AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Observability/
lmnr
lmnr logo

lmnr

Active·★ 3.5k·Apache-2.0·Updated 2026-11-20
★ Essential★ Trending

Laminar is an open-source observability platform purpose-built for AI agents. The README lists tracing with an OpenTelemetry-native SDK that can trace Vercel AI SDK, Browser Use, Stagehand, LangChain, OpenAI, Anthropic, Gemini and more with one line of code; evals with an extensible SDK and CLI for running locally or in CI/CD plus a UI to visualise and compare results; AI monitoring that defines events with natural-language descriptions to track issues and logical errors; SQL access to traces, metrics and events through a built-in editor and API; a dashboard builder; and data annotation and datasets.

It is written in Rust with a custom real-time engine for viewing traces as they happen. The easiest start is the managed platform at laminar.sh. To self-host, clone the repository and run `docker compose up -d`, which gives a lightweight but full-featured stack with the UI at localhost:5667; you must configure the SDK's base URL and ports to match, and for production the README recommends the managed platform or the larger docker-compose-full.yml. TypeScript and Python quickstarts are provided. The code is Apache-2.0 licensed.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-11-15.

License
Apache-2.0
Latest release
v0.3.4 · 2026-11-10
Last commit
2026-11-13
Contributors
34
Forks
264
Open issues and PRs
160
First published
2024-08-29

Source: GitHub, npm and PyPI public APIs.

#AI Observability#Tracing#LLM Evals#AI Monitoring#OpenTelemetry
$ Install
$ git clone https://github.com/lmnr-ai/lmnr && cd lmnr && docker compose up -d
↗ Visit site★ GitHub
01

Features

01OpenTelemetry-native tracing SDK with support for various AI SDKs (Vercel AI SDK, LangChain, OpenAI, etc.).
02Unopinionated, extensible SDK and CLI for running evals, with a UI for visualizing and comparing results.
03AI monitoring with the ability to define events using natural language descriptions to track agent behavior.
04SQL access to all collected data (traces, metrics, events) via a built-in SQL editor and API.
05High-performance architecture written in Rust, featuring a custom real-time engine and ultra-fast full-text search.
02

Why choose it

+OpenTelemetry-native tracing, with one-line instrumentation for Vercel AI SDK, Browser Use, Stagehand, LangChain, OpenAI, Anthropic and Gemini.
+Evals you can run locally or in CI/CD with a UI to compare results.
+SQL editor and API over traces, metrics and events, plus dashboards, datasets and annotation.
+Rust implementation with real-time trace viewing; self-hostable with Docker Compose and Apache-2.0 licensed.
03

Trade-offs

!The simple `docker compose up -d` stack is for quickstart or light use; for production the README recommends the managed platform or the larger full compose file.
!Self-hosting requires configuring the SDK's base URL and ports to point at your instance.
!It targets agent observability, so it overlaps with, but is narrower than, general application monitoring tools.
04

Maintenance check

ActiveChecked: 2026-11-07
Last commit
2026-11-02
Commits, last 90 days
100+
Releases, last 90 days
8
Latest release
v0.3.3 (2026-11-02)
Open issues
162
Recent issues with at least one comment
0/2
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 21, 13, 14, 39, 21, 26, 20, 23, 28, 32, 22, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #697 Is there a way to specify the HTTP or gRPC app server URL without including the port number?11 comments · 2025-07-11
  • #173 Add "favorite" button to traces11 comments · 2024-11-07
  • #797 Unable to View Traces on Laminar Traces Page Due to **StatusCode.DEADLINE_EXCEEDED** Error10 comments · 2025-08-14
  • #1039 browser-use webpage rendering issue9 comments · 2025-11-18
  • #2176 Self-hosted: ClickHouse `system.*_log` tables grow without bound, dominating disk and CPU8 comments · 2026-08-01

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

Vercel AI SDK
Supported
Verified via docs
LangChain
Supported
Verified via docs
OpenAI
Supported
Verified via docs
Anthropic
Supported
Verified via docs
Gemini
Supported
Verified via docs
Stagehand
Supported
Verified via docs
06

Quick start

1
$ git clone https://github.com/lmnr-ai/lmnr
2
$ cd lmnr
3
$ docker compose up -d
07

Use cases

↳Debugging and understanding the execution flow and internal states of AI agents.
↳Evaluating the performance, quality, and reliability of AI agents and their responses.
↳Monitoring AI agents in production for anomalies, logical errors, and custom business behaviors.
08

Alternatives

⚡Top VS:
VSkeep★12.5k→VSopenstatus★9.3k→VSmcp-context-forge★4.9k→VSarchestra★4.5k→
keep logo
keep★ 12.5k
The open-source AIOps and alert management platform
VSCompare→
openstatus logo
openstatus★ 9.3k
🫖 Status page with uptime monitoring & API monitoring as code 🫖
VSCompare→
mcp-context-forge logo
mcp-context-forge★ 4.9k
A Model Context Protocol (MCP) Gateway & Registry. Serves as a central management point for tools, resources, and prompts that can be accessed by MCP-compatible LLM applications. Converts REST API endpoints to MCP, composes virtual MCP servers with added security and observability, and converts between protocols (stdio, SSE, Streamable HTTP).
VSCompare→
archestra logo
archestra★ 4.5k
Archestra is an open-source enterprise AI platform: an internal chat assistant, LLM gateway, MCP gateway and registry, A2A gateway and agent runtime, built on SSO, RBAC, sandboxed execution, guardrails and OpenTelemetry.
VSCompare→
AgentBench logo
AgentBench★ 3.8k
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
VSCompare→
agentgateway logo
agentgateway★ 6.3k
Next Generation Agentic Proxy for AI Agents and MCP servers
VSCompare→
metamcp logo
metamcp★ 2.8k
MCP Aggregator, Orchestrator, Middleware, Gateway in one docker
VSCompare→
MCPJungle logo
MCPJungle★ 1.6k
Self-hosted MCP Gateway and Registry for AI agents
VSCompare→
See all alternatives →

Featured in these lists

  • Best Open-Source AI Agent Observability and Tracing Tools

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
lmnr-ai /
lmnr
↗

Open-source observability platform for AI agents: tracing, evals and SQL access

3.5k264Apache-2.0
Last commit2d ago
StatusActive
CategoryObservability
Contributors34
Latest releasev0.3.4
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.