risky?LangSight
Why did this session cost $47 instead of $3?LangSight

LLM quality is only
half the problem.

Teams already have ways to inspect prompts and eval scores. What they still cannot answer fast enough:

Which of 15 tools failed?

Your orchestrator calls 15 tools across 4 MCP servers. Something returned bad data. Without traces, you spend hours replaying requests — in the dark.

MCP server degraded silently

Schema changed. Latency spiked 10x. Auth expired. The agent keeps calling, gets bad data, and hallucinates. You find out from users, not alerts.

$4,200 in unexpected tool costs

A sub-agent retries geocoding-mcp 47 times per session. Nobody noticed until the invoice arrived. You need cost attribution at the tool level, not the model level.

Is this MCP server safe to run?

66% of community MCP servers have critical code smells. Tool poisoning attacks are real. You need automated scanning, not hope.

Four pillars of
runtime observability.

01

Action Traces

See the exact sequence of tool calls, handoffs, failures, and costs across a full agent session. Multi-agent trees reconstructed automatically from parent_span_id.

$ langsight sessions --id sess-f2a9b1

sess-f2a9b1  (support-agent)
├── jira-mcp/get_issue        89ms  ✓
├── postgres-mcp/query        42ms  ✓
├──  → billing-agent          handoff
│   ├── crm-mcp/update    120ms  ✓
│   └── slack-mcp/notify    —   ✗  timeout

Root cause: slack-mcp timed out at 14:32
02

MCP Health

Detect down, slow, stale, or changed MCP servers before they silently corrupt agent behavior. Schema drift detection catches breaking changes in minutes.

$ langsight mcp-health

Server           Status   Latency   Schema    Tools
snowflake-mcp    ✅ UP    142ms     Stable    8
slack-mcp        ⚠️ DEG  1,240ms   Stable    4
jira-mcp         ❌ DOWN  —         —         —
postgres-mcp     ✅ UP    31ms      Changed   5
03

MCP Security

Scan for CVEs, OWASP MCP Top 10, tool poisoning signals, weak auth, and risky configs. Run in CI with --ci to block deploys on CRITICAL findings.

$ langsight security-scan

CRITICAL  jira-mcp      CVE-2025-6514
  Remote code execution in mcp-remote

HIGH      slack-mcp     OWASP-MCP-01
  Tool description contains injection pattern

HIGH      postgres-mcp  OWASP-MCP-04
  No authentication configured
04

Cost Attribution

Move from "the invoice is $4,200" to "billing-agent's geocoding MCP retries 47x per session at $0.005/call."

$ langsight costs --hours 24

Tool                 Calls  Failed  Cost     %
geocoding-mcp        2,340  12      $1,872   44.6%
postgres-mcp/query   890    3       $445     10.6%
claude-3.5 (LLM)    156    0       $312     7.4%

Zero to traced
in 5 minutes.

1

Install & discover

30 seconds

pip install langsight
langsight init

# Auto-discovered 4 MCP servers
2

Instrument your agent

2 lines of code

from langsight.sdk import LangSightClient

client = LangSightClient(url="...")
traced = client.wrap(mcp, server_name="pg")
3

See everything

real-time

langsight sessions
langsight mcp-health
langsight security-scan
langsight costs --hours 24

Built for production.

Multi-Agent Call Trees

Core

parent_span_id links sub-agent calls across any depth. See the path from orchestrator to leaf tool.

Session Replay

v0.2

Re-execute any session against live MCP servers. Compare two runs side-by-side to see what changed.

Anomaly Detection

v0.2

Z-score analysis against 7-day baseline. Warning at |z|>=2, critical at |z|>=3. No manual thresholds.

Agent SLO Tracking

v0.2

Define success_rate and latency_p99 targets per agent. Get alerted before you breach availability.

AI Root Cause Analysis

4 LLMs

langsight investigate sends evidence to Claude, GPT-4o, Gemini, or Ollama and returns remediation steps.

Prometheus Metrics

v0.2

Native /metrics endpoint. Plug into your existing Grafana stack. Request counts, latencies, SSE connections.

Drop into any framework.

LangChain
LangGraph · Langflow
CrewAI
Multi-agent orchestration
Pydantic AI
Type-safe agents
LibreChat
Self-hosted chat
OTLP
Any OpenTelemetry framework
Claude · Cursor
Auto-discovered by init

Use alongside Langfuse, LangWatch, or LangSmith

They trace the LLM reasoning layer (what the model decided). LangSight traces the action layer (what the agent called, what failed, what it cost). Different questions, same agent.

BSL 1.1 · Self-host free forever

Your data. Your infra.
No vendor dependency.

Self-host on your own infrastructure. No data ever leaves your network. No paid tiers. No gated features. No usage limits.

Your data stays yours

PostgreSQL + ClickHouse via docker compose up. Both fully under your control. No telemetry phoning home.

No vendor lock-in

BSL 1.1 — converts to Apache 2.0 after 4 years. Fork it, modify it, embed it. The only restriction: don't resell it as a hosted service.

5-minute setup

One script generates secrets, starts 5 containers, seeds demo data. You're looking at traces before your coffee is ready.

Own the runtime layer
of your agent systems.

If your agents depend on MCP, LangSight keeps that dependency observable, reliable, and secure.

Trace what broke. Find what's expensive. Scan what's unsafe.

$pip install langsight && langsight init
BSL 1.1 — self-host freeNo account neededdocker compose up — full stack in 5 min